Abstract: Methods are provided for generating a prescription map for the application of crop inputs. In one method, the user draws a boundary on a map within a user interface and the system identifies relevant soil data and generates a soil map overlay and legend for changing the application prescription for various soils and soil conditions. In another method, the user instead drives a field boundary which is recorded on a planter monitor using a global positioning receiver, and the system generates a soil map and legend for changing the application prescription.

Abstract: 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.

Abstract: A method for building and using soil models that determine soil properties from soil spectrum data is provided. In an embodiment, building soil model may be accomplished using soil spectrum data received via hyperspectral sensors from a land unit. A processor updates the soil spectrum data by removing interference signals from the soil spectrum data. Multiple ground sampling locations within the land unit are then determined based on the updated soil spectrum data. Soil property data are obtained from ground sampling at the ground sampling locations. Soil models that correlate the updated soil spectrum data with the soil property data are created based on the updated soil spectrum data and the soil property data. The soil models are sent to a storage for future use.

Abstract: Described herein are implements that include a vehicle having a system for sensing or testing soil and/or vegetation as the vehicle traverses a field.

Abstract: 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.

Abstract: 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.

Abstract: Systems and method for computing yield values through a neural network from a plurality of different data inputs are disclosed. 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.

Abstract: A method for calibrating forecasts involving temperature, precipitation, and other weather related variables is provided. In an embodiment historical ensemble-based forecasts and historical observations are received by an agricultural intelligence computing system. Historical differences are determined between the forecasts and the observations corresponding to the forecasts and stored in the volatile memory of the agricultural intelligence computing system. The agricultural intelligence computing system receives current ensemble-based forecasts and a request for improved forecasts. The agricultural intelligence computing system retrieves the historical differences and uses a combination of the historical differences and the current ensemble-based forecasts to create probability distributions for the weather for each lead day. The agricultural intelligence computing system then samples from the probability distributions to create improved ensemble-based forecasts at the requested location.

Abstract: 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.

Abstract: In an embodiment, the techniques herein include receiving a request for a suggested distribution rate of a particular field-distributed commodity in a particular geographical area. Based on that request, two or more rate models for distribution of the particular field-distributed commodity are computed, where one rate model is a user-tolerance model. The suggested distribution rate of the particular field-distributed commodity is determined by performing Bayesian updating where the user-tolerance model is treated as a prior distribution and distributions for each of the other rate models of the two or more rate models for distribution of the particular field-distributed commodity in the particular geographical area are treated as input data in the Bayesian updating. The determined suggested distribution rate of the particular field-distributed commodity is then sent in response to the received request.

Abstract: Systems, methods and apparatus for monitoring soil properties and applying fertilizer during a planting operation. Various sensors are disposed in ground engaging components for monitoring soil properties. The ground engaging components may have structure for opening a side trench in the sidewalls of the seed trench and may include liquid application conduits for injecting liquid into the sidewalls of the resulting side trenches.

Abstract: Systems, methods and apparatus are provided for monitoring soil properties including soil moisture, soil electrical conductivity and soil temperature. Embodiments include a soil reflectivity sensor and/or a soil temperature sensor for measuring moisture and temperature.

Abstract: A method for temperature interpolation is provided. In an embodiment climatology records and temperature observations are received by a weather computing system over a network from an outside source. The temperature observations are subtracted from the climatology records to create anomalies. The anomalies are extrapolated across a map using various modeling methods and stored in the volatile memory of weather computing system. When the weather computing system receives a request for a temperature at a specific location, the weather computing system retrieves the anomaly field from the volatile memory and applies it to the climatology records at the requested location to determine the temperature for that location.

Abstract: 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 effect operational control of the agricultural implement based on the characterized image.

Abstract: 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.

Abstract: In an embodiment, computer processes are programmed to determine planting plans based on planting characteristics data received for an agricultural field and a plurality of management zone delineation options defined for the agricultural field. Each of the planting plans specifies different planting recommendations for the agricultural field. A first graphical representation of the planting plans, and an interactive object is generated and displayed on a computing device. The interactive object is configured to receive input specifying a relative importance ratio between the planting plans for determining a new planting plan for the agricultural field. A particular relative importance ratio is received via the interactive object, and is used to determine the new planting plan, which specifies new planting recommendations for the agricultural field. Information about the new planting plan is displayed on the computer device.

Abstract: 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.

Abstract: A computer implemented method for generating digital models of relative crop yield based on nitrate values in the soil is provided. 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 location of a plurality of locations. The system then 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.

Abstract: 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.

Abstract: 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.