Paper Title
INTELLIGENT SOIL HEALTH MONITORING USING MACHINE LEARNING

Abstract
Good soil makes good crops. But many farmers still struggle to understand what their soil truly needs. Traditional soil testing methods are slow, expensive, and often out of reach for small or remote farms. This paper explores a simple, technology-driven solution that uses machine learning to analyze soil data and help farmers make smarter, faster fertilizer decisions. By looking at key nutrients like nitrogen, phosphorus, and potassium along with environmental factors such as temperature and humidity the system predicts nutrient deficiencies and suggests the right fertilizers for healthier soil and better harvests. A Random Forest model was chosen for its accuracy and reliability, and the final recommendations are delivered through an easy-to-use web app built with Flask and deployed on Render. The goal is to make soil analysis accessible, practical, and helpful for the people who work the land every day. Keywords - Soil Health, Machine Learning, Fertilizer Suggestion, Sustainable Farming, NPK Prediction, Random Forest, Smart Agriculture