Investigating the Deep Learning Performance for Deforestation Mapping Using Landsat Multispectral Data

A.M. Chandrika Malkanthi; B.T.G.S. Kumara; D.R. Welikanna; R.M.K.T. Rathnayaka

doi:10.4028/p-4s2C0f

Paper Titles

Duty Cycle-Aware Energy-Efficient MAC Protocol for Single-Layer Hierarchal UAV-WSN
p.81

Advancing Circular Economy: Utilizing Shredded Scrap Tyres in Gabion Wall Construction
p.93

Flammability Characteristics of Waste-Based Fibre-Reinforced Composite Using Palmyra Fibre and Waste Polythene
p.101

Experimental Study to Investigate the Compression Responses of Concrete with Waste Tire Aggregates under Varying Loading Conditions
p.115

Spatially Integrated Water and Wastewater Management: A Model Design for Fish Markets in Sri Lanka
p.129

Performance Verification of the Leachate Treatment Plant: A Dilution-Based Engineering Approach
p.141

AI Adoption in the Research Component of Business Processes: Enhancing Effectiveness in Client Acquisition for IT Services Organizations
p.151

Investigating the Deep Learning Performance for Deforestation Mapping Using Landsat Multispectral Data
p.163

Applying the Multifaceted Potential of Seaweed in Bioplastics to Advance Sustainable Development in Sri Lanka – A Review
p.175

HomeAdvances in Science and TechnologyAdvances in Science and Technology Vol. 177Investigating the Deep Learning Performance for...

Investigating the Deep Learning Performance for Deforestation Mapping Using Landsat Multispectral Data

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.