Systems and methods for determining a degree or rate of error for treatments at a field are disclosed herein. In some embodiments, a system receives first data corresponding to a first agronomic treatment at a field and second data corresponding to a second agronomic treatment at the field. The system uses the first and second data to determine differences and overlaps between characteristics of the first and second data to quantify an error rate at individual subsets of the field. Based on the quantified error rate, a number of metrics and yield data may be interpreted differently or modified to fit the result of the quantified error rate. The system uses the quantified error rate to predict the effectiveness of treatments, modify the rate of experienced yields at a field, and recommend real-time and subsequent corrective actions to take at the field.
Embodiments of the disclosed technologies are capable of inputting, to a machine-learned classifier that has been created using a set of neural network-based models, multi-band digital image data that represents an aerial view of an agricultural field location containing an horticultural product; outputting, by the classifier, annotated image data, the annotated image data comprising annotation data indicative of individual instances of the horticultural product in the agricultural field location; using the annotated image data, computing a first predicted yield for the agricultural field location; adjusting the first predicted yield by a scaling factor to produce a second predicted yield for the agricultural field location.
Embodiments of the disclosed technologies are capable of inputting, to a machine-learned model that has been trained to recognize a horticultural product in digital imagery, digital video data comprising frames that represent a view of the horticultural product in belt-assisted transit from a picking area of a field to a harvester bin; outputting, by the machine-learned model, annotated video data; using the annotated video data, computing quantitative data comprising particular counts of the individual instances of the horticultural product associated with particular timestamp data; using the timestamp data, mapping the quantitative data to geographic location data to produce a digital yield map; causing display of the digital yield map on a field manager computing device.
A computer-implemented method for recommending agricultural activities is implemented by an agricultural intelligence computer system in communication with a memory. The method includes receiving a plurality of field definition data, retrieving a plurality of input data from a plurality of data networks, determining a field region based on the field definition data, identifying a subset of the plurality of input data associated with the field region, determining a plurality of field condition data based on the subset of the plurality of input data, identifying a plurality of field activity options, determining a recommendation score for each of the plurality of field activity options based at least in part on the plurality of field condition data, and providing a recommended field activity option from the plurality of field activity options based on the plurality of recommendation scores.
G06Q 10/06 - Resources, workflows, human or project managementEnterprise or organisation planningEnterprise or organisation modelling
G06Q 10/04 - Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
Systems and methods for identifying operational abnormalities based on data received from an agricultural implement performing a task in an agricultural field are described herein. In an embodiment, a system receives time-series data captured from an agricultural implement performing an agronomic activity on an agricultural field, the time-series data including, for each of a plurality of timestamps, a location of the agricultural implement. The system identifies a plurality of passes in the time-series data and using the identified plurality of passes, identifies a plurality of location on the agricultural field in which the activity performed by the agricultural implement included a particular operational abnormality. The system generates a map of operational abnormalities for the agricultural field, the map of operational abnormalities including the plurality of locations on the agricultural field in which the activity performed by the agricultural implement included the particular operational abnormality.
In some embodiments, a computer-implemented method for predicting agronomic field property data for one or more agronomic fields using a trained machine learning model is disclosed. The method comprises receiving, at an agricultural intelligence computer system, agronomic training data; training a machine learning model, at the agricultural intelligence computer system, using the agronomic training data; in response to receiving a request from a client computing device for agronomic field property data for one or more agronomic fields, automatically predicting the agronomic field property data for the one or more agronomic fields using the machine learning model configured to predict agronomic field property data; based on the agronomic field property data, automatically generating a first graphical representation; and causing to display the first graphical representation on the client computing device.
A method for controlling application of agrichemical products, comprises acquiring remotely sensed digital image data: developing a prescription to apply at least one agrichemical product in a variable manner based on at least the digital image data, wherein the prescription describes a plurality of passes of a particular autonomous vehicle over a field to apply the at least one agrichemical product: applying the at least one agrichemical product to a crop in the variable manner by the particular autonomous vehicle according to the prescription.
Systems and methods for improving graphical displays of field data are described herein. In an embodiment, a system generates a plurality of data files by performing, for each data file of the plurality of data files: identifying a start condition; in response to identifying the start condition, generating a new data file; recording data of an apparatus moving through an agricultural field in the new data file, the data comprising locations of the apparatus during said recording; identifying a stop condition; and, in response to identifying the stop condition, storing the new data file. The system causes displaying a field map corresponding to the agricultural field through a graphical user interface. When the system receives input through the graphical user interface selecting multiple locations on the field map, the system identifies, for each selected location of the multiple locations, a corresponding data file of the plurality of data files and generates and displays through the graphical user interface, a geographic region comprising locations in the identified corresponding data files, the geographic region being bounded by locations in one or more of the identified corresponding data files. The system may further update the graphical user interface to include a data panel corresponding to the geographic region.
G06F 3/00 - Input arrangements for transferring data to be processed into a form capable of being handled by the computerOutput arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
A vehicle may be programmed to traverse a field while using sensors to detect objects and operating in a first image capture mode, for example, capturing low-resolution images of objects in the field, typically crops. Under program control, depending on whether an object inna low-resolution digital image is recognized as a crop, and whether the object is in an expected geo-location for crops, the vehicle may cease traversing temporarily and switch to a second image capture mode, for example, capturing a high-resolution image of the object, for use in disease analysis or classification, weed analysis or classification, alert notifications or other messages, or other processing.
In some embodiments, a system and a computer-implemented method for integrating voice-based interface in agricultural systems are disclosed. A method comprises: receiving speech data of a spoken voice command comprising a request for agricultural information; transmitting the speech data to a voice service provider to transform the speech data to a sequence of request text strings; receiving the sequence of request text strings comprising an intent string that indicates a category of the spoken voice command; based on the sequence of request text strings, generating queries for obtaining result sets of agricultural data relevant to the category of the spoken voice command; transmitting the queries to agricultural data repositories; receiving the result sets of agricultural data; based on the result sets, generating control signals for modifying controls implemented in an agricultural machine; transmitting the control signals to the agricultural machine to control agricultural tasks performed by the agricultural machine.
An example computer-implemented method includes receiving a plurality of agricultural data records including yield properties of products grown in fields and raw field features of the fields. The method also includes transforming the raw field features into distinct feature classes that characterize key features affecting yield of the one or more products, and generating, using data from the plurality of agricultural data records and the distinct feature classes, genomic-by-environmental relationships between one or more products, yield properties of the one or more products, and field features associated with the one or more products. Further, the method includes generating, based at least in part on the genomic-by-environmental relationships, predicted yield performance for a set of products associated with one or more target environments, generating product recommendations for the one or more target environments based on the predicted yield performance for the set of products, and providing one or more instructions configured to cause display of the product recommendations.
In an embodiment, a computer-implemented method of generating and displaying a comprehensive depiction of a weather element comprises: based on archived forecast model and observed data, training a machine learning model; calibrating current forecast data by applying the machine learning model to yield a calibrated forecast probability density function; displaying graphical representation of recently observed data and calibrated forecast probability density.
In an embodiment, a computer-implemented method of calibrating an imaging system in real-time, comprising: obtaining a first reading by a first sensor; establishing a dynamic link between the first reading and exposure time of a second sensor; using the dynamic link to control the exposure time of the second sensor; obtaining a second reading by the second sensor during the controlled exposure time; wherein the steps are performed by one or more computing devices.
B64C 39/02 - Aircraft not otherwise provided for characterised by special use
G01N 21/27 - ColourSpectral properties, i.e. comparison of effect of material on the light at two or more different wavelengths or wavelength bands using photo-electric detection
18.
REAL-TIME AGRICULTURAL RECOMMENDATIONS USING WEATHER SENSING ON EQUIPMENT
One technical field of the present disclosure is computer-implemented agricultural data processing. Another technical field is computer-implemented collection of real-time localized weather data and use of the weather data in agricultural operations and provide continuous monitoring of spray effectiveness, automated creation of field buffer zones to prevent application of products under conditions that will adversely affect adjacent crops or fields, automated generation of regulatory reports and automatic drift management.
A01C 23/00 - Distributing devices specially adapted for liquid manure or other fertilising liquid, including ammonia, e.g. transport tanks or sprinkling wagons
A01M 7/00 - Special adaptations or arrangements of liquid-spraying apparatus for purposes covered by this subclass
G06F 19/00 - Digital computing or data processing equipment or methods, specially adapted for specific applications (specially adapted for specific functions G06F 17/00;data processing systems or methods specially adapted for administrative, commercial, financial, managerial, supervisory or forecasting purposes G06Q;healthcare informatics G16H)
19.
DATA STORAGE AND TRANSFER DEVICE FOR AN AGRICULTURAL INTELLIGENCE COMPUTING SYSTEM
In an embodiment, the disclosed technologies include an apparatus for storing data and communicating data between a vehicle or an agricultural implement and a computing device. Embodiments include a non-conductive housing, an antenna coupled to the non-conductive housing, an integrated circuit coupled to the antenna, a thermally and electrically conductive housing coupled to the integrated circuit, at least one ground clip coupled to the thermally and electrically conductive housing, at least one other integrated circuit coupled to the at least one ground clip, a memory coupled to the other integrated circuit and arranged to at least temporarily store digital communications between a vehicle or an agricultural implement and the computing device, and a connector communicatively coupled to the memory and arranged to mate with a connector of the vehicle or the agricultural implement.
H01L 27/02 - Devices consisting of a plurality of semiconductor or other solid-state components formed in or on a common substrate including integrated passive circuit elements with at least one potential-jump barrier or surface barrier
H01L 27/06 - Devices consisting of a plurality of semiconductor or other solid-state components formed in or on a common substrate including integrated passive circuit elements with at least one potential-jump barrier or surface barrier the substrate being a semiconductor body including a plurality of individual components in a non-repetitive configuration
H01L 27/12 - Devices consisting of a plurality of semiconductor or other solid-state components formed in or on a common substrate including integrated passive circuit elements with at least one potential-jump barrier or surface barrier the substrate being other than a semiconductor body, e.g. an insulating body
20.
DIGITAL MODELING AND TRACKING OF AGRICULTURAL FIELDS FOR IMPLEMENTING AGRICULTURAL FIELD TRIALS
A system for implementing a trial in one or more fields is provided. In an embodiment, an agricultural intelligence computing system receives field data for a plurality of agricultural fields. Based, at least in part, on the field data for the plurality of agricultural fields, the agricultural intelligence computing system identifies one or more target agricultural fields. The agricultural intelligence computing system determines whether the one or more target agricultural fields are in compliance with the trial. The agricultural intelligence computing system then receives result data for the trial and, based on the result data, computes a benefit value for the trial.
A01B 79/02 - Methods for working soil combined with other agricultural processing, e.g. fertilising, planting
G06Q 10/04 - Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
G06Q 10/06 - Resources, workflows, human or project managementEnterprise or organisation planningEnterprise or organisation modelling
In an approach, a method for fusing point data with areal averages is performed by a computing system. The fusion procedure is coherent, in the sense that the computing system takes into account what the areal averages represent with respect to the point data. The overarching goal is to fit a model that takes into account the information derived from both data sets. The areal averages provide an estimate for what the integral of a model representing the behavior of the environmental variable should be over a particular district and the point values indicate the estimated value at particular locations. Thus, the integral of the fitted model over a district of the grid should approximate the value provided by the areal averages while also approximating the value provided by the point data for locations which are provided by the point data.
A method and apparatus for adjusting seeding rates at a sub-field level is provided. The method comprises identifying, using a server computer, a set of target agricultural fields with intra-field crop variability based upon historical agricultural data comprising historical yield data and historical observed agricultural data for a plurality of fields: receiving, a plurality of digital images of the set of target agricultural fields; determining, vegetative index values for geo-locations within each field of the set of target agricultural fields, vegetative index productivity scores for each sub-field zone of each target field in the set of target agricultural fields; receiving current seeding rates for each of the sub-field zones, determining, adjusted seeding rates using the vegetative index productivity scores corresponding to each of the sub-fields zones.
Systems and methods for improving the use of precipitation sensors are described herein. In an embodiment, an agricultural intelligence computer system receives one or more digital precipitation records comprising a plurality of digital data values representing precipitation amount at a plurality of locations. The system receives digital forecast records comprising a plurality of digital data values representing precipitation forecasts comprising predictions of precipitation at a plurality of lead times. The system identifies a plurality of forecast values for a plurality of locations at a particular time corresponding to a different lead time. The system uses the plurality of forecast values to generate a probability of precipitation at each of the plurality of locations. The system determines that the probability of precipitation at a particular location is lower than a stored threshold value and, in response, stores data identifying the particular location as having received no precipitation.
Systems and methods for utilizing a spatial statistical model to maximize efficacy in performing trials on agronomic fields are disclosed herein. In an embodiment, a system receives first yield data for a first portion of an agronomic field, the first portion of the agronomic field having received a first treatment, and second yield data, for a second portion of the agronomic field, the second portion of the agronomic field having received a second treatment that is different than the first treatment. The system uses a spatial statistical model and the first yield data to compute a yield value for the second portion of the agronomic field, the yield value indicating an agronomic yield for the second portion of the agronomic field if the second portion of the agronomic field had received the first treatment instead of the second treatment. Based on the computed yield value and the second yield data, the system selects the second treatment. In an embodiment, in response to selecting the second treatment, the system generates a prescription map, the prescription map including the second treatment. The system may also generate one or more scripts which, when executed by an application controller, cause the application controller to control an operating parameter of an agricultural implement to apply the second treatment
In an embodiment, digital images of agricultural fields are received at an agricultural intelligence processing system. Each digital image includes a set of pixels having pixel values, and each pixel value of a pixel includes a plurality of spectral band intensity values. Each spectral band intensity value describes a spectral band intensity of one band among several bands of electromagnetic radiation. For each of the agricultural fields, spectral band intensity values of each band are preprocessed at a field level using the digital images for that agricultural field resulting in preprocessed intensity values. The preprocessed intensity values are provided as input to a machine learning model. The model generates a predicted yield value for each field. The predicted yield value is used to update field yield maps of agricultural fields for forecasting and can be displayed via a graphical user interface (GUI) of a client computing device.
In an embodiment, a computer-implemented method for predicting subfield soil properties for an agricultural field comprises: receiving satellite remote sensing data that includes a plurality of images capturing imagery of an agricultural field in a plurality of optical domains; receiving a plurality of environmental characteristics for the agricultural field; generating a plurality of preprocessed images based on the plurality of satellite remote sensing data and the plurality of environmental characteristics; identifying, based on the plurality preprocessed images, a plurality of features of the agricultural field; generating a subfield soil property prediction for the agricultural field by executing one or more machine learning models on the plurality of features; transmitting the subfield soil property prediction to an agricultural computer system.
A computer-implemented method for generating an improved map of field anomalies using digital images and machine learning models is disclosed. In an embodiment, a method comprises: obtaining a shapefile that defines boundaries of an agricultural plot and boundaries of the field containing the plot; obtaining a plurality of plot images; calibrating and pre-processing the plurality of plot images to create a plot map of the agricultural plot at a plot level; based on the plot map, generating a plot grid; based on the plot grid and the plot map, generating a plurality of plot tiles; based on the plurality of plot tiles, generating, using a machine learning model and a plurality of image classifiers corresponding to one or more anomalies, a set of classified plot images that depicts at least one anomaly; based on the set of classified plot images, generating a plot anomaly map for the agricultural plot.
Techniques for providing improvements in agricultural science by optimizing irrigation treatment placements for testing are provided, including analyzing a plurality of digital images of a field to determine vegetation density changes in a sector of the field. The techniques proceed by comparing a distribution of pixel characteristics in the digital images for each field sector to determine sectors in which minimal density deviations are present. Instructions for irrigation placements and testing may be displayed or modified based on the results of the sector determinations.
A method for determining national crop yields during a growing season is accomplished using a server computer system that receives observed agricultural data records for a specific geo-location at a specific time. The server calculates weather index values from the agricultural data records that represent crop stress on plants. Geo-specific weather indices are generated from the weather index values, which then are aggregated to generate aggregated weather index data series. Representative features are selected from each aggregated weather index data series to create a covariate matrix for each geographic area. Crop yield for the geographic area is calculated using a linear regression model based on the covariate matrix for the specific geographic area. The server determines a national crop yield for the specific year as a sum of the crop yields for the specific geographic areas nationally adjusted using national yield adjustment instructions.
In an embodiment, a computer-implemented method of tracking soil sampling in a field is disclosed. The method comprises receiving, by a processor, digitally stored field map data and digitally stored sampling data. The method further comprises displaying, by the processor, a field map depicting the first set of sampling points in a computer-generated graphical user interface. In addition, the method comprises receiving a selection of a first sampling point and displaying first sampling data associated with the first sampling point. The method also comprises receiving an update indicating that a soil sample has been collected at the first sampling point. Finally, the method comprises determining a second sampling point at which a next soil sample is to be collected and displaying the second sampling point in the field map.
An integrated sensor system with modular sensors and wireless connectivity components for monitoring properties of field soil is described. The modular sensors are configured to determine measures of at least one property of soil. Processing units are configured to receive, from the sensors, the measures of at least one property of soil and calculate soil property data based on the measures. A transmitter is configured to receive the soil property data from the processing units, establish a communications connection with at least one computer device, and automatically transmit the soil property data to the at least one computer device via the communications connection. The communications connection may be a wireless connection established between the transmitter and a smart hub or a LoRA-enabled device. The sensors, the processors, and the transmitter may be installed inside a portable probe.
A system and processing methods for refining a convolutional neural network (CNN) to capture characterizing features of different classes are disclosed. In some embodiments, the system is programmed to start with the filters in one of the last few convolutional layers of the initial CNN, which often correspond to more class-specific features, rank them to hone in on more relevant filters, and update the initial CNN by turning off the less relevant filters in that one convolutional layer. The result is often a more generalized CNN that is rid of certain filters that do not help characterize the classes.
An example computer-implemented method includes receiving agricultural data records comprising a first set of yield properties for a first set of seeds grown in a first set of environments, and receiving genetic feature data related to a second set of seeds. The method further includes generating a second set of yield properties for the second set of seeds associated with a second set of environments by applying a model using the genetic feature data and the agricultural data records. In addition, the method includes determining predicted yield performance for a third set of seeds associated with one or more target environments by applying the second set of yield properties, and generating seed recommendations for the one or more target environments based on the predicted yield performance for the third set of seeds. In the present example, the method also includes causing display, on a display device communicatively coupled to the server computer system, the seed recommendations.
In an embodiment, a sensor system and a method for monitoring properties of field soils and wastewater are described. In an embodiment, a sensor system comprises a cartridge system implemented in an integrated circuit. The cartridge system comprises a chemical sensor and a computer processor coupled to the chemical sensor. The chemical sensor is configured to receive a sample of a test material such as soil or wastewater. Based on the sample of the test material, the chemical sensor determines a measure of a property in the test material. The computer processor receives, from the chemical sensor, the measure of the property in the test material, and computes, based on, at least in part, the measure of the property in the test material, a concentration level of the property in the test material. Based on the concentration level of the property in the test material, the computer processor generates an output that includes the concentration level. In an embodiment, the concentration level of the property in the test material is provided to a computer-based controller that controls agricultural equipment executing an agricultural prescription in an agricultural field.
Systems and methods for implementing a trial in one or more fields is provided. According to an embodiment, an agricultural intelligence computer system identifies a plurality of sets of adjacent locations in a field and computes a difference value between the locations. The system uses the different values for the plurality of sets of adjacent locations to determine a short length variability score. The system may then use the short length variability score to identify fields for implementing a trial and/or locations within a field to implement the trial. In embodiments, the system uses a grid overlay which the system orients based on header information received from agricultural implements. In embodiments, the system alters the grid overlay to increase a number of testing locations on the agricultural field and/or within different management zones.
Embodiments generate digital plans for agricultural fields. In an embodiment, a model receives digital inputs including stress risk data, product maturity data, field location data, planting date data, and/or harvest date data. The model mathematically correlates sets of digital inputs with threshold data associated with the stress risk data. The model is used to generate stress risk prediction data for a set of product maturity and field location combinations. In a digital plan, product maturity data or planting date data or harvest date data or field location data can be adjusted based on the stress risk prediction data. A digital plan can be transmitted to a field manager computing device. An agricultural apparatus can be moved in response to a digital plan.
A01B 79/02 - Methods for working soil combined with other agricultural processing, e.g. fertilising, planting
G06Q 10/04 - Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
G06Q 10/06 - Resources, workflows, human or project managementEnterprise or organisation planningEnterprise or organisation modelling
In some embodiments, the system is programmed to build from multiple training sets multiple digital models, each for recognizing plant diseases having symptoms of similar sizes. Each digital model can be implemented with a deep learning architecture that classifies an image into one of several classes. For each training set, the system is thus programmed to collect images showing symptoms of one or more plant diseases having similar sizes. These images are then assigned to multiple disease classes. For a first one of the training sets used to build the first digital model, the system is programmed to also include images that correspond to a healthy condition and images of symptoms having other sizes. These images are then assigned to a no-disease class and a catch-all class. Given a new image from a user device, the system is programmed to then first apply the first digital model. For the portions of the new image that are classified into the catch-all class, the system is programmed to then apply another one of the digital models. The system is programmed to finally transmit classification data to the user device indicating how each portion of the new image is classified into a class corresponding to a plant disease or no plant disease.
Systems and methods for identifying clouds and cloud shadows in satellite imagery are described herein. In an embodiment, a system receives a plurality of images of agronomic fields produced using one or more frequency bands. The system also receives corresponding data identifying cloud and cloud shadow locations in the images. The system trains. a machine learning system to identify at least cloud locations using the images as inputs and at least data identifying pixels as cloud pixels or non-cloud pixels as outputs. When the system receives one or more particular images of a particular agronomic field produced using the one or more frequency bands, the system uses the one or more particular images as inputs into the machine learning system to identify a plurality of pixels in the one or more particular images as particular cloud locations.
A system and processing methods for configuring and utilizing a convolutional neural network (CNN) for plant disease recognition are disclosed. In some embodiments, the system is programmed to collect photos of infected plants or leaves where regions showing symptoms of infecting diseases are marked. Each photo may have multiple marked regions. Depending on how the symptoms are sized or clustered, one marked region may include only one lesion caused by one disease, while another may include multiple, closely-spaced lesions caused by one disease. The system is programmed to determine anchor boxes having distinct aspect ratios from these marked regions for each convolutional layer of a single shot multibox detector (SSD). For certain types of plants, common diseases lead to relatively many aspect ratios, some having relatively extreme values. The system is programmed to then train the SSD using the marked regions and the anchor boxes and apply the SSD to new photos to identify diseased plants.
A computer-implemented data processing method providing an improvement in executing machine learning processes on digital data representing physical properties related to agriculture is described. In an embodiment, the method comprises: receiving, from a computing device, a request to browse machine learning models stored in a digital model repository; retrieving, from the digital model repository and transmitting to the computing device, information about the machine learning models stored in the digital model repository; receiving, from the computing device, a selection, from the machine learning models, of a particular model and receiving particular input for the particular model; using resources available in a model execution infrastructure platform, executing the particular model on the particular input to generate particular outputs; transmitting the particular output to a computer configured on an agricultural machine to control the agricultural machine as the agricultural machine performs agricultural tasks in an agricultural field.
In an embodiment, the techniques herein include receiving a request for growing predictions for multiple regions within a growing operation. From there, user-specific tolerance rates are received for each region and scientifically-generated recommended prescription rates are determined for each region of the multiple regions. Weather risk estimates are determined for each region for each rate, and those weather risk estimates are returned in response to the request for growing predictions.
Techniques are provided for receiving a first set of historical agricultural data and a second set of historical agricultural data; generating a plurality of projected target yield ranges using the first set and the second set of historical agricultural data by generating a historic yield distribution; generating one or more yield ranking scores for one or more fields of a grower using the first set of historical agricultural data, and assigning a projected target yield range of the plurality of projected target yield ranges to each of the one or more fields based on the one or more yield ranking scores to generate assigned projected target yield ranges; receiving a third set of historical agricultural data comprising seed optimization data, and generating a recommended change in seed population or a recommended change in seed density; causing displaying the yield improvement recommendation for each of the one or more fields.
G06F 15/18 - in which a program is changed according to experience gained by the computer itself during a complete run; Learning machines (adaptive control systems G05B 13/00;artificial intelligence G06N)
43.
SUBFIELD MOISTURE MODEL IMPROVEMENT USING OVERLAND FLOW MODELING WITH SHALLOW WATER COMPUTATIONS
A computer-implemented data processing method comprises: receiving precipitation data and infiltration data for an agricultural field; obtaining surface water depth data, surface water velocity data, and surface water discharge data for the same agricultural field; determining subfield geometry data for the agricultural field; executing a plurality of water calculations and wave calculations using the subfield geometry data to generate an overland flow model that includes moisture levels for the agricultural field; based on, at least in part, the overland flow model, generating and causing displaying a visual graphical image of the agricultural field comprising a plurality of color pixels having color values corresponding to the moisture levels determined for the agricultural field. Output of the overland flow model is provided to control computers of seeders, planters, fertilizer spreaders, harvesters, or combines to control seeding, planting, fertilizing or irrigation activities in the field
In an embodiment, an agricultural intelligence receives agronomic field data for an agronomic field, comprising one or more input parameters, nutrient application values, and measured yield values. The system uses a digital model of crop growth to compute, for a plurality of locations on the field, a required nutrient value indicating a required amount of nutrient to produce the measured yield values. The system identifies a subset of the plurality of locations where the computed required nutrient value is greater than the nutrient application value and computes, for each location, a residual value comprising a difference between the required nutrient value and the nutrient application value. The system generates a residual map comprising the residual values. Using the residual map and the one or more input parameters for each of the plurality of locations, the system generates and stores model correction data for the agronomic field.
A computer-implemented method of predicting yields and recommending seeding rates for subfields with informed risks is disclosed. The method comprises receiving, by a processor, weather data for a first period consisting of a plurality of sub-periods for one or more subfields of a field; for each of the plurality of sub-periods for the one subfield: calculating a moisture stress indicator from the weather data; predicting, for each of a list of seeding rates, a yield from the moisture stress indicator using a trained model; and selecting one of the list of seeding rates based on the list of predicted yields; identifying one of the predicted yields corresponding to the selected seeding rate; determining, by the processor, a risk profile associated with a range of yields for the one subfield based on the predicted yields identified for the plurality of sub-periods; transmitting data related to the risk profile to a device associated with the one subfield.
Systems and methods for generating agronomic yield maps from field health imagery maps are described herein. In an embodiment, an agricultural intelligence computer system receives a field health imagery map for a particular agronomic field. The system additional receives data describing a total harvested mass of a crop on the particular agronomic field. The system computes an average yield for the plurality of locations on the particular agronomic field. Using the field health imagery map, the system generates a spatial distribution of agronomic yield based, at least in part, on the average yield. The system then generates a yield map using the spatial distribution of agronomic yield.
G01C 21/00 - NavigationNavigational instruments not provided for in groups
G06Q 10/04 - Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
47.
AUTOMATICALLY ASSIGNING HYBRIDS OR SEEDS TO FIELDS FOR PLANTING
Techniques are provided for assigning hybrid products or seed products to agricultural fields with optimal yield performance. In one embodiment, a method comprises receiving datasets specifying agricultural fields and inventories of hybrid products or seed products; obtaining input data comprising relative maturity values, historic yield values, and mean yield values for regions; calculating pair datasets consisting of permutations of product assignments and corresponding converse assignments of products and fields; inputting specified features of the pair dataset(s) to a trained machine learning model to yield POS values for each of the product assignments and its corresponding converse assignment; blending the POS values with field classification data using an operations research model to result in creating and storing score values for each of the product assignments and the corresponding converse assignments; generating and causing displaying at least the product assignments in a graphical user interface display of a client computing device.
Techniques are provided for receiving a first set of historical agricultural data for one or more fields of a grower and a second set of historical agricultural data comprising a dataset of hybrid seed properties; cross-referencing the first set and the second set of historical agricultural data to generate a yield range improvement recommendation for each of the one or more fields, wherein the yield improvement recommendation comprises a recommended change in seed population or a recommended change in seed density; generating predictive yield data for the one or more fields by applying the yield improvement recommendation to the first set of historical agricultural data; generating comparison yield data using the grower yield data and the predictive yield data for the one or more fields; and causing displaying the comparison yield data for the grower.
A computer-implemented method of targeting grower fields for crop yield lift is disclosed. The method comprises receiving, by a processor, crop seeding rate data and corresponding crop yield data over a period of time regarding a group of fields associated with a plurality of grower devices; receiving, by the processor, a current seeding rate for a grower's field associated with one of a plurality of grower devices; determining, whether the grower's field will be responsive to increasing a crop seeding rate for the grower's field from the current seeding rate to a target seeding rate based on the crop seeding rate data and corresponding crop yield data; preparing, in response to determining that the grower's field will be responsive, a prescription including a new crop seeding rate and a specific hybrid to be implemented in the grower's field.
In an embodiment, a computer-implemented data processing method comprises: receiving digital input specifying a request to display a map image of a specified agricultural field for a particular day; in response to receiving the input, calculating an interpolated digital image of the specified agricultural field with a plurality of different field properties, by: dividing a digital map of the specified field into a plurality of grids each having a same size and a same area; obtaining, from digital storage, a plurality of data for the different field properties and assigning the data as covariates; grouping the grids into a specified number of clusters based on values of the covariates; pseudo-randomly selecting a specified number of one or more sample values in each of the clusters; evaluating a digital fertility model using the sample values and storing a plurality of output values from the digital fertility model.
A computer-implemented method is disclosed. The method comprises causing display of a first map of one or more agricultural fields, the first map indicating a first type of farming data; receiving cost data corresponding to a second type of farming data; receiving revenue data; performing an RoI analysis for the one or more agricultural fields having a plurality of components, including cost data associated with a third type of farming data, the revenue data, and corresponding RoI data; causing display of a second map of the one or more agricultural fields concurrently with the first map, the second map indicating a first component of the RoI analysis; receiving a selection of points from the second map, the selection corresponding to a boundary of a region within the one or more agricultural fields; causing display of a report indicating the first component of the RoI analysis specific to the region.
Systems and methods for determining a risk of damage to a crop on an agronomic field are described. In an embodiment, a computer system receives, for each hour of a first day, weather data identifying temperature values and humidity values associated with a geographic location. The computer system determines, for a particular hour of the first day, that a temperature value is within a first range of values and a humidity value is within a second range of values and, in response, identifies the particular hour as a risk hour. The computer system computes, for a second day, a risk value for one or more agronomic fields at the geographic location based, at least in part, on one or more identified risk hours between a day of planting a crop on the one or more agronomic fields and the second day. The computer system determines that the risk value is above a risk value threshold and, in response, determines that the crop on the one or more agronomic fields is at risk of suffering damage from a particular crop damaging factor. The computer system stores data indicating that the crop is at risk of suffering damage from the particular crop damaging factor.
A system and method for identifying a probability of disease affecting a crop based on data received over a network is described herein, and may be implemented using computers for providing improvements in plant pathology, plant pest control, agriculture, or agricultural management. In an embodiment, a server computer receives environmental risk data, crop data, and crop management data relating to one or more crops on a field. Agricultural intelligence computer system 130 computes one or more crop risk factors based, at least in part, the crop data, one or more environmental risk factors based, at least in part, the environmental data, and one or more crop management risk factors based, at least in part, on the crop management data. Using a digital model of disease probability, agricultural intelligence computer system 130 computes a probability of onset of a particular disease for the one or more crops on the field based, at least in part, on the one or more crop risk factors, the one or more environmental risk factors, and the one or more crop management factors.
G06Q 10/06 - Resources, workflows, human or project managementEnterprise or organisation planningEnterprise or organisation modelling
G06Q 10/04 - Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
54.
SEQUENTIAL DATA ASSIMILATION TO IMPROVE AGRICULTURAL MODELING
In an embodiment, a computer-implemented method of assimilation of soil moisture data is disclosed. The method comprises receiving a digital data model related to soil moisture with a plurality of parameters for a given geographical location; identifying a time-based or event- based trigger for a first of the plurality of parameters; and receiving a plurality of values for the plurality of parameters measured from soil samples for a series of time points. The method further comprises applying sequential data assimilation through the series of time points as soon as the plurality of measured values are received for each of the series of time points, by executing an optimization method to optimize values of the plurality of parameters with respect to the plurality of measured values for each of the time points, when the time- based or event-based trigger is satisfied for one of the series of time points.
Techniques are provided for generating a set of target hybrid seeds with optimal yield and risk performance, including a server receiving a candidate set of hybrid seeds along with probability of successful yield values, associated historical agricultural data and property information, and selecting a subset of the hybrid seeds that have probability of success values greater than a filtering threshold. The server generates representative yield values for hybrid seeds based on the historical agricultural data and risk values for each hybrid seed. The server generates a dataset of target hybrid seeds for planting based on the risk values, the yield values, and the properties for the target fields. The dataset of target hybrid seeds includes target hybrid seeds that meet a specific threshold for a range of risk values. The server causes display of the dataset of target hybrid seeds including yield values and risk values for the target fields.
Techniques are provided for generating target success group of hybrid seeds for target fields include a server receiving agricultural data records that represent crop seed data describing seed and yield properties of hybrid seeds and first field geo-location data for agricultural fields where the hybrid seeds were planted. The server receives second geo-locations data for target fields where hybrid seeds are to be planted. The server generates a dataset of hybrid seed properties that include yield values and environmental classifications for hybrid seeds and then a dataset of success probability scores that describe the probability of a successful yield on the target fields based on the dataset of hybrid seed properties and the second geo-location data. The server generates target success yield group of hybrid seeds and probability of success values based on success probability scores and a yield threshold. The server causes display of the target success yield group.
A system and method for improving radar based precipitation estimates using spatiotemporal interpolation is provided. In an embodiment, an agricultural intelligence computer system receives a plurality of radar based precipitation rate values representing precipitation rate measurements at a plurality of locations and a plurality of times. The agricultural intelligence computer system identifies a first non-zero radar based precipitation rate value associated with a first location of the plurality of locations and a first time of the plurality of times. The agricultural intelligence computer also identifies a second non-zero radar based precipitation rate value associated with a second location of the plurality of locations and a second time of the plurality of times. The agricultural intelligence computer system determines that the first non-zero radar based precipitation rate value corresponds to the second non-zero radar based precipitation rate value. Based on the first non-zero radar based precipitation rate value and the second non-zero radar based precipitation rate value, the agricultural intelligence computer system computes a non-zero precipitation accumulation value at a third location and a third time.
In an embodiment, a system for measuring soil element concentration in a field in real time is disclosed. The system comprises an extraction apparatus coupled to a mobility component configured to move the system in the agricultural field. The extraction apparatus configured to receive a plurality of soil samples successively from a soil probe coupled to the mobility component, when the mobility component is operating. The extraction apparatus containing an extractant solution that is a solvent of the soil samples. In addition, the extraction apparatus comprising a mixer that is configured to mix the soil samples with the extractant solution, thereby forming a solution mix. The system also comprises a chemical sensor coupled to the extraction apparatus, the chemical sensor configured to measure a concentration level of a soil element in the solution mix. Furthermore, the system comprises a processor coupled to the chemical sensor, the processor configured to calculate a concentration level of the soil element in each of the plurality of soil samples after the soil sample is received by the extraction apparatus and before a successive soil sample is received by the extraction apparatus.
A01C 23/00 - Distributing devices specially adapted for liquid manure or other fertilising liquid, including ammonia, e.g. transport tanks or sprinkling wagons
G01N 21/25 - ColourSpectral properties, i.e. comparison of effect of material on the light at two or more different wavelengths or wavelength bands
A computer system and related computer-implemented methods for recognizing crop diseases from large FoV images are disclosed. In some embodiments, the computer system is configured to initially build a first digital model in memory for identifying a region capturing a leaf, and a second model for identifying a region capturing a leaf infected with a disease. Given a large FoV image, under program control, the system is programmed to then automatically identify candidate regions that might capture single leaves from the large FoV image using the first model. The system is programmed to further determine whether the candidate regions capture symptoms of a crop disease on single leaves using on the second model.
In an embodiment, a method of real-time disease recognition in a crop field is disclosed. The method comprises causing a camera to continuously capture surroundings to generate multiple images. The method further comprises causing a display device to continuously display the multiple images as the multiple images are generated. In addition, the method comprises processing each of one or more of the multiple images. The processing comprises identifying at least one of a plurality of diseases and calculating at least one disease score associated with the at least one disease for a particular image; causing the display device to display information regarding the at least one disease and the at least one disease score in association with a currently displayed image; receiving input specifying one or more of the at least one disease; and causing the display device to show additional data regarding the one or more diseases, including a remedial measure for the one or more diseases.
A system for implementing a trial in one or more fields is provided. In an embodiment, a server computer receives field data for a plurality of agricultural fields. Based, at least in part, on the field data for the plurality of agricultural fields, the server computer identifies one or more target agricultural fields. The server computer sends, to a field manager computing device associated with the one or more target agricultural fields, a trial participation request. The server receives data indicating acceptance of the trial participation request from the field manager computing device. The server determines one or more locations on the one or more target agricultural fields for implementing a trial and sends data identifying the one or more locations to the field manager computing device. When the server computer receives application data for the one or more target agricultural fields, the server computer determines whether the one or more target agricultural fields are in compliance with the trial. The server computer then receives result data for the trial and, based on the result data, computes a benefit value for the trial.
G06Q 50/00 - Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
Described herein are implements and methods for leveling of measured values of sensors across an implement having sensors. In one embodiment, a method for leveling sensors across an implement having a plurality of sensors comprises providing an implement having a plurality of sensors, measuring a value at each sensor, calculating an average of all values measured, associating the value at one of the rows to the average, and calculating a correction factor for the one of the rows based on the association.
A computer-implemented method is disclosed. The method comprises receiving, by a processor, input data including: a number T of treatments applied to a field, a number L of treatment locations for each treatment, a list of treatment polygons within the field, and a map for the field indicating one or more values of a set of design parameters corresponding to environment factors for each of a plurality of locations in the field; computing, by the processor, an environment class index for each of a group of locations in the list of treatment polygons based on the map; distributing the list of treatment polygons to the T treatments based on the computed environment class indices; selecting, for each of the T of treatments, L treatment locations from the group of locations in the treatment polygons distributed to the treatment; causing display of information regarding the selected treatment locations.
A computer-implemented method is disclosed. The method comprises receiving input data including a map for a management zone in a field indicating one or more values of a set of agricultural characteristics for each of a plurality of locations; identifying a set of values for the set of agricultural characteristics for each of a group of locations based on map; normalizing a set of model values for the set of agricultural characteristics used by an agricultural modeling tool and the set of values of the set of agricultural characteristics for each of the group of locations; selecting one of the group of locations as a sampling location based on the normalized set of model values, the normalized sets of values for the group of locations, and a first distance constraint related to a distance to a boundary of the management zone; causing display of information regarding the selected location.
G07C 5/08 - Registering or indicating performance data other than driving, working, idle, or waiting time, with or without registering driving, working, idle, or waiting time
65.
CROP YIELD ESTIMATION USING AGRONOMIC NEURAL NETWORK
In an embodiment, a server computer system receives a particular dataset relating to one or more agricultural fields wherein the particular data set comprises particular crop identification data, particular environmental data, and particular management practice data. Using a first neural network, the server computer system computes a crop identification effect on crop yield from the particular crop identification data. Using a second neural network, the server computer system computes an environmental effect on crop yield from the particular environmental data. Using a third neural network, the server computer system computes a management practice effect on crop yield from the management practice data. Using a master neural network, the server computer system computes one or more predicted yield values from the crop identification effect on crop yield, the environmental effect on crop yield, and the management practice effect on crop yield.
Systems, methods and apparatus are provided for monitoring soil properties including soil moisture, soil electrical conductivity and soil temperature during an agricultural input application. Embodiments include a soil reflectivity sensor and/or a soil temperature sensor mounted to a seed firmer for measuring moisture and temperature in a planting trench. A thermopile for measuring temperature via infrared radiation is described herein. In one example, the thermopile is disposed in a body and senses infrared radiation through an infrared transparent window. Aspects of any of the disclosed embodiments may be implemented in or communicate with an agricultural intelligence computer system as described herein.
In an embodiment, a data processing method comprises receiving permanent properties data for a plurality of agricultural sub-fields of an agricultural field; determining whether at least one data item is missing for any sub-field of the plurality of agricultural sub-fields in the permanent properties data, and if so, generating additional properties data for the plurality of agricultural sub-fields; generating preprocessed permanent properties data by merging the permanent properties data with the additional properties data; generating filtered permanent properties data by removing, from the preprocessed permanent properties data, a set of preprocessed permanent properties records corresponding to a subset of the plurality of agricultural sub-fields in which two or more crops were grown in the same year; applying a regression operator to the filtered permanent properties data to determine a plurality of intra-field variations values that represent intra-field variations in predicted yield of crop harvested from the plurality of agricultural sub-fields.
G06F 19/00 - Digital computing or data processing equipment or methods, specially adapted for specific applications (specially adapted for specific functions G06F 17/00;data processing systems or methods specially adapted for administrative, commercial, financial, managerial, supervisory or forecasting purposes G06Q;healthcare informatics G16H)
G06G 7/48 - Analogue computers for specific processes, systems, or devices, e.g. simulators
G06G 7/58 - Analogue computers for specific processes, systems, or devices, e.g. simulators for chemical processes
G06N 7/00 - Computing arrangements based on specific mathematical models
68.
IDENTIFYING MANAGEMENT ZONES IN AGRICULTURAL FIELDS AND GENERATING PLANTING PLANS FOR THE ZONES
In an embodiment, yield data representing yields of crops that have been harvested from an agricultural field and field characteristics data representing characteristics of the agricultural field is received and used to determine a plurality of management zone delineation options. Each option, of the plurality of management zone delineation options, comprises zone layout data for an option. The plurality of management zone delineation options is determined by: determining a plurality of count values for a management class count; generating, for each count value, a management delineation option by clustering the yield data from and the field characteristics data, assigning zones to clusters, and including the zones in a management zone delineation option. One or more options from the plurality of management zone delineation options are selected and used to determine one or more planting plans. A graphical representation of the options and the planting plans is displayed for a user.
A soil imaging system having a work layer sensor disposed on an agricultural implement to generate an electromagnetic field through a soil area of interest as the agricultural implement traverses a field. A monitor in communication with the work layer sensor is adapted to generate a work layer image of the soil layer of interest based on the generated electromagnetic field. The work layer sensor may also generate a reference image by generating an electromagnetic field through undisturbed soil. The monitor may compare at least one characteristic of the reference image with at least one characteristic of the work layer image to generate a characterized image of the work layer of interest. The monitor may display operator feedback and may affect operational control of the agricultural implement based on the characterized image.
In an embodiment, a method comprises: receiving pre-planting data representing a lower bound date value and an upper bound date value of dates for a pre-planting application of fertilizer to an agricultural field; side-dressing data representing a lower bound date value and an upper bound date value of dates for a side-dressing application; fertilizer cost data representing a cost of a fertilizer application; labor cost data representing a cost of applying fertilizer to the field; and expected profit data. Based on the received data, one or more penalty constraints are determined. Based on the received data, a fertilizing schedule is generated. The schedule comprises the one or more valid calendar dates on which fertilizing the agricultural field is recommended and the one or more valid fertilizer amounts to be applied to the agricultural field on the one or more valid calendar dates to maximize a yield from the agricultural field.
G01J 3/51 - Measurement of colourColour measuring devices, e.g. colorimeters using electric radiation detectors using colour filters
G01N 21/27 - ColourSpectral properties, i.e. comparison of effect of material on the light at two or more different wavelengths or wavelength bands using photo-electric detection
G06F 15/00 - Digital computers in generalData processing equipment in general
72.
DELINEATING MANAGEMENT ZONES BASED ON HISTORICAL YIELD MAPS
In an embodiment, a method comprises: receiving digital yield data representing yields of crops that have been harvested from an agricultural field; applying an empirical cumulative density function to the digital yield data to generate transformed digital yield data; smoothing the transformed digital yield data to result in generating and storing smooth transformed digital yield data; determining a first count value for a plurality of management classes; generating a plurality of first management zones for the agricultural field by clustering the smooth transformed digital yield data and using the first count value; generating a set of first merged management zones by merging one or more small management zones, of the plurality of first management zones, with their respective similar neighboring large zones; storing the set of first merged management zones and the first count value in a set of management zone metrics.
In an embodiment, a method comprises determining, in received yield data, one or more passes, each pass including a plurality of observations. For each pass of the one or more passes, one or more discrete derivatives are determined, and based on the one or more discrete derivatives first outlier data is generated. First filtered data is generated by removing the first outlier data from the yield data. Furthermore, for each observation in the yield data, a plurality of nearest neighbor observations is determined, and used to determine a plurality of absolute differences in yield values. Based on the plurality of absolute differences, second outlier data is determined. Second filtered data is generated by removing the second outlier data from the first filtered data. Using a presentation layer of a computer system, a graphical representation of the second filtered data is generated and displayed on the computing system.
In an approach, hyperspectral and/or multispectral remote sensing images are automatically analyzed by a nitrogen analysis subsystem to estimate the value of nitrogen variables of crops or other plant life located within the images. For example, the nitrogen analysis subsystem may contain a data collector module, a function generator module, and a nitrogen estimator module. The data collector module prepares training data which is used by the function generator module to train a mapping function. The mapping function is then used by the nitrogen estimator module to estimate the values of nitrogen variables for a new remote sensing image that is not included in the training set. The values may then be reported and/or used to determine an optimal amount of fertilizer to add to a field of crops to promote plant growth.
Systems and methods for scalable comparisons between two pixel maps are provided. In an embodiment, an agricultural intelligence computer system generates pixel maps from non-image data by transforming a plurality of values and location values into pixel values and pixel locations. The agricultural intelligence computer system converts each pixel map into a vector of values. The agricultural intelligence computer system also generates a matrix of metric coefficients where each value in the matrix of metric coefficients is computed using a spatial distance between to pixel locations in one of the pixel maps. Using the vectors of values and the matrix of metric coefficients, the agricultural intelligence computer system generates a difference metric identifying a difference between the two pixel maps. In an embodiment, the difference metric is normalized so that the difference metric is scalable to pixel maps of different sizes.
In an embodiment, a system receives a first plurality of values representing precipitation gauge measurements at a plurality of gauge locations. The system obtains a second plurality of values representing radar based precipitation estimates at the plurality of gauge locations. For each radar based precipitation estimate value at the plurality of gauge locations, the system identifies one or more corresponding precipitation gauge measurement values, computes a gauge radar differential value for the radar based precipitation estimate, and stores the gauge radar differential value with location data identifying a corresponding location of the plurality of gauge locations. The system obtains a particular radar based precipitation estimate at a non-gauge location. The system determines that one or more particular gauge radar differential values at one or more particular gauge locations correspond to the particular radar based precipitation estimate and computes a particular radar based precipitation estimate error at the non-gauge location.
G01S 7/41 - Details of systems according to groups , , of systems according to group using analysis of echo signal for target characterisationTarget signatureTarget cross-section
G01S 13/95 - Radar or analogous systems, specially adapted for specific applications for meteorological use
77.
Radar based precipitation estimates using spatiotemporal interpolation
A system and method for improving radar based precipitation estimates using spatiotemporal interpolation is provided. In an embodiment, an agricultural intelligence computer system receives a plurality of radar based precipitation rate values representing precipitation rate measurements at a plurality of locations and a plurality of times. The agricultural intelligence computer system identifies a first non-zero radar based precipitation rate value associated with a first location of the plurality of locations and a first time of the plurality of times. The agricultural intelligence computer also identifies a second non-zero radar based precipitation rate value associated with a second location of the plurality of locations and a second time of the plurality of times. The agricultural intelligence computer system determines that the first non-zero radar based precipitation rate value corresponds to the second non-zero radar based precipitation rate value. Based on the first non-zero radar based precipitation rate value and the second non-zero radar based precipitation rate value, the agricultural intelligence computer system computes a non-zero precipitation accumulation value at a third location and a third time.
In an approach, a method for fusing point data with areal averages is performed by a computing system. The fusion procedure is coherent, in the sense that the computing system takes into account what the areal averages represent with respect to the point data. The overarching goal is to fit a model that takes into account the information derived from both data sets. The areal averages provide an estimate for what the integral of a model representing the behavior of the environmental variable should be over a particular district and the point values indicate the estimated value at particular locations. Thus, the integral of the fitted model over a district of the grid should approximate the value provided by the areal averages while also approximating the value provided by the point data for locations which are provided by the point data.
In an approach, a method for fusing point data with areal averages is performed by a computing system. The fusion procedure is coherent, in the sense that the computing system takes into account what the areal averages represent with respect to the point data. The overarching goal is to fit a model that takes into account the information derived from both data sets. The areal averages provide an estimate for what the integral of a model representing the behavior of the environmental variable should be over a particular district and the point values indicate the estimated value at particular locations. Thus, the integral of the fitted model over a district of the grid should approximate the value provided by the areal averages while also approximating the value provided by the point data for locations which are provided by the point data.
Systems and methods for generation of images of a particular type from images of a different type are disclosed. In an embodiment, an agricultural intelligence computer system receives a first plurality of images of a first type and a second plurality of images of a second type. The first and second types may refer to variances in resolution, frequency ranges of frequency bands, and/or types of frequency bands used to generate the images. Based on the first plurality of images and the second plurality of images, the agricultural intelligence computer system generates a feature set dictionary comprising mappings from features of the first plurality of images to features of the second plurality of images. When the agricultural intelligence computer system receives a particular image of the first type, the agricultural intelligence computer system uses the received image and the feature set dictionary to generate an image of the second type.
In an embodiment, agricultural intelligence computer system stores a digital model of nutrient content in soil which includes a plurality of values and expressions that define transformations of or relationships between the values and produce estimates of nutrient content values in soil. The agricultural intelligence computer receives nutrient content measurement values for a particular field at a particular time. The agricultural intelligence computer system uses the digital model of nutrient content to compute a nutrient content value for the particular field at the particular time. The agricultural intelligence computer system identifies a modeling uncertainty corresponding to the computed nutrient content value and a measurement uncertainty corresponding to the received measurement values. Based on the identified uncertainties, the modeled nutrient content value, and the received measurement values, the agricultural intelligence computer system computes an assimilated nutrient content value.
A method for estimating adjusted rainfall values for a set of geo-locations using agricultural data comprises using a server computer system that receives, via a network, agricultural data records that are used to estimate rainfall values for the set of geo-locations. Within the server computer system, rainfall calculation instructions receive digital data including observed radar and rain-gauge agricultural data records. The computer system then aggregates the agricultural data records and creates and stores the agricultural data sets. The agricultural data records are then transformed into one or more distribution sets. The distribution sets are then used to determine regression parameters for a digital rainfall regression model. The digital rainfall regression model then is used to estimate adjusted rainfall values for a new set of geo-locations. The server computer system then generates a digital image that includes the geo-locations and the adjusted rainfall values.
In an approach, a computer receives an observation dataset that identifies one or more ground truth values of an environmental variable at one or more times and a reforecast dataset that identifies one or more predicted values of the environmental variable produced by a forecast model that correspond to the one or more times. The computer then trains a climatology on the observation dataset to generate an observed climatology and trains the climatology on the reforecast dataset to generate a forecast climatology. The computer identifies observed anomalies by subtracting the observed climatology from the observation dataset and forecast anomalies by subtracting the forecast climatology from the reforecast dataset. The computer then models the observed anomalies as a function of the forecast anomalies, resulting in a calibration function, which the computer can then use to calibrate new forecasts received from the forecast model.
A method and system for modeling trends in crop yields is provided. In an embodiment, the method comprises receiving, over a computer network, electronic digital data comprising yield data representing crop yields harvested from a plurality of agricultural fields and at a plurality of time points; in response to receiving input specifying a request to generate one or more particular yield data: determining one or more factors that impact yields of crops that were harvested from the plurality of agricultural fields; decomposing the yield data into decomposed yield data that identifies one or more data dependencies according to the one or more factors; generating, based on the decomposed yield data, the one or more particular yield data; generating forecasted yield data or reconstructing the yield data by incorporating the one or more particular yield data into the yield data.
A method and system for modeling trends in crop yields is provided. In an embodiment, the method comprises receiving, over a computer network, electronic digital data comprising yield data representing crop yields harvested from a plurality of agricultural fields and at a plurality of time points; in response to receiving input specifying a request to generate one or more particular yield data: determining one or more factors that impact yields of crops that were harvested from the plurality of agricultural fields; decomposing the yield data into decomposed yield data that identifies one or more data dependencies according to the one or more factors; generating, based on the decomposed yield data, the one or more particular yield data; generating forecasted yield data or reconstructing the yield data by incorporating the one or more particular yield data into the yield data.
A method for determining national crop yields during the growing season may be accomplished using a system that receives agricultural data records that are used to forecast a national crop yield for a particular year. Weather index values are calculated and aggregated from the agricultural data records. Crop yield estimating instructions select representative features from aggregated weather index data and create a covariate matrix for each specific geographic area. Linear regression instructions calculate the crop yield for the specific geographic area for the specific year using the corresponding covariate matrix for that specific year. The crop estimating instructions determine a national crop yield for the specific year using the sum of the crop yields for the specific geographic areas for the specific year nationally adjusted using national yield adjustment instructions. In an embodiment, the crop yield may refer to a specific crop yield such as corn yield.
A method for determining national crop yields during the growing season comprises receiving agricultural data points for a specific geo-locations. Calculating weather index values, which represent crop stress, from the agricultural data records and generates an aggregated weather index data series, where each aggregated weather index data series contains weather index values for a specific weather index. Selecting representative features from the aggregated weather index data series and creating covariate matrices for each geographic area. Calculating crop yield for the specific geographic area using linear regression on the covariate matrix for specific geographic areas using calculated parameters based on a mean, an error term, and a variance parameter based on a geographic area specific bias coefficient. Determining national crop yield for the specific year by calculating the national crop yield from the sum of the crop yields for the specific geographic areas nationally adjusted using national yield adjustment instructions.
G06F 15/18 - in which a program is changed according to experience gained by the computer itself during a complete run; Learning machines (adaptive control systems G05B 13/00;artificial intelligence G06N)
88.
GENERATING DIGITAL MODELS OF CROP YIELD BASED ON CROP PLANTING DATES AND RELATIVE MATURITY VALUES
A method for generating digital models of potential crop yield based on planting date, relative maturity, and actual production history is provided. In an embodiment, data representing historical planting dates, relative maturity values, and crop yield is received by an agricultural intelligence computer system. Based on the historical data, the system generates spatial and temporal maps of planting dates, relative maturity, and actual production history. Using the maps, the system creates a model of potential yield that is dependent on planting date and relative maturity. The system may then receive actual production history data for a particular field. Using the received actual production history data, a particular planting date, and a particular relative maturity value, the agricultural intelligence computer system computes a potential yield for a particular field.
G06Q 50/00 - Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
In an embodiment, nitrate measurements from soil during a particular portion of a crop's development and corresponding crop yields are received by an agricultural intelligence computing system. Based, at least in part, on the nitrate measurements and corresponding crop yields, the system determines maximum yields for each of a plurality of locations and converts each crop yield value into a relative crop yield by dividing the crop yield value by the maximum crop yield for the location. Using the relative crop yields and the corresponding nitrate values in the soil, the system generates a digital model of relative crop yield as a function of nitrate in the soil during the particular portion of the crop's development. When the system receives nitrate measurements from soil in a particular field during the particular portion of a crop's development, the system computes a relative yield value using the model of relative crop yield.
A system for detecting clouds and cloud shadows is described. In one approach, clouds and cloud shadows within a remote sensing image are detected through a three step process. In the first stage a high-precision low-recall classifier is used to identify cloud seed pixels within the image. In the second stage, a low-precision high-recall classifier is used to identify potential cloud pixels within the image. Additionally, in the second stage, the cloud seed pixels are grown into the potential cloud pixels to identify clusters of pixels which have a high likelihood of representing clouds. In the third stage, a geometric technique is used to determine pixels which likely represent shadows cast by the clouds identified in the second stage. The clouds identified in the second stage and the shadows identified in the third stage are then exported as a cloud mask and shadow mask of the remote sensing image.
G01W 1/02 - Instruments for indicating weather conditions by measuring two or more variables, e.g. humidity, pressure, temperature, cloud cover or wind speed
G06F 17/30 - Information retrieval; Database structures therefor
A method and system for estimating uncertainties in radar based precipitation estimates is provided. In an embodiment, gauge measurements at one or more gauge locations are received by an agricultural intelligence computer system. The agricultural intelligence computer system obtains precipitation estimates for the one or more gauge locations that correspond to the gauge measurements and computes the differences between the precipitation estimates and the gauge measurements. Using the precipitation estimates and the computed differences, the agricultural intelligence computer system then models a dependence of the uncertainty in the precipitation estimates on the value of the precipitation estimates. When the agricultural intelligence computer system receives precipitation estimates for a location where gauge measurements are unavailable, the agricultural intelligence computer identifies an uncertainty for the precipitation estimate based on the value of the precipitation estimate and the model of the dependence of the uncertainty on the precipitation estimate values.
A method for predicting field specific crop yield recommendations. A server computer system receives over a network, digital agricultural data records, including remotely sensed spectral properties of plants and soil moisture records. The computer system aggregates the digital records to create and store geo-specific time series over a specified time. The computer system selects representative features from the geo-specific time series and creates, for each specific geographic area, a covariate matrix comprising the representative features. The computer system assigns a probability value to a component group in a set of parameter component groups, where each component group includes regression coefficients calculated from a probability distribution. The computer system generates the probability distributions used to determine the regression coefficients, the probability distribution used to generate the error term is defined with a mean parameter set at zero and a variance parameter set to a field specific bias coefficient.
G01N 21/27 - ColourSpectral properties, i.e. comparison of effect of material on the light at two or more different wavelengths or wavelength bands using photo-electric detection
G01N 21/33 - Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry using ultraviolet light
G01N 21/35 - Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry using infrared light
Computer-implemented techniques for determining crop harvest times during a growing season based upon hybrid seed properties and weather conditions is provided. A server computer system receives data representing hybrid seed properties, including seed type, relative maturity, and weather data. The computer system creates and stores an equilibrium moisture content time series for the specific geo-location based upon weather data, which is used to determine the rate of grain dry down. The computer system calculates R6 moisture content for a specific hybrid seed based on a plurality of hybrid seed data. The computer system creates a grain dry down time series model, based on the equilibrium moisture content time series, the R6 date, the R6 moisture content, and hybrid seed properties. The computer system determines and displays a harvest time recommendation based on the grain dry down time series and the desired moisture level of the grower.
A method and system for decontaminating raw yield maps by combining filters with spatial outlier detectors is provided. In an embodiment, the method comprises receiving over a computer network electronic digital data comprising first yield data representing crop yields harvested from an agricultural field; applying one or more filters to the first yield data to identify, from the first yield data, first outlier data; generating first filtered data from the first yield data by removing the first outlier data from the first yield data; identifying, in the first filtered data, second outlier data representing outlier values based on one or more outlier characteristics; generating second outlier data from the first filtered data by removing the second outlier data from the first filtered data; generating and causing displaying on a mobile computing device a graphical representation of the crop yields harvested from the agricultural field using only the second outlier data.
Computer-implemented techniques for determining and presenting improved seeding rate recommendations for sowing hybrid seeds in a field. In an embodiment, seeding query logic receiving digital data representing planting parameters including seed type and sowing row width. The seeding query logic retrieves a set of one or more seeding models from a data repository based on planting parameters. Mixture model logic generates an empirical mixture model in digital computer memory that represents a composite distribution of the set of one or more seeding models. The mixture model logic then generates an optimal seeding rate distribution dataset in digital computer memory based upon the empirical mixture model, where the optimal seeding rate distribution dataset represents the optimal seeding rate across all measure fields. Optimal seeding rate recommendation logic calculates and presents on a digital display device an optimal seeding rate recommendation that is based upon the optimal seeding rate distribution dataset.
In an approach, an image of an agricultural field is analyzed using a classifier that has been trained to identify a probability for each pixel within an image that the pixel corresponds to water. A flow simulation is performed to determine regions of the field that are likely to pool water after rainfall based on precipitation data, elevation data, and soil property data of the field. A graph of vertices representing the pixels and edges representing connections between neighboring pixels is generated. The probability of each pixel within the graph being ponding water is set based on the probability pixel being water, the likelihood that water will pool in the area represented by the pixel, the probability of neighboring pixels being ponding water, and a cropland mask that identifies which pixels correspond to cropland. A class for each pixel is then determined that maximizes the joint probability over the graph.
A method for estimating soil properties within a field using hyperspectral remotely sensed data. A soil preprocessing module receives soil spectrum data records that represent a mean soil spectrum of a specific geo-location of a specified area of land. The soil preprocessing module removes interference signals and creates a set of one or more spectral bands. A soil regression module inputs the one or more soil spectral bands and predicts soil property datasets. The soil property datasets include specific soil properties relevant to determining fertility of the soil or soil property levels that may influence soil management at a specific geo-location. The soil regression module selects multiple specific soil property datasets that best represent the existing soil properties including soil properties predicted and the spectral band data used to determine the soil properties. The soil regression module sends this predicted data to a soil model database.
G01N 21/3563 - Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry using infrared light for analysing solidsPreparation of samples therefor
A method and system for generating probabilistic estimates of precipitation intensity from radar reflectivity measurements is provided. In an embodiment, an agricultural intelligence computer system receives radar reflectivity measurements for a particular location from an external data source. The agricultural intelligence computer system constructs a probability distribution of drop sizes describing the probability that the precipitation included drops of various sizes based on the radar reflectivity measurements. The agricultural intelligence computer system samples a plurality of values from the probability of distribution of drop sizes and uses the plurality of values and the radar reflectivity measurements to compute a plurality of rainfall rates. Based on the plurality of rainfall rates, the agricultural intelligence computer system constructs a probability distribution of rainfall rates for the particular location.
G01S 13/00 - Systems using the reflection or reradiation of radio waves, e.g. radar systemsAnalogous systems using reflection or reradiation of waves whose nature or wavelength is irrelevant or unspecified
G01S 13/95 - Radar or analogous systems, specially adapted for specific applications for meteorological use
A method for estimating precipitation values and associated uncertainties is provided. In an embodiment, precipitation records that indicate the occurrence and intensity of precipitation at specific locations are received by a weather computing system. The weather computing system uses the gauge information to separately create multiple realizations of precipitation occurrence fields and precipitation intensity fields. The weather computing system may model the occurrence of precipitation by proposing a value for each point independently and using the proposed value to update all prior proposals. The weather computing system may model the intensity of precipitation by modeling the spatial correlation of precipitation intensity and sampling from distributions at each location to determine the intensity of precipitation at each location. The weather computing system may then combine the precipitation intensity and occurrence fields into one or more final estimate fields.
patents
