Landslide susceptibility prediction based on image semantic segmentation
| Autor: | Liangzhe Han, Qiang Gao, Zirong Zhao, Leilei Sun, Xiao Hu, Bowen Du, Guanghui Wu |
|---|---|
| Rok vydání: | 2021 |
| Předmět: |
Network architecture
Parsing Pixel business.industry Computer science Deep learning 0208 environmental biotechnology Landslide Pattern recognition 02 engineering and technology 010502 geochemistry & geophysics computer.software_genre 01 natural sciences 020801 environmental engineering Remote sensing (archaeology) Segmentation Artificial intelligence Pyramid (image processing) Computers in Earth Sciences business computer 0105 earth and related environmental sciences Information Systems |
| Zdroj: | Computers & Geosciences. 155:104860 |
| ISSN: | 0098-3004 |
| DOI: | 10.1016/j.cageo.2021.104860 |
| Popis: | The visual characteristics of landslide susceptibility have not yet been fully explored. Professional or trained technicians have to take much time and effort to interpret remote sensing images and locate landslides accordingly. Although conventional machine learning methods based on hand-crafted features for landslide susceptibility prediction (LSP) have acquired remarkable performance, they have certain requirements for prior knowledge. Aiming to learn complex and inherent visual patterns of landslides through minimal manual intervention and achieve fine-grained prediction, in this paper, we define LSP as a semantic segmentation problem on optical remote sensing images. Six widely used semantic segmentation models including Fully Convolutional Network, U-Net, Pyramid Scene Parsing Network, Global Convolutional Network (GCN), DeepLab v3 and DeepLab v3+ are introduced and evaluated for LSP. As the lack of landslide datasets, an open labeled landslide dataset of remote sensing imagery is created for research. The results show that GCN and DeepLab v3 are more applicable for this problem scenario, and the best Mean Intersection-over-Union and Pixel Accuracy of models are 54.2% and 74.0% respectively, which could be further improved by more targeted network architectures. In conclusion, semantic segmentation methods are demonstrated to be effctive for predicting new potential landslides based on remote sensing images. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Full Text from ScienceDirect