A Comprehensive Review of Crop Yield Prediction based on Indian Agriculture using Machine Learning.
1Shruthishree S.H, 2Saisreenivasreddy,3Vishnureddy,4Pavankumarreddy,5S. Rohith
*1 Assistant Professor, Department of Computer Science Engineering, FET, Jain University, Kanakapura(T), Ramanagara(D) , Bangalore, India.
*2,*3,*4,*5, B-Tech, Dept. of CSE Jain University: Faculty of Engineering and Technology, Jakkasandra Post, Kanakapura Taluk, Bangalore
---------------------------------------------------------------------***---------------------------------------------------------------------
Abstract - This System that recommends crops an advanced system that recommends appropriate crops for a specific region based on multiple environmental criteria using machine learning algorithms. Crop production is essential to the agriculture industry and to the food supply chain as a whole. Farmers and agricultural organisations, though, face a difficult problem when choosing the best crop to cultivate in a particular region. Crop development and yield are greatly influenced by variables like temperature, rainfall, soil pH, soil moisture, and other environmental factors. This problem is addressed by the crop recommender system employing machine learning, which makes suggestions based on analysis and prediction of data. The method trains a machine learning model using past data, which then forecasts the crops that will grow best in a specific area. The user provides information to the system about the location as well as other elements like the soil type, the availability of irrigation, and the preferred crop type. The algorithm uses the machine learning model to select crops that have a high chance of succeeding in that area based on this input. For farmers, agricultural organisations, and governmental organisations engaged in crop production, the crop recommender system can be useful. The system's crop recommendations can assist farmers in making the best crop choices and enhancing overall productivity. This may then result in increased earnings and environmentally friendly farming methods. The method can aid informing government and agricultural organizations’ decisions regarding crop production policies and strategies.
Key Words: Crop recommendation(CA), Machine learning(ML), Environmental factors(EF), Historical data(HD), Prediction, Yield optimization, Sustainable farming, Agricultural sector, Input parameters, Data analysis, Random Forest, Support vector machine (SVM), Decision Tree regression(DTR), XGBoost Classifier, Hybrid Classifier.
