Prediction of Pesticide Goodness in Potato Crop Across Various Agriculture Lands Using Machine Learning Algorithm

Agriculture as the cornerstone of food production, involves key phases like crop cultivation and animal breeding. Beyond sustenance, agriculture significantly contributes to pharmaceutical industries by producing medicinal plants and plant extracts, serving as fundamental resources for drug development. Additionally, agriculture plays a pivotal role in providing raw materials for fabric production, such as cotton, wool and leather. India is a prominent agricultural producer, focusing on food cultivation and security. Farmers use pesticides to enhance crop protection and yield. Pesticides are the composition of materials such as plant hormones that regulate the plant growth, defoliants that prevent the plants from dying due to certain factors and also other substances that improve the yield of food products. However, predicting the impact of pesticides on crop productivity, especially in diverse agricultural lands like potato cultivation, poses challenges. This study aims to predict pesticide effectiveness in potatoes using various machine learning models, including K-Nearest Neighbors, Random Forest, Support Vector Regressor, and Linear regression. By analyzing the 'Indian Crop Production' dataset, which includes crop-specific data and pesticide usage information, the research aims to provide valuable insights for informed decision-making in agriculture.