FARM EASY: Smart Agriculture for Sustainable Development with IoT Monitoring and ML Optimization

Abstract

In the comprehensive study, we introduce FARM EASY, an innovative IoT-enabled agricultural monitoring system tailored to cater to the diverse needs of farmers. The system integrates sensors for monitoring moisture levels, controlling water pumps, and tracking temperature and humidity, ensuring a holistic approach to precision farming. The research delves into the evaluation of four machine learning models: Random Forest, Support Vector Machine (SVM), Neural Network, and Decision Tree. Notably, the experiments incorporated different crops, including but not limited to wheat, rice, soyabeans, to assess the models’ adaptability across a variety of agriculture senarios. Amidst the models tested, SVM emerges as the most promising candidate, showcasing exceptional performance. Specifically, the SVM model ith C= 1.0 and ’rbf’ kernel achieves an accuracy of 0.92, precision of 0.94, recall of 0.89, F1 score of 0.91, and ROC AUC of 0.95. these findings highlight the potentional of FARM EASY and machine learning to revolutionize precision agriculture across various crops, offering a tailored and data-driven approach for sustainable farming practices.