Abstract: Systems and methods that use geospatial data to train machine learning models to make predictions based on the geospatial data, for example for use in precision agriculture. A database is created that includes agricultural geospatial data acquired from two or more data sources. Using the spatial and temporal extent of response data, a training vector and a training feature matrix are then generated using a data systematic approach to engineer a virtually infinite number of training features derived from the database. A plurality of machine learning models are then trained using the training vector and the training feature matrix, with each one of the trained machine learning models generating a test result. At least one of the trained machine learning models is chosen to create predictions using new data at the spatial and temporal extent of interest. An output is created using the prediction(s) on the new data.

Abstract: A method of determining the nitrogen status of an area of land includes determining a critical nitrogen concentration for aboveground vegetation of plants in the area of land based on a dry weight biomass of entire plants and determining an actual nitrogen concentration for the aboveground vegetation of the plants. A critical nitrogen concentration for the entire plants is determined based on the dry weight biomass of the entire plants. The actual nitrogen concentration for the aboveground vegetation, the critical nitrogen concentration for the aboveground vegetation, the critical nitrogen concentration for the entire plants and the dry weight biomass of the entire plants are combined to form the nitrogen status for the area of land.