A Comprehensive Crop Recommendation System Lever- aging Internet of Things and Machine Learning

In the pursuit of sustainable agriculture and food security, the efficient use of soil nutrients is paramount. This paper presents the development of an Internet of Things (IoT) and Machine Learning (ML)-based system for crop recommendation. The system features a sensor that leverages visible infrared spectroscopy to accurately determine the nitrogen-phosphorus-potassium (NPK) concentration in soil. Integrated into a sensor node comprising of the ESP32 system-on-chip (SoC), this device collects real-time soil data and transmits it to the cloud. In the cloud, a web application employs a machine learning model developed from the random forest ML algorithm to analyze the NPK data and recommend the most suitable crops for cultivation on the given land. The developed model achieved a 91.1% overall accuracy. This approach not only optimizes crop selection but also promotes sustainable agricultural practices by ensuring that crops are matched to the soil's nutrient profile, consequently leading to improved crop yield while reducing environmental impact.