Exploring the relationship between rainfall and crop yield and best practices adoption using participatory approach

Crop yield is a standard measurement for the amount of agricultural production. Sustainable agriculture demands an increase in crop yield. This study deals with rainfed agriculture; hence, precipitation becomes the driving factor for crop yield. Heat maps are used to examine the rainfall and crop yield correlations. ML is an essential tool in decision-making, and many ML algorithms are available for prediction. This study uses the ML algorithms to predict whether the crop yield will increase with increased rainfall. Logistic regression, Decision tree classifier, Random Forest classifier, and XGBoost classifier are the algorithms chosen for analysis. Altogether this region consists of forty crops but focuses on five predominant annual crops. Implementation-based results are the universal goal of every research which society needs. The chances of implementation are associated with two major components: the reliability of the results and society's willingness. Analysis of these components needs ground truthing and Participatory Rural Appraisal, respectively. Farmers and villagers filled out a questionnaire about the details required for this study. The survey was an active approach to collecting necessary information from the participants. The survey showed positive results among one hundred and fifty samples from six blocks. Finally, cashew nut, sugarcane, and turmeric showed good dependency on the precipitation, and around 88% of villagers are ready to implement the results derived from ML algorithms.