Study on the Uncertainty of Machine Learning Model for Earthquake-Induced Landslide Susceptibility Assessment
The landslide susceptibility assessment based on machine learning can accurately predict the probability of landslides happening in the region. However, there are uncertainties in machine learning applications. In this paper, Artificial Neural Network (ANN), Random Forest (RF), Support Vector Machin...
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2022-06-01
|
Series: | Remote Sensing |
Subjects: | |
Online Access: | https://www.mdpi.com/2072-4292/14/13/2968 |
_version_ | 1797408314870464512 |
---|---|
author | Haixia Feng Zelang Miao Qingwu Hu |
author_facet | Haixia Feng Zelang Miao Qingwu Hu |
author_sort | Haixia Feng |
collection | DOAJ |
description | The landslide susceptibility assessment based on machine learning can accurately predict the probability of landslides happening in the region. However, there are uncertainties in machine learning applications. In this paper, Artificial Neural Network (ANN), Random Forest (RF), Support Vector Machine (SVM), and Logistic Regression (LR) are used to assess the landslide susceptibility in order to discuss the model uncertainty. The model uncertainty is explained in three ways: landslide susceptibility zoning result, risk area (high and extremely high) statistics, and the area under Receiver Operating Characteristic Curve (ROC). The findings indicate that: (1) Landslides are restricted by influence factors and have the distribution law of relatively concentrated and strip-shaped distribution in space. (2) The percentage of real landslide in risk area is 86%, 87%, 82%, and 61% in SVM, RF, LR, and ANN, respectively. The area under ROC of RF, SVM, LR, and ANN, respectively, is 90.92%, 80.45%, 73.75%, and 71.95%. (3) Compared with the prediction accuracy of the training set and test set from the same earthquake, the accuracy of landslide prediction in the different earthquakes is reduced. |
first_indexed | 2024-03-09T03:56:40Z |
format | Article |
id | doaj.art-85f6bccb5dca4bb985327beceb9c022a |
institution | Directory Open Access Journal |
issn | 2072-4292 |
language | English |
last_indexed | 2024-03-09T03:56:40Z |
publishDate | 2022-06-01 |
publisher | MDPI AG |
record_format | Article |
series | Remote Sensing |
spelling | doaj.art-85f6bccb5dca4bb985327beceb9c022a2023-12-03T14:19:35ZengMDPI AGRemote Sensing2072-42922022-06-011413296810.3390/rs14132968Study on the Uncertainty of Machine Learning Model for Earthquake-Induced Landslide Susceptibility AssessmentHaixia Feng0Zelang Miao1Qingwu Hu2School of Remote Sensing and Information Engineering, Wuhan University, Wuhan 430072, ChinaSchool of Geosciences and Info-Physics, Central South University, Changsha 410017, ChinaSchool of Remote Sensing and Information Engineering, Wuhan University, Wuhan 430072, ChinaThe landslide susceptibility assessment based on machine learning can accurately predict the probability of landslides happening in the region. However, there are uncertainties in machine learning applications. In this paper, Artificial Neural Network (ANN), Random Forest (RF), Support Vector Machine (SVM), and Logistic Regression (LR) are used to assess the landslide susceptibility in order to discuss the model uncertainty. The model uncertainty is explained in three ways: landslide susceptibility zoning result, risk area (high and extremely high) statistics, and the area under Receiver Operating Characteristic Curve (ROC). The findings indicate that: (1) Landslides are restricted by influence factors and have the distribution law of relatively concentrated and strip-shaped distribution in space. (2) The percentage of real landslide in risk area is 86%, 87%, 82%, and 61% in SVM, RF, LR, and ANN, respectively. The area under ROC of RF, SVM, LR, and ANN, respectively, is 90.92%, 80.45%, 73.75%, and 71.95%. (3) Compared with the prediction accuracy of the training set and test set from the same earthquake, the accuracy of landslide prediction in the different earthquakes is reduced.https://www.mdpi.com/2072-4292/14/13/2968earthquake-induced landslidesusceptibility assessmentmachine learningmodel uncertainty |
spellingShingle | Haixia Feng Zelang Miao Qingwu Hu Study on the Uncertainty of Machine Learning Model for Earthquake-Induced Landslide Susceptibility Assessment Remote Sensing earthquake-induced landslide susceptibility assessment machine learning model uncertainty |
title | Study on the Uncertainty of Machine Learning Model for Earthquake-Induced Landslide Susceptibility Assessment |
title_full | Study on the Uncertainty of Machine Learning Model for Earthquake-Induced Landslide Susceptibility Assessment |
title_fullStr | Study on the Uncertainty of Machine Learning Model for Earthquake-Induced Landslide Susceptibility Assessment |
title_full_unstemmed | Study on the Uncertainty of Machine Learning Model for Earthquake-Induced Landslide Susceptibility Assessment |
title_short | Study on the Uncertainty of Machine Learning Model for Earthquake-Induced Landslide Susceptibility Assessment |
title_sort | study on the uncertainty of machine learning model for earthquake induced landslide susceptibility assessment |
topic | earthquake-induced landslide susceptibility assessment machine learning model uncertainty |
url | https://www.mdpi.com/2072-4292/14/13/2968 |
work_keys_str_mv | AT haixiafeng studyontheuncertaintyofmachinelearningmodelforearthquakeinducedlandslidesusceptibilityassessment AT zelangmiao studyontheuncertaintyofmachinelearningmodelforearthquakeinducedlandslidesusceptibilityassessment AT qingwuhu studyontheuncertaintyofmachinelearningmodelforearthquakeinducedlandslidesusceptibilityassessment |