Real Time Crop Recommendation System Using Machine Learning

Food security depends heavily on agriculture, and crop selection based on environmental factors is essential for optimizing production. This project, Real-time Crop Recommendation System Using Machine Learning, combines machine learning and Internet of Things-based sensor technologies to offer real-time crop suggestions that are adapted to climate and soil conditions. Several sensors, including soil moisture, pH, temperature, humidity, sunlight lux, and a raindrop module, are linked to the NodeMCU ESP8266 hardware system. Real-time ambient and soil characteristics are gathered by these sensors and sent to the Blynk Cloud IoT platform for monitoring. A machine learning model based on the Random Forest Classifier is then trained using the collected data and a dataset that includes ten distinct crops (onion, potato, tomato, rice, banana, maize, guava, pomegranate, and sugarcane). After analyzing these variables, the algorithm forecasts which crop would be best to grow. This method maximizes agricultural output by giving farmers data-driven insights to help them make wise decisions. This strategy guarantees real-time adaptation to shifting environmental circumstances, in contrast to conventional approaches that depend on experience and broad weather patterns. Future improvements will involve adding more sensors, growing the dataset, and improving the model's accuracy.