Flood change detection model based on an improved U-net network and multi-head attention mechanism
Abstract This work aims to improve the accuracy and efficiency of flood disaster monitoring, including monitoring before, during, and after the flood, to achieve accurate extraction of flood disaster change information. A modified U-Net network model, incorporating the Transformer multi-head attenti...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-01-01
|
| Series: | Scientific Reports |
| Subjects: | |
| Online Access: | https://doi.org/10.1038/s41598-025-87851-6 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832571753261432832 |
|---|---|
| author | Fajing Wang Xu Feng |
| author_facet | Fajing Wang Xu Feng |
| author_sort | Fajing Wang |
| collection | DOAJ |
| description | Abstract This work aims to improve the accuracy and efficiency of flood disaster monitoring, including monitoring before, during, and after the flood, to achieve accurate extraction of flood disaster change information. A modified U-Net network model, incorporating the Transformer multi-head attention mechanism (TM), is developed specifically for the characteristics of Synthetic Aperture Radar (SAR) images. By integrating the TM, the model effectively prioritizes image regions relevant to flood disasters. The model is trained on a substantial volume of annotated SAR image data, and its performance is assessed using metrics such as loss function, accuracy, and precision. Experimental findings demonstrate significant improvements in loss value, accuracy, and precision compared to existing models. Specifically, the accuracy of the model algorithm in this work reaches 95.52%, marking a 3.46% improvement over the baseline U-Net network. Additionally, the developed model achieves an accuracy of 90.11% while maintaining a loss value of approximately 0.59, whereas other model algorithms exceed a loss value of 0.74. Thus, this work not only introduces a novel technical approach for flood disaster monitoring but also has the potential to enhance disaster response procedures and provide scientific evidence for disaster management and risk assessment processes. |
| format | Article |
| id | doaj-art-c34871a9ecd84acc9ea02f4bbf36fce0 |
| institution | Kabale University |
| issn | 2045-2322 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj-art-c34871a9ecd84acc9ea02f4bbf36fce02025-02-02T12:21:35ZengNature PortfolioScientific Reports2045-23222025-01-0115111610.1038/s41598-025-87851-6Flood change detection model based on an improved U-net network and multi-head attention mechanismFajing Wang0Xu Feng1School of Transportation and Geometics Engineering, Yangling Vocational & Technical CollegeSchool of Transportation and Geometics Engineering, Yangling Vocational & Technical CollegeAbstract This work aims to improve the accuracy and efficiency of flood disaster monitoring, including monitoring before, during, and after the flood, to achieve accurate extraction of flood disaster change information. A modified U-Net network model, incorporating the Transformer multi-head attention mechanism (TM), is developed specifically for the characteristics of Synthetic Aperture Radar (SAR) images. By integrating the TM, the model effectively prioritizes image regions relevant to flood disasters. The model is trained on a substantial volume of annotated SAR image data, and its performance is assessed using metrics such as loss function, accuracy, and precision. Experimental findings demonstrate significant improvements in loss value, accuracy, and precision compared to existing models. Specifically, the accuracy of the model algorithm in this work reaches 95.52%, marking a 3.46% improvement over the baseline U-Net network. Additionally, the developed model achieves an accuracy of 90.11% while maintaining a loss value of approximately 0.59, whereas other model algorithms exceed a loss value of 0.74. Thus, this work not only introduces a novel technical approach for flood disaster monitoring but also has the potential to enhance disaster response procedures and provide scientific evidence for disaster management and risk assessment processes.https://doi.org/10.1038/s41598-025-87851-6SAR imageryArtificial intelligenceU-Net networkFlood disaster identificationAttention mechanism |
| spellingShingle | Fajing Wang Xu Feng Flood change detection model based on an improved U-net network and multi-head attention mechanism Scientific Reports SAR imagery Artificial intelligence U-Net network Flood disaster identification Attention mechanism |
| title | Flood change detection model based on an improved U-net network and multi-head attention mechanism |
| title_full | Flood change detection model based on an improved U-net network and multi-head attention mechanism |
| title_fullStr | Flood change detection model based on an improved U-net network and multi-head attention mechanism |
| title_full_unstemmed | Flood change detection model based on an improved U-net network and multi-head attention mechanism |
| title_short | Flood change detection model based on an improved U-net network and multi-head attention mechanism |
| title_sort | flood change detection model based on an improved u net network and multi head attention mechanism |
| topic | SAR imagery Artificial intelligence U-Net network Flood disaster identification Attention mechanism |
| url | https://doi.org/10.1038/s41598-025-87851-6 |
| work_keys_str_mv | AT fajingwang floodchangedetectionmodelbasedonanimprovedunetnetworkandmultiheadattentionmechanism AT xufeng floodchangedetectionmodelbasedonanimprovedunetnetworkandmultiheadattentionmechanism |