article · SN Applied Sciences
Machine learning approaches offer a pathway to semantic segmentation for land cover classification in Gambella National Park. Mapping land cover in regions with highly heterogeneous classes across small areas has previously proved difficult due to coarse satellite image resolution, reliance on standard statistical classifiers, and challenges in selecting optimal patch sizes. To tackle these constraints, a deep learning pixel-level semantic segmentation technique was developed using high-resolution Sentinel-2 satellite imagery. The approach adapts the LinkNet architecture by modifying its encoder to incorporate ResNet34. Performance was assessed alongside support vector machine and random forest classifiers using convolutional neural network features. The modified LinkNet-ResNet34 model attained an average F1-score of 87.4 percent, surpassing the random forest approach at 82 percent and the support vector machine at 81 percent.
Accurate land cover classification is essential for monitoring complex natural landscapes with diverse environmental features. By delivering reliable pixel-level identification in heterogeneous areas using Sentinel-2 imagery, deep learning models provide improved spatial mapping capabilities. This overcomes historical technical bottlenecks related to patch-size selection and coarse image resolution in complex protected environments such as national parks.
The work demonstrates an applied and tested approach to land cover mapping in heterogeneous landscapes. Environmental monitoring agencies, park authorities, and conservation planners could utilise this pixel-level classification model to process Sentinel-2 data for environmental tracking. Because the research remains validated at the model evaluation stage within a single study area, operational software integration and commercial deployment would require further development and wider geographical testing.
AI-generated from the published abstract. Always read the original work before citing.
Abstract This work uses machine learning approaches to present semantic segmentation for land cover classification in Gambella National Park (GNP). Land cover classification has become more accurate due to developments in remote sensing data. Land cover classification from satellite images has been studied, but the methodologies and satellite data employed so far are not suitable for research regions with the possibility to find heterogeneous land cover classes within small areas. Previous studies found issues with the satellite images coarser spatial resolution, the use of standard statistical methods as classifiers, and the difficulty in optimal patch size selection when patch-based classification is used. To address these issues, we suggested a deep learning-based semantic segmentation model that could be utilized as a pixel-level land cover classification technique. The suggested technique employed high-resolution Sentinel-2 satellite images of our study area (GNP) as a dataset and constructed and assessed pixel-level classification models. As a deep learning-based classification model, we have used the Link-Net architecture and its encoder part was modified further to incorporate the state-of-the-art architecture called ResNet34. The developed models, support vector machine with CNN features (CNN–SVM), random forest with CNN features (CNN-RF), LinkNet model with ResNet-34 as encoder (LinkNet-ResNet34), attain average F1-Score values of 81%,82%, and 87.4% respectively.
This page summarises published work. The authoritative version sits with the publisher.
DOI: 10.1007/s42452-023-05280-4
Is something wrong with this record? Report it or request removal.
Discussion
Have you built on this work, tried to replicate it, or seen it applied in practice? Share what you know. Verified researchers and MARATTO™ domain experts can open a discussion, and any member can reply. Contributions are reviewed before they appear.
No discussion yet. Open the first thread.
New to MARATTO™? Create a free account.
