Case Study: EOS achieves accurate sugarcane yield prediction in São Paulo with EOSDA

EOS predicts sugarcane yields in São Paulo with EOS

The customer, EOS Data Analytics (EOSDA), faced the challenge of accurately predicting sugarcane yields in São Paulo, Brazil, where diverse weather and soil conditions made traditional manual methods ineffective. The vendor, EOSDA, tackled this by using its AI-powered satellite imagery analytics to create a scalable yield prediction model.

The solution implemented by EOSDA involved calibrating the WOFOST crop model with historical data, weather inputs from NASA POWER, and soil maps from ISRIC SoilGrids. This tailored approach allowed EOSDA to accurately predict sugarcane yields at the field level, providing farmers with actionable insights to optimize resources and improve productivity, and proving the model's scalability for broader application.

EOS