Automatic Remote Sensing Identification of Co-Seismic Landslides Using Deep Learning Methods
Open Access
Abstract
Rapid and accurate extraction of landslide areas triggered by earthquakes has far-reaching significance for geological disaster risk assessment and emergency rescue. At present, visual interpretation and field survey are still the most-commonly used methods for landslide identification, but these methods are often time-consuming and costly. For this reason, this paper tackles the problem of co-seismic landslide identification and the fact that there is little sample information in existing studies on landslide. A landslide sample dataset with 4000 tags was produced. With the YOLOv3 algorithm as the core, a convolutional neural network model with landslide characteristics was established to automatically recognize co-seismic landslides in satellite remote sensing images. By comparing it with the graphical interpretation results of remote sensing images, we found that the remote sensing for landslide recognition model constructed in this paper demonstrated high recognition accuracy and fast speed. The F1 value was 0.93, indicating that the constructed model was stable. The research results can provide reference for emergency rescue and disaster investigation of the same co-seismic landslide disaster.Keywords
Funding Information
- National Key National Key Research and Development Program of China (2021YFC3000401, SKLGP2018Z010, 41871303, 2021YFG0365, kj-2021-3, 2022-YF05-01090-SN)
- State Key Laboratory of Geohazard Prevention and Geoenvironment Protection Independent Research Project (2021YFC3000401, SKLGP2018Z010, 41871303, 2021YFG0365, kj-2021-3, 2022-YF05-01090-SN)
- the National Natural Science Foundation of China (NSFC) (2021YFC3000401, SKLGP2018Z010, 41871303, 2021YFG0365, kj-2021-3, 2022-YF05-01090-SN)
- Sichuan Provincial Science and Technology Support Project5 (2021YFC3000401, SKLGP2018Z010, 41871303, 2021YFG0365, kj-2021-3, 2022-YF05-01090-SN)
- Department of Natural Resources of Sichuan Province (2021YFC3000401, SKLGP2018Z010, 41871303, 2021YFG0365, kj-2021-3, 2022-YF05-01090-SN)
- Chengdu Technology Innovation R&D Project (2021YFC3000401, SKLGP2018Z010, 41871303, 2021YFG0365, kj-2021-3, 2022-YF05-01090-SN)
This publication has 17 references indexed in Scilit:
- Landslide susceptibility assessment using different slope units based on the evidential belief function modelGeocarto International, 2019
- Landslides by the 2018 Hokkaido Iburi-Tobu Earthquake on September 6Landslides, 2018
- Glacier surface characteristics derivation and monitoring using Hyperspectral datasets: a case study of Gepang Gath glacier, Western HimalayaGeocarto International, 2017
- Landslide mapping and monitoring by using radar and optical remote sensing: Examples from the EC-FP7 project SAFERRemote Sensing Applications: Society and Environment, 2016
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal NetworksIEEE Transactions on Pattern Analysis and Machine Intelligence, 2016
- Fatal landslides in EuropeLandslides, 2016
- Rapid susceptibility mapping of co-seismic landslides triggered by the 2013 Lushan Earthquake using the regression model developed for the 2008 Wenchuan EarthquakeJournal of Mountain Science, 2013
- A Fast Learning Algorithm for Deep Belief NetsNeural Computation, 2006
- Special issue from the symposium on Remote Sensing and Monitoring of LandslidesEngineering Geology, 2002
- Sar integrated techniques for geohazard assessmentAdvances In Space Research, 1995