Abstract
<title>Abstract</title> <p>This study explores the application of machine learning (ML) algorithms for the automated detection of forest degradation using remote sensing data. Five machine learning models: Logistic Regression (LR), Decision Tree (DT), Random Forest (RF), Naïve Bayes (NB), and Support Vector Classifier (SVC) were trained and evaluated using multi-temporal satellite imagery and vegetation indices such as Normalized Difference Vegetation Index (NDVI) and Enhanced Vegetation Index (EVI). A reference dataset was generated through remote sensing image interpretation and field validation to train and validate these models. The results revealed that all models performed well in distinguishing degraded and undisturbed forest areas, with accuracy scores ranging from 92% to 99%. Among the models, SVC demonstrated the highest performance, achieving 99% accuracy, followed by DT (98%) and RF (97%). The Receiver Operating Characteristic (ROC) Curve analysis further confirmed the superiority of these models in detecting forest degradation patterns. These findings highlight the effectiveness of ML-based remote sensing analysis as a reliable and scalable tool for monitoring forest health. Thus, it recommends the adoption of ML-driven forest assessment frameworks in Nigeria’s conservation policies to enhance sustainable forest management.</p>