TOOLS 50+1: Technology of Object-Oriented Languages and Systems – Innopolis University, Innopolis (Russia)
Crop yield and early disease forecasting is one of the most important strategies in agriculture which enables sustainability.
This work aims to make the Sentinel data usable for the agricultural domain to support large-scale crop disease detection and yield prediction relying upon chlorophyll dynamics.
The objectives are therefore to develop machine learning models for within-season prediction of sorghum foliar disease development based on Sentinel-derived NDVI (normalized difference vegetation index) and biomass yields before harvest based on fAPAR(fraction of absorbed photosynthetically active radiation) measurements from Sentinel 2A and Sentinel 2B satellite constellation images.
See more: The visual presentation