Enhanced Crop Yield through IoT-Based Soil Monitoring and Machine Learning Analysis for Rice and Sugarcane Cultivation

Abstract

Agriculture, a cornerstone of global economies, faces persistent challenges in efficient crop monitoring. This study introduces a groundbreaking IoT-based framework, integrated with a novel Deep Ensemble Learning (DEL) technique. The cuurent study objective is to enhance rice and sugarcane yield through monitoring soil parameters precisely. The framework employs an array of sensors, including moisture and pH sensors, to determine key soil properties: moisture content, pH level, Nutrient Retention Capability (NRC), and oxygen content. These parameters are crucial in assessing nutrient availability, Organic Carbon Content (OCC), soil texture, and root health. Data captured by sensors is transmitted via an Arduino kit to the cloud, where it undergoes analysis by advanced deep learning models, namely Bidirectional Long Short-Term Memory (Bi-LSTM). The ensemble of models ensures high accuracy in predicting soil parameter. The farmers acquires the processed data through a mobile application that offers actionable insights and facilitating real-time, automated agricultural interventions. Empirical results from field trials demonstrate a significant enhancement in soil parameter detection and monitoring accuracy.The application enables the IoT and DEL-based system in rice and sugarcane fields that enhances the crop yeild by 97% compared to traditional schemes. The study demonstrates the potential of integrating IoT and machine learning in agriculture paradigm shift towards the precision farming, and sets a new standard for sustainable, efficient agricultural practices.