Team YO
The Yield Oracles
Team YO is comprised of five students from UC Berkeley's Master of Information and Data Science (MIDS) program. The program is delivered online by the School of Information and features a multidisciplinary curriculum designed to prepare data science professionals to solve real-world problems using complex and unstructured data.
One of the core requirements of the MIDS degree is completing a synthetic Capstone course, where students combine the technical, analytic, interpretive, and communication skills they have learned during their time in the program to execute a full data science project.
This website summarizes the work undertaken by Team YO to complete the Capstone requirement. Our project aimed to predict soybean yields using ONLY satellite and weather data. We studied different modelling techniques to determine which are better for this purpose. We also attempted to make predictions earlier in the soybean growth cycle, striving for similar or better accuracy than gold-standard USDA models. Since our cost basis for this prediction is much lower than the USDA's (which utilizes a significantly more hands-on and labor intensive approach), "close enough" modelling results have tremendous advantage, and this information is extremely valuable to commodities markets.