A method of predicting crop yield includes generating, via a processor, a plurality of vectors representative of growing conditions for a current time period and a plurality of vectors representative of growing conditions for a previous time period. The processor compares the plurality of vectors for the current time to the vectors of the previous time periods for corresponding growing conditions and determines which previous vectors are closest to the current vectors. The plurality of previous time periods are each associated with crop yields. Thus, the processor can determine a crop yield for the current time period for a selected crop producing field and crop type based on crop yields for the closest previous time periods.

A method of predicting crop yield includes generating, via a processor, a plurality of vectors representative of growing conditions for a current time period and a plurality of vectors representative of growing conditions for a previous time period. The processor compares the plurality of vectors for the current time to the vectors of the previous time periods for corresponding growing conditions and determines which previous vectors are closest to the current vectors. The plurality of previous time periods are each associated with crop yields. Thus, the processor can determine a crop yield for the current time period for a selected crop producing field and crop type based on crop yields for the closest previous time periods.

Well management includes receiving, from a user computing system, a simulation job request for simulating well management on the cloud computing system including compute nodes, and obtaining, for the simulation job request, search spaces for completion stage simulations, fracture stage simulations, and production stage simulations. Well management further includes orchestrating, using the search spaces, the completion stage simulations, the fracture stage simulations, and the production stage simulations on the cloud computing system to obtain at least one optional well plan, and sending the at least one optional well plan to the user computer system.

Well management includes receiving, from a user computing system, a simulation job request for simulating well management on the cloud computing system including compute nodes, and obtaining, for the simulation job request, search spaces for completion stage simulations, fracture stage simulations, and production stage simulations. Well management further includes orchestrating, using the search spaces, the completion stage simulations, the fracture stage simulations, and the production stage simulations on the cloud computing system to obtain at least one optional well plan, and sending the at least one optional well plan to the user computer system.

Example embodiments provide systems and methods for simulating a disease outbreak using a relatively simple formula based on a limited number of input parameters. In particular, disease severity is computed based on a relationship between leaf wetness duration and average temperature during a wetness period. The resulting model is a physical, deterministic model that accepts hourly weather data as input and outputs the most significant severity event of disease infection during a specified (e.g., one-day) period. This information can then be used to guide the application of various treatments when they can be most effective (e.g., when predicted disease severity is at its worst).

Example embodiments provide systems and methods for simulating a disease outbreak using a relatively simple formula based on a limited number of input parameters. In particular, disease severity is computed based on a relationship between leaf wetness duration and average temperature during a wetness period. The resulting model is a physical, deterministic model that accepts hourly weather data as input and outputs the most significant severity event of disease infection during a specified (e.g., one-day) period. This information can then be used to guide the application of various treatments when they can be most effective (e.g., when predicted disease severity is at its worst).

Methods and systems estimate crop coefficients of a crop. At least one image sensor system captures a plurality of multispectral images of the crop and image data is derived from the multispectral images. At least one vegetation index of the crop is determined based on image data in at least a first spectral band. The reflectance of the crop monotonically increases and reaches a reflectance of at least 20% for at least one wavelength in the first spectral band. A crop coefficient of the crop is estimated based on the determined at least one vegetation index.

Methods and systems estimate crop coefficients of a crop. At least one image sensor system captures a plurality of multispectral images of the crop and image data is derived from the multispectral images. At least one vegetation index of the crop is determined based on image data in at least a first spectral band. The reflectance of the crop monotonically increases and reaches a reflectance of at least 20% for at least one wavelength in the first spectral band. A crop coefficient of the crop is estimated based on the determined at least one vegetation index.

A threshing state management system includes an image capture unit 80 that captures an image of a threshed material threshed by a threshing apparatus, a state detection neural network 72 that outputs a threshing processing state in the threshing apparatus based on image input data generated based on the captured image from the image capture unit 80, a parameter determination unit 73 that determines a control parameter of the threshing apparatus based on the threshing processing state, and a threshing control unit TU that controls the threshing apparatus based on the control parameter.

An agricultural data collection framework is provided in a system and method for tracking and managing livestock, and for analyzing animal conditions such as health, growth, nutrition, and behavior. The framework uses ultra-high frequency interrogation of RFID tags to collect individual animal data across multiple geographical locations, and incorporates artificial intelligence techniques to develop machine learning base models for statistical process controls around each animal for evaluating the animal condition. The framework provides a determination of normality at an individual animal basis or for a specific location, and generates alerts, predictions, and a targeted processing or application schedule for prioritizing and delivering resources when intervention is needed.