Major Cropping Pattern Prediction in Bangladesh from Land, Soil and Climate Data Using Machine Learning Techniques

The cultivation of crops on land periodically throughout the year is a cropping pattern. This research considered the prediction of major cropping patterns in Bangladesh through only the cultivation-related factors like land, soil, and climate data using Machine Learning techniques. We have considered 52 Upazilas in Bangladesh for data collection which was extracted from the book series Land and Soil Resources Usage Guidelines (in Bangla) published by SRDI, MoA, Dhaka, Bangladesh. The predictor features are a mixture of categorical and numerical data. On the other hand, the number of predicted classes is very large. So, we have used a machine learning model to introduce an effective cropping pattern prediction method that can handle mixed data points with a large number of classes. Machine learning algorithms such as K-nearest neighbors (KNN), Decision Tree (DT), Random Forest Classifier (RFC), XGboost (XGB), and Support Vector Machine (SVM) have been used for cropping pattern prediction. Our models can accurately predict cropping patterns. We have achieved more than 95% accuracy using our dataset for most of the machine learning models that we have used. Also, we have created a back-end and front-end system to use those trained machine learning models easily to predict cropping patterns.