A Comparative Analysis of Machine Learning Algorithms for Crop Recommendation

• Main Authors: M, Chandrika, Khaiyum, Samitha, Bhat, Vinay Krishna, Kodnad R, Raksha
• Format: Conference Proceeding
• Language: English
• Subjects: Agriculture; Climate data; Crop recommendation; Crops; Decision trees; Farming productivity; India's economy; LightGBM; Logistic regression; Machine learning algorithms; Meteorology; Population growth; Prediction algorithms; Productivity; Random forests; Soil; Soil data; Support vector machines; Yield prediction
• ISSN: 2767-1097
• DOI: 10.1109/CSITSS64042.2024.10816737

This paper looks at how crop recommendation and yield prediction analysis, with the help of sophisticated machine learning, help enhance farming productivity. The choices of crops and the best time for applying fertilizers are determined by using LightGBM, decision trees, SVM, logistic regression, and random forest algorithms based on soil and climate data. Upon comparing these algorithms, LightGBM and Random Forest are identified as the best algorithms. Intelligent decision support systems are imperative to agriculture's importance in India's economy. These systems use machine learning to give the best results in terms of yields, resources used, and vulnerability to market and climatic changes. In addition, taking into account the forecasts of an increase in the world population to 9.7 billion by 2050, the pressure to generate more food in a sustainable manner is inevitable. This has underlined the need and importance of adopting such intelligent technologies in improving agriculture to feed the increasing population with regard to food and conservation of the environment.