Near-Realtime Estimation and Forecasting of National and Global Specialty Crop Supplies

Global production of perishable food crops is increasingly vulnerable to supply chain interruptions given climatic changes in key growing areas, with associated pressures such as reduced water stores, increasing incidents of new diseases and pests, and disruptive events such as wildfires and floods. Detailed knowledge of crop supply at any given time and an ability to forecast the anticipated supply into the near future are key to increasing the resiliency, efficiency and sustainability of perishable food crop production nationally and globally. This CCRPP project will refine and commercialize capabilities developed during Phase II to determine current day supply of important vegetable and berry crops and to forecast their future supply. We use novel techniques to classify the crops, which are grown in many relatively small fields in close proximity and with relatively short and staggered growth periods - attributes which historically have prevented their reliable detection and tracking with satellite imagery. We apply an innovative approach to generating larger sets of labeled data given the typical dearth of labels from on-the-ground information, which promises to make our capability highly scalable and efficient. Applying machine learning and computer vision techniques to time series of satellite imagery, the system forecasts harvest events, on a field by field basis, several weeks in advance and with an error of about one week. The outcome will be an operational capability to deliver up-to-date estimates of crop supply and risk monitoring and forecasts of the associated supply chain for these crops into the near future, for commercial stakeholders of the fresh produce industry and with applications to global food security.

Potential applications include the NASA Harvest consortium for global ag and food security and NASA Acres for US ag. Labeled imagery data will be relevant for training other NASA land class models through repositories such as MLHub. Frequently updating crop acreages will address the data gap in the Cropland Data Layer (CDL) and would be of direct benefit to critical federal and state programs, including the national GHG MMRV strategy, the U.S. Bureau of Reclamation, the National Land Cover Database (NLCD), and state water boards.

This is a mature technology (TRL 7) — the realistic path in is usually NASA's Technology Transfer Program: licensing an existing NASA patent, or a Space Act Agreement to use NASA facilities/expertise directly. NASA also runs a startup licensing program with no upfront fee for companies formed to commercialize a specific NASA technology.

None of these are guaranteed paths for this specific project — TechPort itself doesn't have an "apply" button. Reaching out to the contact(s) above with a specific question is usually the fastest way to find out what's actually open.