ARTIFICIAL NEURAL NETWORK IN AGRICULTURE PRODUCTION: A LITERATURE REVIEW

Dr. Syed Tabrez Hassan¹

¹Associate Professor,School of Business and Economics, Adamas University, Kolkata

Abstract:

Agriculture has been the cradle of civilization, and in the case of India, it remains a cornerstone of its economy, heavily reliant on crop productivity. Currently, India holds the second position globally in farm production. The agriculture sector, along with allied activities like forestry and fisheries, contributed to 14.5% of the GDP in 2015, engaging about 50% of the total workforce. Despite a noticeable decline in its contribution to the GDP, agriculture continues to be the broadest economic foundation in India, playing a pivotal role in the socio-economic framework. Various factors impact Indian agriculture, including climate, topography, history, geography, biology, politics, and institutional and socio-economic elements. Over time, shifts in natural factors, technological advancements, and evolving policies have led to significant variations in agricultural production across different regions of the country.

Crop prediction can be accomplished through the application of diverse machine learning algorithms, including mathematical and statistical methods. This section outlines some of the methods that have been previously examined and studied.

Keywords: Agribusiness, ANN, Machine Learning