Journal
WATER
Volume 14, Issue 20, Pages -Publisher
MDPI
DOI: 10.3390/w14203320
Keywords
deep learning; rainfall-induced landslide; sediment disaster; Keras; multilayer perceptron; hyperparameter tuning; mountain disaster risk reduction
Categories
Funding
- National Science and Technology Council of Taiwan, ROC [MOST 110-2625-M-020-001, MOST 111-2221-E-002-164]
Ask authors/readers for more resources
The complex mechanism of landslides and their connection to climate change have made them critical events globally, affecting the long-term sustainable development of nations. Taiwan experiences numerous landslides every year and requires an effective warning system. This study uses a deep learning algorithm to predict landslide rainfall thresholds and assist decision makers in responding to landslides early and reducing the risk.
The complex and extensive mechanism of landslides and their direct connection to climate change have turned these hazards into critical events on a global scale, which can have significant negative influences on the long-term sustainable development of nations. Taiwan experiences numerous landslides on different scales almost every year. However, Typhoon Morakot (2009), with large-scale landslides that trapped people, demonstrated the importance of an early warning system. The absence of an effective warning system for landslides along with the impossibility of its accurate monitoring highlighted the necessity of landslide rainfall threshold prediction. Accordingly, the prediction of the landslide rainfall threshold as an early warning system could be an effective tool with which to develop an emergency evacuation protocol. The purpose of this study is to present the capability of the deep learning algorithm to determine the distribution of landslide rainfall thresholds in a potential large-scale landslide area and to assess the distribution of recurrence intervals using probability density functions, as well as to assist decision makers in early responses to landslides and reduce the risk of large-scale landslides. Therefore, the algorithm was developed for one of the potential large-scale landslide areas (the Alishan D098 sub-basin), Taiwan, which is classified as a Type II Landslide Priority Area. The historical landslide data, maximum daily rainfall, 11 topographic factors from 2004 to 2017, and the Keras application programming interface (API) python library were used to develop two deep learning models for landslide susceptibility classification and landslide rainfall threshold regression. The predicted result shows the lowest landslide rainfall threshold is located primarily in the northeastern downstream of the Alishan catchment, which poses an extreme risk to the residential area located upstream of the landslide area, particularly if large-scale landslides were to be triggered upstream of Alishan. The landslide rainfall threshold under controlled conditions was estimated at 780 mm/day (20-year recurrence interval), or 820 mm/day (25-year recurrence interval). Since the frequency of extreme rainfall events caused by climate change is expected to rise in the future, the overall landslide rainfall threshold was considered 980 mm/day for the entire area.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available