Soil Monitoring and Crop Recommendation System Using Machine Learning and Internet of Things
Dr. P. B. Ambhore1, Sadiya Abdul Salim2, Sajeed Khan3, Yash Ingle4, Abhay Patle5
1Guide of Department of Information Technology, Government college of Engineering Amravati 444604.
2Student of Department of Information Technology, Government college of Engineering Amravati 444604.
3Student of Department of Information Technology, Government college of Engineering Amravati 444604.
4Student of Department of Information Technology, Government college of Engineering Amravati 444604.
5Student of Department of Information Technology, Government college of Engineering Amravati 444604.
---------------------------------------------------------------------***---------------------------------------------------------------------
Abstract - Agriculture is the pillar of the Indian economy, with over 50% of India's population dependent on it. Variations in weather, climate, and environmental conditions pose significant risks to agriculture. Machine learning (ML) serves as a crucial decision support tool for Crop Yield Prediction (CYP), aiding decisions on crop selection and management during the growing season. CYP involves predicting yields using historical data, meteorological parameters, and past yield records. ML-based crop yield prediction offers accurate forecasts by leveraging diverse datasets, including meteorological conditions, soil characteristics, and historical crop performance. This technology helps farmers make informed decisions, optimize resource allocation, and mitigate risks from environmental unpredictability. Integrating ML into CYP promotes sustainable farming practices, ensuring food security and economic stability amid a dynamic agricultural landscape. The Random Forest regression, a supervised learning model, has demonstrated high performance, achieving an accuracy of 92.3%. This method supports optimal yield forecasting, aiding farmers and policymakers in better planning for crop production and management.
Key Words: agriculture, crop yield prediction, machine learning, meteorological data, Random Forest regression, sustainable farming.
