MACHINE LEARNING-BASED CROP YIELD PREDICTION USING WEATHER AND SOIL PARAMETERS: A SURVEY

Abstract

Agriculture is one of the fundamental sectors contributing to economic growth and food security worldwide. Accurate crop yield prediction plays a crucial role in agricultural planning, resource management, and decision-making. Traditional agricultural prediction methods often fail to handle complex relationships among climatic conditions, soil characteristics, and crop productivity. In recent years, Machine Learning (ML) techniques have emerged as effective tools for analyzing agricultural datasets and predicting crop yields with improved accuracy. This survey paper presents a comprehensive review of machine learning-based crop yield prediction approaches using weather and soil parameters up to the year 2022. Various ML algorithms such as Linear Regression, Decision Tree, Random Forest, Support Vector Machine (SVM), Artificial Neural Network (ANN), and Deep Learning models are discussed. The paper also highlights datasets, methodologies, advantages, and limitations of existing research works. Furthermore, research gaps and future directions in smart agriculture and precision farming are identified. The survey concludes that hybrid machine learning and deep learning models integrated with IoT and remote sensing technologies can significantly improve agricultural productivity and sustainability.