CROP RECOMMENDATION SYSTEM USING MACHINE LEARNING
Aniket Kulkarni, Abhishek Kumar, Yash Pavse, Yash Pavse, N Heemageetha, Sankara Babu, G Suneetha, Y Charles Babu, G Nagendra Kumar, Karuna, Patil, Beldar, Naik, Deshpande, Parent, Tardieu, Niketa Gandhi, Leisa Armstrong, Owaiz Petkar, Awuor, Kimeli, Rabah, Rambim, W Fan, C Chong, G Xiao Ling, Y Hua, W Juyun
Abstract
The accurate prediction of crop yields poses significant challenges in developing agricultural systems.Fluctuating climatic conditions, including periods of drought and rising temperatures, create substantial difficulties for farmers, governments, and traders who seek precision and analysis in crop production across different weather scenarios.To address this issue, this system employs a machine-learning approach using the Random Forest algorithm, which demonstrates the ability to analyze crop growth in relation to prevailing climatic conditions and biophysical changes.Datasets on crop growth from various sources are collected and utilized for both training and testing purposes.The Random Forest classifier proves to be highly effective in predicting crop yield, as evidenced by its precise data analysis capabilities.The outcomes obtained from this approach highlight the algorithm's efficiency in analyzing crops under current climatic conditions, thereby offering valuable insights for agricultural decision-making.