Optimizing Crop Yield Data

Optimizing Crop Yield Data Collection for Supply Chain Enhancement

Collecting high-quality crop data is expensive, but is paramount to improving policies and programs that can dramatically benefit smallholder farmers in numerous ways, especially by enhancing supply chains. The NASA Harvest Program at the University of Maryland along with their partners collected high-quality datasets to capture yield and other field characteristics in smallholder rice fields in Tanzania. Their local partners included the Sokoine University of Agriculture based in Morogoro and Flamingoo Food Limited. The project leveraged ECAAS’s Open Data Kit (ODK) to collect yield data and test the utility of these data by testing and applying the Global Earth Observations for Crop Inventory Forecasting (GEOCIF) system at a field scale on rice. GEOCIF, a machine learning forecasting model, estimates field-scale crop yields and their applicability to other rice-growing regions. By demonstrating the utility of machine learning models for optimizing yield data collection, this project informed and reduced the cost of collecting yield data that were critical for agricultural decision-making.

Tanzania

• Project Lead:
  • Dr. Catherine Nakalembe
• Team Members:
  • Dr. Inbal Becker-Reshef, Dr. Hannah Kerner, Dr. Ritvik Sahajpal
    Department of Geographical Sciences, University of Maryland College Park/ NASA Harvest Program
• Key Partners:
  • Dr. Sixbert K Mourice, Sokoine University of Agriculture (SUA), Tanzania
  • Dr. Andreas Schlueter, Adrian Weisensee and Leonard Lusaganya, Flamingoo Foods Company Limited, Tanzania