Harnessing Machine Learning to Assess Climate Change Impacts on Agricultural Productivity (KEY IJP************856)

• Joel Varghese,Dr Sandeep Gupta

Abstract

This review paper investigates the intersection between climate change and agriculture through the lens of machine learning (ML). They examine how such models improve predictions of crop yields under varying climatic conditions, including Multivariate Adaptive Regression Splines (MARS), neural networks, and hybrid approaches. The review concentrates on their nature in modeling the non-linear relationship between climate variables and agricultural productivity, particularly food grains and oilseeds court in India. Besides enumerating the strengths, weaknesses, and promises of ML methods for providing insights into the decision-making process of policymakers, the work traces newly recognized pathways detailing ML research and its role in propelling adaptive agricultural strategies to usher in sustainable development.