PREDICTION OF CROP YIELD BASED ON SOIL MOISTURE

Agriculture, as one of the oldest and most fundamental human activities, plays a vital role in ensuringfood security and supporting economies globally. However, modern agricultural practices face several challenges,including climate change, resource depletion, and variable environmental conditions, all of which can impactcrop yields. Consequently, accurate prediction of crop yields has become an essential tool in optimizingagricultural practices, ensuring sustainable food production, and maximizing farm productivity.In this context, the Prediction of Crop Yield has emerged as a critical area of research, particularly with theadvent of advanced machine learning techniques. These techniques can help provide more precise estimatesby analyzing the relationship between various environmental, soil, and crop factors.This project presents a Crop Yield Prediction System, designed to leverage machine learning algorithms,specifically the Decision Tree model, to predict agricultural yields based on key soil and environmentalparameters. The system is web-based and developed using the Flask framework, making it accessible and easyto use for farmers, agricultural researchers, and industry professionals.The primary objective of this system is to automate the yield prediction process, enabling users to input essentialagricultural parameters such as soil pH, temperature, humidity, wind speed, and nutrient levels (Nitrogen,Phosphorus, Potassium). The application processes these inputs through data preprocessing techniques,including numerical transformation and one-hot encoding, which align the data with the model's requiredstructure.