Method and system for spatial-economic analysis of agricultural fields

A computing system for providing a high-resolution analysis of an agricultural field, comprising:

• one or more processors;
• and
• one or more memories storing instructions that, when executed by the one or more processors, cause the computing system to:
• partition the agricultural field into hexagonal grid cells;
• measure a set of agricultural inputs for each of the respective grid cells,
• wherein the set of agricultural inputs includes both direct costs and indirect costs;
• receive market data corresponding to a crop planted on the agricultural field;
• compute an agricultural yield for each of the respective grid cells;
• compute a gross revenue for each of the respective grid cells by analyzing a respective cost of each of the agricultural inputs, the market data and the respective agricultural yield of each of the respective grid cells;
• compute a net revenue for each of the respective grid cells by subtracting at least the direct costs and the indirect costs from the respective gross revenue;
• generate an analysis report including the gross revenue, the agricultural yield, and the net revenue for each of the respective selected grid cells by processing the respective selected grid cells using a machine learning model trained using labeled yield data and revenue data to generate one or more recommendations, each corresponding to a respective one of the respective grid cells;
• and
• transmit the analysis report to a computing device for display to the user,
• wherein the analysis report includes recommendations for adding or subtracting one or more agricultural inputs based on the net revenue and as-applied data of the respective grid cells.

A non-transitory computer readable medium containing program instructions that when executed, cause a computer to:

• partition the agricultural field into hexagonal grid cells;
• measure a set of agricultural inputs for each of the respective grid cells,
• wherein the set of agricultural inputs includes both direct costs and indirect costs;
• receive market data corresponding to a crop planted on the agricultural field;
• compute an agricultural yield for each of the respective grid cells;
• compute a gross revenue for each of the respective grid cells by analyzing a respective cost of each of the agricultural inputs, the market data and the respective agricultural yield of each of the respective grid cells;
• compute a net revenue for each of the respective grid cells by subtracting at least the direct costs and the indirect costs from the respective gross revenue;
• generate an analysis report including the gross revenue, the agricultural yield, and the net revenue for each of the respective selected grid cells by processing the respective selected grid cells using a machine learning model trained using labeled yield data and revenue data to generate one or more recommendations, each corresponding to a respective one of the respective grid cells;
• and
• transmit the analysis report to a computing device for display to the user,
• wherein the analysis report includes recommendations for adding or subtracting one or more agricultural inputs based on the net revenue and as-applied data of the respective grid cells.