Accurate Detection of Treeless Areas in Forests Using Deep Learning Models

Abstract

In order to maintain biological diversity, control climate, and manage sustainable resources, forests are an essential part of the global ecosystem. To improve the efficacy of forestry methods, estimate the effects of natural disasters, and fortify environmental legislation, it is crucial to monitor and classify forests. This study applies deep learning models, especially U-Net and Res-Net, to imagery from satellites to identify deforested areas within forests. The models were studied for segmentation, and the resulting data was compared. With 96.1% accuracy, 27% IoU, and 92.7% Dice Coefficient, the U-Net model performed quite well in identifying deforested areas inside of forests. As a result of these excellent results, U-Net architecture-based applications have the potential to positively impact a wide range of applications, from forestry to monitoring and predicting fires, assessing the consequences of natural disasters, and improving environmental policy.