Planted Area
Each farm field is assigned a crop using an approach that varies over the course of the year. Pre-season associations are based on crop rotation patterns. The associations are updated midway through the growing season to determine the crop type based on analysis of multi-spectral satellite data. After the season is complete the USDA releases its official Cropland Data Layer (CDL). This provides the basis for the final crop-to-field associations for growing seasons that have passed. The total area planted to a given crop within a user’s draw area is calculated by summing the field-by-field acres for all fields contained therein.
Yield Forecast
Yield forecasts are produced using an ensemble of machine learning-based models that translate weather conditions, soil conditions, USDA crop condition reports, as well as various other data and metadata into forecasted crop yields at the county level. These county-level yield forecasts are then disaggregated across all fields hosting that same crop within the county using both historical and current-season satellite-based indicators of crop development and health. Once the USDA Risk Management Agency (RMA) releases ‘final’ yields for a season for each crop and county combination, those yields are similarly disaggregated to produce final field-level estimates of crop yields.
Abandonment
Abandonment is forecast using machine learning models that draw associations between weather/soil conditions, crop condition ratings and satellite data and county-level crop abandonment rates published by the RMA. Since it is not known which specific fields will be (or were) abandoned, the impacts of crop abandonment are only quantified at the draw area level. As such, the summation of acres and production from all of the individual fields within a county will generally not equal that which would be associated with that county if it were set up as its own draw area. The latter would show smaller acreage and production than the summation from its fields due to the factoring in of crop abandonment.
Production
Draw area production is calculated by summing field-level production within the draw area and then reducing that based on the reported or predicted rate of crop abandonment. Field-level production is calculated simply as the field acreage multiplied by the corresponding fields expected yield.
Inventory (currently only on-farm inventory)
This figure is the estimated amount of the selected crop being held as on-farm inventory. Inventory is assigned to each farmer’s bins based on a combination of the volumes of various crops the farmer has grown in the most recent crop year and propensity-to-store data based on statewide allocation of the available storage space (as published by the USDA). The farm-level inventory data are then normalized to be consistent with state-level inventory data reported by the USDA in its quarterly grain stocks reports.