Details
| Original language | English |
|---|---|
| Article number | 112589 |
| Journal | Ecological indicators |
| Volume | 167 |
| Early online date | 13 Sept 2024 |
| Publication status | Published - Oct 2024 |
Abstract
Forest burned area (FBA) detection using remote sensing (RS) data is critical for timely forest management and recovery attempts after wildfires. This study introduces a dual-path attention residual-based U-Net (DPAttResU-Net), a novel end-to-end deep learning (DL) model tailored for FBA detection using dual-source post-fire Sentinel-1 (S1) and Sentinel-2 (S2) satellite RS imagery. To better distinguish FBAs from other land cover types, DPAttResU-Net incorporates a dual-pathway structure to exploit complementary geometrical/physical and spectral features from S1 and S2, respectively. An integral component in the proposed architecture is the channel-spatial attention residual (CSAttRes) block, which emphasizes salient features through the channel and spatial attention modules, thus improving the burned area feature representation. To compare DPAttResU-Net to state-of-the-art DL models, experiments were conducted on benchmark FBA datasets collected over 12 areas, where ten datasets were used as training data and two datasets were used to test the trained DL models. The experimental results demonstrate the high proficiency of the proposed deep model in meticulously delineating FBAs. In further detail, DPAttResU-Net, with a PFN of 17.96 (%) in the first case and an IoU of 89.31 (%) in the second case, outperformed the existing U-Net-based models. Accordingly, through dual-path integration and attention mechanisms, DPAttResU-Net contributes to accurately identifying FBAs by preserving their geometrical details, making it a promising tool for post-wildfire forest management.
Keywords
- Channel-spatial attention mechanism, Deep learning, Dual-path U-Net architecture, Forest burned area detection, Sentinel-1, Sentinel-2
ASJC Scopus subject areas
- Decision Sciences(all)
- General Decision Sciences
- Agricultural and Biological Sciences(all)
- Ecology, Evolution, Behavior and Systematics
- Environmental Science(all)
- Ecology
Sustainable Development Goals
Cite this
- Standard
- Harvard
- Apa
- Vancouver
- BibTeX
- RIS
In: Ecological indicators, Vol. 167, 112589, 10.2024.
Research output: Contribution to journal › Article › Research › peer review
}
TY - JOUR
T1 - FBA-DPAttResU-Net
T2 - Forest burned area detection using a novel end-to-end dual-path attention residual-based U-Net from post-fire Sentinel-1 and Sentinel-2 images
AU - Khankeshizadeh, Ehsan
AU - Tahermanesh, Sahand
AU - Mohsenifar, Amin
AU - Moghimi, Armin
AU - Mohammadzadeh, Ali
N1 - Publisher Copyright: © 2024 The Author(s)
PY - 2024/10
Y1 - 2024/10
N2 - Forest burned area (FBA) detection using remote sensing (RS) data is critical for timely forest management and recovery attempts after wildfires. This study introduces a dual-path attention residual-based U-Net (DPAttResU-Net), a novel end-to-end deep learning (DL) model tailored for FBA detection using dual-source post-fire Sentinel-1 (S1) and Sentinel-2 (S2) satellite RS imagery. To better distinguish FBAs from other land cover types, DPAttResU-Net incorporates a dual-pathway structure to exploit complementary geometrical/physical and spectral features from S1 and S2, respectively. An integral component in the proposed architecture is the channel-spatial attention residual (CSAttRes) block, which emphasizes salient features through the channel and spatial attention modules, thus improving the burned area feature representation. To compare DPAttResU-Net to state-of-the-art DL models, experiments were conducted on benchmark FBA datasets collected over 12 areas, where ten datasets were used as training data and two datasets were used to test the trained DL models. The experimental results demonstrate the high proficiency of the proposed deep model in meticulously delineating FBAs. In further detail, DPAttResU-Net, with a PFN of 17.96 (%) in the first case and an IoU of 89.31 (%) in the second case, outperformed the existing U-Net-based models. Accordingly, through dual-path integration and attention mechanisms, DPAttResU-Net contributes to accurately identifying FBAs by preserving their geometrical details, making it a promising tool for post-wildfire forest management.
AB - Forest burned area (FBA) detection using remote sensing (RS) data is critical for timely forest management and recovery attempts after wildfires. This study introduces a dual-path attention residual-based U-Net (DPAttResU-Net), a novel end-to-end deep learning (DL) model tailored for FBA detection using dual-source post-fire Sentinel-1 (S1) and Sentinel-2 (S2) satellite RS imagery. To better distinguish FBAs from other land cover types, DPAttResU-Net incorporates a dual-pathway structure to exploit complementary geometrical/physical and spectral features from S1 and S2, respectively. An integral component in the proposed architecture is the channel-spatial attention residual (CSAttRes) block, which emphasizes salient features through the channel and spatial attention modules, thus improving the burned area feature representation. To compare DPAttResU-Net to state-of-the-art DL models, experiments were conducted on benchmark FBA datasets collected over 12 areas, where ten datasets were used as training data and two datasets were used to test the trained DL models. The experimental results demonstrate the high proficiency of the proposed deep model in meticulously delineating FBAs. In further detail, DPAttResU-Net, with a PFN of 17.96 (%) in the first case and an IoU of 89.31 (%) in the second case, outperformed the existing U-Net-based models. Accordingly, through dual-path integration and attention mechanisms, DPAttResU-Net contributes to accurately identifying FBAs by preserving their geometrical details, making it a promising tool for post-wildfire forest management.
KW - Channel-spatial attention mechanism
KW - Deep learning
KW - Dual-path U-Net architecture
KW - Forest burned area detection
KW - Sentinel-1
KW - Sentinel-2
UR - http://www.scopus.com/inward/record.url?scp=85203636591&partnerID=8YFLogxK
U2 - 10.1016/j.ecolind.2024.112589
DO - 10.1016/j.ecolind.2024.112589
M3 - Article
AN - SCOPUS:85203636591
VL - 167
JO - Ecological indicators
JF - Ecological indicators
SN - 1470-160X
M1 - 112589
ER -