Research Projects

Agricultural droughts – which occur due to deficit in soil water content – threaten the food security due to their impact on crop yields. There is a need to model these droughts to assist the stakeholders (government and farmers) for an effective crop management to sustain the crop productivity. Satellite remote sensing has enabled observation soil moisture, precipitation and vegetation dynamics, among others, at continental and global scales over the past four decades. Machine learning gained importance recently due to the ability to learn from the abundant data that has been accumulated from satellite sensors and other sources. This project aims to use state-of-the-art machine learning techniques to model and forecast agricultural droughts at sub-seasonal to seasonal (S2S) scales over India. The agricultural drought shall be modelled in an integrated manner by accounting the effects of soil moisture and vegetation. The project proposes a hybrid forecasting system that combines statistical and dynamical forecasts, which are obtained from ML algorithms. The methodology shall be implemented over India. This project can support NADAMS, an existing drought monitoring system by Government of India, and shall contribute towards establishing a near-real-time S2S drought forecasting system in India.