IoT-Enhanced Agricultural Water Management System Utilizing Conventional Machine Learning Methods
Jagendra Singh, Neha Garg, Sonal Kukreja, Mayank Saini, Ishaan Singh, Shachi Mall
Abstract
This study delves into IoT-enhanced Agricultural Water Management, aspiring to transform farming for enhanced crop output and sustainability. It focuses on an intelligent system incorporating a sensor network and varied machine learning methods for climate monitoring and yield prediction in tomato cultivation. Notably, the Convolutional Neural Network (CNN) stood out with a 95.2% accuracy rate in predicting yields, highlighting its potential as a pivotal tool in effective irrigation management. This adaptive, data-driven system promises advanced water management, addressing pressing global concerns of food security and resource conservation by aligning agricultural practices with environmental parameters and enabling heightened crop productivity.