A Systematic Review of Ml Techniques in Crop Yield Prediction

Abstract

In India, there are several strategies to enhance crop productivity and boost economic growth in agriculture. One promising avenue involves leveraging recent technological advancements, such as Machine learning (ML), to predict crop outcomes based on atmospheric and soil parameters of agricultural land. ML serves as a crucial tool for aiding decisions related to crop yield prediction, offering valuable insights into determining optimal crops to cultivate and guiding actions throughout the crop's growing season. In our investigation, we systematically reviewed the literature to collect and merge data concerning the algorithms and characteristics employed in research centered on forecasting crop yields. Different ML algorithms have been employed for facilitating research in crop yield prediction.  The study under consideration examines ML approaches, including Support Vector Machine (SVM) and Random Forest (RF), in the context of predicting crop yields.