Abstract
Landslide susceptibility mapping (LSM) is an effective way to predict spatial probability of landslide occurrence. Existing convolutional neural network (CNN)-based methods apply self-built CNN with simple structure, which failed to reach CNN's full potential on high-level feature extraction, meanwhile ignored the use of numerical predisposing factors. For the purpose of exploring feature fusion based CNN models with greater reliability in LSM, this study proposes an ensemble model based on channel-expanded pre-trained CNN and traditional machine learning model (CPCNN-ML). In CPCNN-ML, pre-trained CNN with mature structure is modified to excavate high-level features of multichannel predisposing factor layers. LSM result is generated by traditional machine learning (ML) model based on hybrid feature of high-level features and numerical predisposing factors. Lantau Island, Hong Kong is selected as study area; temporal landslide inventory is used for model training and evaluation. Experimental results show that CPCNN-ML has ability to predict landslide occurrence with high reliability, especially the CPCNN-ML based on random forest. Contrast experiments with self-built CNN and traditional ML models further embody the superiority of CPCNN-ML. It is worth noting that coastal regions are newly identified landslide-prone regions compared with previous research. This finding is of great reference value for Hong Kong authorities to formulate appropriate disaster prevention and mitigation policies.
Highlights
A S ONE of the most destructive and frequently appeared geohazard, landslides have brought a tremendous threatManuscript received August 10, 2020; revised January 27, 2021; accepted March 10, 2021
Effectiveness of channel-expanded PCNN model (CPCNN)-Extracted High-Level features With the aim of boosting performance and efficiency of self-built convolutional neural network (CNN), pre-trained CNN model (PCNN) and corresponding fine-tune strategy were modified and applied in CPCNN-machine learning (ML) to extract high-level features of landslide predisposing factor layers
Frequently occurred landslides in Lantau Island pose a great threat to the property and lives of Hong Kong (HK) citizens
Summary
A S ONE of the most destructive and frequently appeared geohazard, landslides have brought a tremendous threatManuscript received August 10, 2020; revised January 27, 2021; accepted March 10, 2021. From January 2004 to December 2016, more than 55 997 people were killed by landslides and landslide-induced geohazard [1]. The negative impact caused by landslides on the sustainable development of social and environment is cause for great concern. In order to mitigate landslide hazards, it is urgent to establish a system to predict where landslides would occur in the future [2]. LSM provides an effective way to achieve “Reduce the Adverse Effects of Natural Disasters” target of sustainable development goal (SDG) 11. Based on LSM, landslide-prone areas could be identified, which helps the government to devise an effective disaster mitigation strategy [5] and accelerate the implementation of SDGs 2030
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
More From: IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.