Ml-enhanced mechanistic crop modeling to address noise-induced uncertainty for drought environmental monitoring in rice

Abstract

Advancing our understanding of environmental interactions in rice crops contributes to food production in water-limited regions. This paper proposes an integrated crop modeling architecture, demonstrating how machine-learning (ML) models enhance classic Mechanistic Crop Modeling (MCM) estimations by learning directly from environmental data. Here, we quantify the impact of noise-induced uncertainty on the CERES-Rice crop growth model, particularly relevant for drought-tolerant varieties that exhibit complex adaptation mechanisms, such as Nerica 4 (Oryza sativaOryza glaberrima hybrid). Environment characterization is achieved through a novel 3D Gaussian Mixture Model (GMM), offering enhanced precision and scalability when coupled with remote-sensing satellite-derived environmental data. By coupling both MCM and ML models, we achieved superior estimations for grain yield () and biomass () in the northwest Tambacounda region of Senegal in Africa, providing reliable estimates of grain conversion efficiency and kg/ha·mm water use efficiency from an environment characterized by sandy soils with high saturated hydraulic conductivity (1.1 cm/h) and the lowest regional precipitation (513 mm, 49%).