Dataset for: Retrieval of Rice Crop Biophysical Parameters from Sentinel-2 Imagery Using Parsimonious Multioutput Machine Learning Techniques Project

This dataset contains Jupyter notebook code for training novel parsimonious multioutput machine learning models for simultaneous retrieval of Leaf Area Index (LAI) and Leaf Chlorophyll Content (LCC) biophysical parameters from Sentinel-2 imagery. It also contains about 200 in-situ rice LAI and LCC measurements, three Sentinel-2 images resampled using the Sen2Res tool embedded in SNAP software, the study area shapefiles, predicted biophysical parameters maps, and SHapley Additive exPlanations (SHAP) feature importance plots. Field campaigns were conducted in 2023 at Ahero Irrigation Scheme, Kenya, as part of Afri4CAst project.