IoT and Machine Learning-Based Prediction of Smart Soil Moisture Monitoring and Irrigation System

Abstract

Abstract— A country like India faces an acute water shortage, with 35 million people lacking access to safe water. India is the world's largest groundwater user, as tube wells, the main source of irrigation for Indians, provide 46% of water for irrigation. IoT and machine learning can be vital in overcoming acute water shortages and achieving optimum water resource utilization. This paper aims to present an ML model to estimate the soil moisture level and IoT to act upon it. We are introducing a working plan to collect data on soil moisture, temperature, and humidity, utilizing sensor nodes deployed in the agricultural field to gather various sensor data. The gathered data is forwarded through IoT and stored in a cloud-based database like MongoDB. This data applies to machine learning techniques for classification. Several models, such as Naive Bayes (NB), Logistic Regression (LR), and Support Vector Machine models (SVM), are utilized. The experimental results, with accuracy rates of 98.8%, 99.0%, and 99.3% for Naive Bayes, Logistic Regression, and Support Vector Machine models respectively. The combination of IoT and machine learning helps to achieve environmental goals efficiently in water resource utilization and better crop yield.