Landslide Susceptibility Mapping Using Machine Learning: A Danish Case Study
Mapping of landslides, conducted in 2021 by the Geological Survey of Denmark and Greenland (GEUS), revealed 3202 landslides in Denmark, indicating that they might pose a bigger problem than previously acknowledged. Moreover, the changing climate is assumed to have an impact on landslide occurrences...
Published in: | ISPRS International Journal of Geo-Information |
---|---|
Main Authors: | , , , , |
Format: | Text |
Language: | English |
Published: |
Multidisciplinary Digital Publishing Institute
2022
|
Subjects: | |
Online Access: | https://doi.org/10.3390/ijgi11060324 |
id |
ftmdpi:oai:mdpi.com:/2220-9964/11/6/324/ |
---|---|
record_format |
openpolar |
spelling |
ftmdpi:oai:mdpi.com:/2220-9964/11/6/324/ 2023-08-20T04:06:58+02:00 Landslide Susceptibility Mapping Using Machine Learning: A Danish Case Study Angelina Ageenko Lærke Christina Hansen Kevin Lundholm Lyng Lars Bodum Jamal Jokar Arsanjani agris 2022-05-27 application/pdf https://doi.org/10.3390/ijgi11060324 EN eng Multidisciplinary Digital Publishing Institute https://dx.doi.org/10.3390/ijgi11060324 https://creativecommons.org/licenses/by/4.0/ ISPRS International Journal of Geo-Information; Volume 11; Issue 6; Pages: 324 predictive modelling spatial prediction Denmark landslides logistic regression support vector machine random forest climate change RCP8.5 Text 2022 ftmdpi https://doi.org/10.3390/ijgi11060324 2023-08-01T05:11:34Z Mapping of landslides, conducted in 2021 by the Geological Survey of Denmark and Greenland (GEUS), revealed 3202 landslides in Denmark, indicating that they might pose a bigger problem than previously acknowledged. Moreover, the changing climate is assumed to have an impact on landslide occurrences in the future. The aim of this study is to conduct the first landslide susceptibility mapping (LSM) in Denmark, reducing the geographical bias existing in LSM studies, and to identify areas prone to landslides in the future following representative concentration pathway RCP8.5, based on a set of explanatory variables in an area of interest located around Vejle Fjord, Jutland, Denmark. A subset from the landslide inventory provided by GEUS is used as ground truth data. Three well-established machine learning (ML) algorithms—Random Forest, Support Vector Machine, and Logistic Regression—were trained to classify the data samples as landslide or non-landslide, treating the ML task as a binary classification and expressing the results in the form of a probability in order to produce susceptibility maps. The classification results were validated through the test data and through an external data set for an area located outside of the region of interest. While the high predictive performance varied slightly among the three models on the test data, the LR and SVM demonstrated inferior accuracy outside of the study area. The results show that the RF model has robustness and potential for applicability in landslide susceptibility mapping in low-lying landscapes of Denmark in the present. The conducted mapping can become a step forward towards planning for mitigative and protective measures in landslide-prone areas in Denmark, providing policy-makers with necessary decision support. However, the map of the future climate change scenario shows the reduction of the susceptible areas, raising the question of the choice of the climate models and variables in the analysis. Text Greenland MDPI Open Access Publishing Greenland Vejle Fjord ENVELOPE(-21.700,-21.700,70.750,70.750) ISPRS International Journal of Geo-Information 11 6 324 |
institution |
Open Polar |
collection |
MDPI Open Access Publishing |
op_collection_id |
ftmdpi |
language |
English |
topic |
predictive modelling spatial prediction Denmark landslides logistic regression support vector machine random forest climate change RCP8.5 |
spellingShingle |
predictive modelling spatial prediction Denmark landslides logistic regression support vector machine random forest climate change RCP8.5 Angelina Ageenko Lærke Christina Hansen Kevin Lundholm Lyng Lars Bodum Jamal Jokar Arsanjani Landslide Susceptibility Mapping Using Machine Learning: A Danish Case Study |
topic_facet |
predictive modelling spatial prediction Denmark landslides logistic regression support vector machine random forest climate change RCP8.5 |
description |
Mapping of landslides, conducted in 2021 by the Geological Survey of Denmark and Greenland (GEUS), revealed 3202 landslides in Denmark, indicating that they might pose a bigger problem than previously acknowledged. Moreover, the changing climate is assumed to have an impact on landslide occurrences in the future. The aim of this study is to conduct the first landslide susceptibility mapping (LSM) in Denmark, reducing the geographical bias existing in LSM studies, and to identify areas prone to landslides in the future following representative concentration pathway RCP8.5, based on a set of explanatory variables in an area of interest located around Vejle Fjord, Jutland, Denmark. A subset from the landslide inventory provided by GEUS is used as ground truth data. Three well-established machine learning (ML) algorithms—Random Forest, Support Vector Machine, and Logistic Regression—were trained to classify the data samples as landslide or non-landslide, treating the ML task as a binary classification and expressing the results in the form of a probability in order to produce susceptibility maps. The classification results were validated through the test data and through an external data set for an area located outside of the region of interest. While the high predictive performance varied slightly among the three models on the test data, the LR and SVM demonstrated inferior accuracy outside of the study area. The results show that the RF model has robustness and potential for applicability in landslide susceptibility mapping in low-lying landscapes of Denmark in the present. The conducted mapping can become a step forward towards planning for mitigative and protective measures in landslide-prone areas in Denmark, providing policy-makers with necessary decision support. However, the map of the future climate change scenario shows the reduction of the susceptible areas, raising the question of the choice of the climate models and variables in the analysis. |
format |
Text |
author |
Angelina Ageenko Lærke Christina Hansen Kevin Lundholm Lyng Lars Bodum Jamal Jokar Arsanjani |
author_facet |
Angelina Ageenko Lærke Christina Hansen Kevin Lundholm Lyng Lars Bodum Jamal Jokar Arsanjani |
author_sort |
Angelina Ageenko |
title |
Landslide Susceptibility Mapping Using Machine Learning: A Danish Case Study |
title_short |
Landslide Susceptibility Mapping Using Machine Learning: A Danish Case Study |
title_full |
Landslide Susceptibility Mapping Using Machine Learning: A Danish Case Study |
title_fullStr |
Landslide Susceptibility Mapping Using Machine Learning: A Danish Case Study |
title_full_unstemmed |
Landslide Susceptibility Mapping Using Machine Learning: A Danish Case Study |
title_sort |
landslide susceptibility mapping using machine learning: a danish case study |
publisher |
Multidisciplinary Digital Publishing Institute |
publishDate |
2022 |
url |
https://doi.org/10.3390/ijgi11060324 |
op_coverage |
agris |
long_lat |
ENVELOPE(-21.700,-21.700,70.750,70.750) |
geographic |
Greenland Vejle Fjord |
geographic_facet |
Greenland Vejle Fjord |
genre |
Greenland |
genre_facet |
Greenland |
op_source |
ISPRS International Journal of Geo-Information; Volume 11; Issue 6; Pages: 324 |
op_relation |
https://dx.doi.org/10.3390/ijgi11060324 |
op_rights |
https://creativecommons.org/licenses/by/4.0/ |
op_doi |
https://doi.org/10.3390/ijgi11060324 |
container_title |
ISPRS International Journal of Geo-Information |
container_volume |
11 |
container_issue |
6 |
container_start_page |
324 |
_version_ |
1774718351979839488 |