Investigating the Deep Learning Performance for Deforestation Mapping Using Landsat Multispectral Data
- 13 May 2026
- conference paper
- Published by Trans Tech Publications, Ltd. in Advances in Science and Technology
- Vol. 177, 163-174
Abstract
Deforestation is a significant threat to the sustainability of the ecosystem, leading to adverse effects such as climate change, biodiversity loss, and socio-economic consequences. Timely monitoring of forest destruction enables effective implementation of preventive mechanisms supported by law enforcement. Advancements in remote sensing, coupled with enhanced deep learning techniques, boost efficient deforestation monitoring as these technologies support real-time analysis of complex satellite images. Thus, this study aimed to develop a classification model to identify forest areas from non-forest areas using Landsat-8 data acquired for Wilpattu park, Sri Lanka, between 2015 to 2024. We explored model building using minimal input of two bands in satellite data, facilitating low resource needs. Seven deep learning models were explored, progressing from Convolution Neural Networks to Transformer-based models to build the classifier using a set of patches of size 100×100. The results were evaluated using standard metrics such as accuracy, precision, recall, F1 score, and Kappa index. We found that SegNet outperformed the remaining models with an overall accuracy of 96.36%, F1 score of 0.97, and Kappa index of 0.92, demonstrating excellent ability to distinguish the classes. However, the efficiency of the model needs further improvement. The proposed system will contribute to deforestation detection, offering a simpler model development approach with minimum input requirements. The proposed method can be adopted to other domains where the chosen band combination supports effective detection, such as water body identification.Keywords
This publication has 17 references indexed in Scilit:
- Advanced characterization of deforestation frontiers in Nigeria utilizing deep learning and Bayesian approaches with sentinel-1 SAR imageryGeocarto International, 2025
- Automatic deforestation driver attribution using deep learning on satellite imageryGlobal Environmental Change, 2024
- Deep Transformer-Based Network Deforestation Detection in the Brazilian Amazon Using Sentinel-2 ImageryIEEE Geoscience and Remote Sensing Letters, 2024
- Remote sensing based forest cover classification using machine learningScientific Reports, 2024
- A survey of machine learning and deep learning in remote sensing of geological environment: Challenges, advances, and opportunitiesISPRS Journal of Photogrammetry and Remote Sensing, 2023
- Deforestation Detection in the Brazilian Amazon Using Transformer-based Networks2023
- A Vision Transformer Model for Convolution-Free Multilabel Classification of Satellite Imagery in Deforestation MonitoringIEEE Transactions on Neural Networks and Learning Systems, 2022
- Estimating Deforestation using Machine Learning Algorithms2021
- Crops Classification from Sentinel-2A Multi-spectral Remote Sensing Images Based on Convolutional Neural Networks2018
- Deep learning for pixel-level image fusion: Recent advances and future prospectsInformation Fusion, 2018