Abstract
Agriculture faces growing challenges from climate variability, resource scarcity, soil degradation, and emerging pests and diseases. Computer-based models support scientific decision-making by simulating agricultural processes using weather, soil, crop, water, management, and socioeconomic data. Traditional crop models, including DSSAT, APSIM, AquaCrop, and WOFOST, estimate crop growth, yield, and environmental responses. Recent advances in artificial intelligence, machine learning, remote sensing, IoT, and digital twins have expanded predictive capabilities. This article reviews agricultural modelling approaches, applications, advantages, limitations, and future prospects, emphasizing integrated, accurate, and sustainable decision-support systems.
BECOME A MEMBER