Analysis and Prediction of Soil Fertility using Machine Learning Techniques: A Case Study of North Wollo Zone in Amhara Region

This research aimed to analyze and predict soil fertility using machine learning techniques, focusing on the North Wollo zone in the Amhara region of Ethiopia. The study is crucial due to the increasing demand for agricultural production among constraints such as limited land and water resources. The objective of this study is to analyze and predict soil fertility using machine learning techniques, specifically targeting the North Wollo zone in the Amhara region of Ethiopia. The dataset for this study comprises 20,168 instances, including both fertile and nonfertile samples, with 19 selected attributes. Several machine learning models were evaluated on both the original and SMOTEbalanced datasets. The models included Random Forest, AdaBoost, Support Vector Machine (SVM), and XGBoost classifiers. The Random Forest classifier consistently demonstrated the highest performance, with testing accuracies of 95.50% on the original dataset and 94.39% on the SMOTE-balanced dataset. AdaBoost also showed strong performance, achieving testing accuracies of 94.00% and 94.39% on the original and SMOTE-balanced datasets, respectively. SVM and XGBoost performed well but were slightly less accurate compared to the ensemble methods. However, XGBoost showed robust performance on both datasets, with testing accuracies of 93.00% and 93.07%. Feature importance analysis using the Random Forest classifier has shown that factors such as Clay, CEC, CaCO3, Sand, and Mn significantly impact soil fertility prediction. The study concluded that the Random Forest classifier, an ensemble-based learning technique, was the most reliable and accurate model for predicting soil fertility. These results highlight the importance of specific soil properties in determining fertility and can guide targeted soil management practices to improve agricultural productivity.