Machine Learning Based Crop Recommendation Using Tuned Classifiers and Ensemble Methods

Abstract

Faiza Noushin Priya, Shahria Badhon, Mirza Md. Hasibul Hasan, Sraboni Ghosh Joya and Mahfiza Akter

The choice of a suitable crop for a given situation is determined by soil and various climatic parameters. For choosing these crops, we commonly use machine learning models, but combining multiple models, called ensembling, and checking whether an ensemble model can beat one well-tuned model is still an important question. In this paper this is directly checked. We have chosen two public ’crop recommendations’ datasets for comparison, and selected a balanced sample consisting of 22 crops and 2,200 records. Five models were trained under identical conditions; Logistic Regression, KNN, Random Forest, XG Boost, and Feedforward Neural Network. Next, we fine-tuned the hyperparameters of the top three models using Grid Search and incorporated them into the soft voting, hard voting and stacking ensembles. To avoid data leakage, we used train, validation and test set with a clean split that ensures at no point we had the same observations split between the three sets. The final results indicate that a well calibrated Random Forest model obtained the same accuracy as the three ensemble models. This demonstrates that if a single model is tuned right, this won’t help performance if one introduces additional models on this dataset. This therefore provides a cost-effective, lightweight and easy-to-install answer without running redundant models side by side for precision farming and for automatic crop selection applications.

PDF