Landslide Susceptibility Assessment Using Integrated Deep Learning Algorithm along the China-Nepal Highway
The China-Nepal Highway is a vital land route in the Kush-Himalayan region. The occurrence of mountain hazards in this area is a matter of serious concern. Thus, it is of great importance to perform hazard assessments in a more accurate and real-time way. Based on temporal and spatial sensor data, t...
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2018-12-01
|
Series: | Sensors |
Subjects: | |
Online Access: | https://www.mdpi.com/1424-8220/18/12/4436 |
_version_ | 1811304272359325696 |
---|---|
author | Liming Xiao Yonghong Zhang Gongzhuang Peng |
author_facet | Liming Xiao Yonghong Zhang Gongzhuang Peng |
author_sort | Liming Xiao |
collection | DOAJ |
description | The China-Nepal Highway is a vital land route in the Kush-Himalayan region. The occurrence of mountain hazards in this area is a matter of serious concern. Thus, it is of great importance to perform hazard assessments in a more accurate and real-time way. Based on temporal and spatial sensor data, this study tries to use data-driven algorithms to predict landslide susceptibility. Ten landslide instability factors were prepared, including elevation, slope angle, slope aspect, plan curvature, vegetation index, built-up index, stream power, lithology, precipitation intensity, and cumulative precipitation index. Four machine learning algorithms, namely decision tree (DT), support vector machines (SVM), Back Propagation neural network (BPNN), and Long Short Term Memory (LSTM) are implemented, and their final prediction accuracies are compared. The experimental results showed that the prediction accuracies of BPNN, SVM, DT, and LSTM in the test areas are 62.0%, 72.9%, 60.4%, and 81.2%, respectively. LSTM outperformed the other three models due to its capability to learn time series with long temporal dependencies. It indicates that the dynamic change course of geological and geographic parameters is an important indicator in reflecting landslide susceptibility. |
first_indexed | 2024-04-13T08:04:19Z |
format | Article |
id | doaj.art-0a0095606f3a4fc9b796067cd17023e3 |
institution | Directory Open Access Journal |
issn | 1424-8220 |
language | English |
last_indexed | 2024-04-13T08:04:19Z |
publishDate | 2018-12-01 |
publisher | MDPI AG |
record_format | Article |
series | Sensors |
spelling | doaj.art-0a0095606f3a4fc9b796067cd17023e32022-12-22T02:55:12ZengMDPI AGSensors1424-82202018-12-011812443610.3390/s18124436s18124436Landslide Susceptibility Assessment Using Integrated Deep Learning Algorithm along the China-Nepal HighwayLiming Xiao0Yonghong Zhang1Gongzhuang Peng2Department of Information and Communication, Nanjing University of Information Science and Technology, Nanjing 210044, ChinaDepartment of Information and Communication, Nanjing University of Information Science and Technology, Nanjing 210044, ChinaEngineering Research Institute, University of Science and Technology Beijing, Beijing 100083, ChinaThe China-Nepal Highway is a vital land route in the Kush-Himalayan region. The occurrence of mountain hazards in this area is a matter of serious concern. Thus, it is of great importance to perform hazard assessments in a more accurate and real-time way. Based on temporal and spatial sensor data, this study tries to use data-driven algorithms to predict landslide susceptibility. Ten landslide instability factors were prepared, including elevation, slope angle, slope aspect, plan curvature, vegetation index, built-up index, stream power, lithology, precipitation intensity, and cumulative precipitation index. Four machine learning algorithms, namely decision tree (DT), support vector machines (SVM), Back Propagation neural network (BPNN), and Long Short Term Memory (LSTM) are implemented, and their final prediction accuracies are compared. The experimental results showed that the prediction accuracies of BPNN, SVM, DT, and LSTM in the test areas are 62.0%, 72.9%, 60.4%, and 81.2%, respectively. LSTM outperformed the other three models due to its capability to learn time series with long temporal dependencies. It indicates that the dynamic change course of geological and geographic parameters is an important indicator in reflecting landslide susceptibility.https://www.mdpi.com/1424-8220/18/12/4436landslide susceptibilityChina-Nepal Highwaymachine learningLSTMremote sensing images |
spellingShingle | Liming Xiao Yonghong Zhang Gongzhuang Peng Landslide Susceptibility Assessment Using Integrated Deep Learning Algorithm along the China-Nepal Highway Sensors landslide susceptibility China-Nepal Highway machine learning LSTM remote sensing images |
title | Landslide Susceptibility Assessment Using Integrated Deep Learning Algorithm along the China-Nepal Highway |
title_full | Landslide Susceptibility Assessment Using Integrated Deep Learning Algorithm along the China-Nepal Highway |
title_fullStr | Landslide Susceptibility Assessment Using Integrated Deep Learning Algorithm along the China-Nepal Highway |
title_full_unstemmed | Landslide Susceptibility Assessment Using Integrated Deep Learning Algorithm along the China-Nepal Highway |
title_short | Landslide Susceptibility Assessment Using Integrated Deep Learning Algorithm along the China-Nepal Highway |
title_sort | landslide susceptibility assessment using integrated deep learning algorithm along the china nepal highway |
topic | landslide susceptibility China-Nepal Highway machine learning LSTM remote sensing images |
url | https://www.mdpi.com/1424-8220/18/12/4436 |
work_keys_str_mv | AT limingxiao landslidesusceptibilityassessmentusingintegrateddeeplearningalgorithmalongthechinanepalhighway AT yonghongzhang landslidesusceptibilityassessmentusingintegrateddeeplearningalgorithmalongthechinanepalhighway AT gongzhuangpeng landslidesusceptibilityassessmentusingintegrateddeeplearningalgorithmalongthechinanepalhighway |