{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,3]],"date-time":"2026-03-03T16:56:12Z","timestamp":1772556972112,"version":"3.50.1"},"reference-count":34,"publisher":"MDPI AG","issue":"13","license":[{"start":{"date-parts":[[2022,6,21]],"date-time":"2022-06-21T00:00:00Z","timestamp":1655769600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"National Key Research and Development Program of China","award":["2020YFC1521900"],"award-info":[{"award-number":["2020YFC1521900"]}]},{"name":"National Key Research and Development Program of China","award":["2017B020218001"],"award-info":[{"award-number":["2017B020218001"]}]},{"name":"Science and Technology Planning Project of Guangdong Province, China","award":["2020YFC1521900"],"award-info":[{"award-number":["2020YFC1521900"]}]},{"name":"Science and Technology Planning Project of Guangdong Province, China","award":["2017B020218001"],"award-info":[{"award-number":["2017B020218001"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Remote Sensing"],"abstract":"<jats:p>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.<\/jats:p>","DOI":"10.3390\/rs14132968","type":"journal-article","created":{"date-parts":[[2022,6,22]],"date-time":"2022-06-22T04:12:01Z","timestamp":1655871121000},"page":"2968","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":27,"title":["Study on the Uncertainty of Machine Learning Model for Earthquake-Induced Landslide Susceptibility Assessment"],"prefix":"10.3390","volume":"14","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3815-717X","authenticated-orcid":false,"given":"Haixia","family":"Feng","sequence":"first","affiliation":[{"name":"School of Remote Sensing and Information Engineering, Wuhan University, Wuhan 430072, China"}]},{"given":"Zelang","family":"Miao","sequence":"additional","affiliation":[{"name":"School of Geosciences and Info-Physics, Central South University, Changsha 410017, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0866-6678","authenticated-orcid":false,"given":"Qingwu","family":"Hu","sequence":"additional","affiliation":[{"name":"School of Remote Sensing and Information Engineering, Wuhan University, Wuhan 430072, China"}]}],"member":"1968","published-online":{"date-parts":[[2022,6,21]]},"reference":[{"key":"ref_1","unstructured":"Ma, S.Y. (2018). Study on Seismic Landslide Risk Assessment Based on Newmark Model: A Case Study of Lushan Earthquake and Wenchuan Earthquake. [Master\u2019s Thesis, Institute of Geology, China Earthquake Administration]."},{"key":"ref_2","first-page":"1151","article-title":"A preliminary study on spatial distribution and susceptibility assessment of geological hazards induced by the August 8, 2017 Jiuzhaigou earthquake","volume":"4","author":"Lanxin","year":"2017","journal-title":"J. Eng. Geol."},{"key":"ref_3","first-page":"306","article-title":"Study on landslide risk assessment method based on artificial neural network","volume":"20","author":"Zhao","year":"2013","journal-title":"Urban Constr."},{"key":"ref_4","first-page":"153","article-title":"Support vector machine model for Spatial Prediction of landslide Disaster and its Application","volume":"6","author":"Dai","year":"2007","journal-title":"Earth Sci. Front."},{"key":"ref_5","first-page":"1085","article-title":"Assessment of landslide susceptibility based on optimization random forest model","volume":"43","author":"Liu","year":"2018","journal-title":"Inf. Sci. Technol. Wuhan Univ."},{"key":"ref_6","unstructured":"Hammer, B., and Villmann, T. (2007, January 25\u201327). How to process uncertainty in machine learning. Proceedings of the ESANN 2007, 15th European Symposium on Artificial Neural Networks, Bruges, Belgium."},{"key":"ref_7","first-page":"1176","article-title":"Sensitivity analysis of 2013 Lushan earthquake landslide factors based on CF method supported by GIS","volume":"22","author":"Liu","year":"2014","journal-title":"J. Eng. Geol."},{"key":"ref_8","first-page":"3","article-title":"The application of stepwise regression analysis in the sensitivity analysis of landslide factors","volume":"6","author":"Zhang","year":"2008","journal-title":"Sci. Technol. Econ. Mark."},{"key":"ref_9","first-page":"1393","article-title":"Application of Bayesian information standard in sensitivity Analysis of landslide factors","volume":"8","author":"Li","year":"2006","journal-title":"Rock Soil Mech."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"4787","DOI":"10.1007\/s10668-019-00406-4","article-title":"A GIS-based factor clustering and landslide susceptibility analysis using AHP for Gish River Basin, India","volume":"22","author":"Basu","year":"2020","journal-title":"Environ. Dev. Sustain."},{"key":"ref_11","unstructured":"(2022, May 05). Uncertainty in Position Estimation Using Machine Learning. Available online: http:\/\/arxiv.org\/abs\/2106.02370."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"857","DOI":"10.1016\/j.gsf.2020.09.004","article-title":"GIS-Based Landslide Susceptibility Modeling: A Comparison between Fuzzy Multi-Criteria and Machine Learning Algorithms","volume":"12","author":"Ali","year":"2021","journal-title":"Geosci. Front."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"355","DOI":"10.1007\/s12594-018-0862-5","article-title":"A Novel Classifier Based on Composite Hyper-cubes on Iterated Random Projections for Assessment of Landslide Susceptibility","volume":"91","author":"Binh","year":"2018","journal-title":"J. Geol. Soc. India"},{"key":"ref_14","unstructured":"Liu, X.L. (2021). Landslide susceptibility assessment based on Sampling technique and Bayesian spatial statistical model. [Master\u2019s Thesis, Southwest University of Science and Technology]."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"77","DOI":"10.1016\/j.geomorph.2015.07.002","article-title":"Database and spatial distribution of landslides triggered by the Lushan, China Mw 6.6 earthquake of 20 April 2013","volume":"248","author":"Xu","year":"2015","journal-title":"Geomorphology"},{"key":"ref_16","unstructured":"Shi, L.L. (2014). Temporal and Spatial Variation of Vegetation Coverage in Lushan County of Earthquake Region. [Master\u2019s Thesis, Sichuan Normal University]."},{"key":"ref_17","unstructured":"Liu, L.N. (2015). Assessment of Debris Flow Susceptibility in Lushan Earthquake Area. [Master\u2019s Thesis, China University of Geosciences]."},{"key":"ref_18","first-page":"787","article-title":"Geological hazard assessment based on information model supported by slope unit","volume":"35","author":"Jia","year":"2017","journal-title":"Henan Sci."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"81","DOI":"10.1016\/j.cageo.2013.04.006","article-title":"Landslide susceptibility analysis with logistic regression model based on FCM sampling strategy","volume":"57","author":"Wang","year":"2013","journal-title":"Comput. Geosci."},{"key":"ref_20","first-page":"53","article-title":"Research on welding tube factory inventory prediction based on BP neural network","volume":"25","author":"Liu","year":"2017","journal-title":"J. Beijing Inst. Petrochem. Technol."},{"key":"ref_21","first-page":"55","article-title":"Landslide geological disaster prediction method based on BP neural network","volume":"8","author":"Ke","year":"2014","journal-title":"Eng. Investig."},{"key":"ref_22","unstructured":"Li, L. (2015). Study on Landslide Disaster in Chongqing Based on Random Forest Model. [Master\u2019s Thesis, Chongqing Normal University]."},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Gupta, S.K., and Dericks, P.S. (2020, January 26). Data Imbalance in Landslide Susceptibility Zonation: A Case Study of Mandakini River Basin, Uttarakhand, India. Proceedings of the IGARSS 2020-2020 IEEE International Geoscience and Remote Sensing Symposium, Geoscience and Remote Sensing Symposium, IGARSS 2020-2020 IEEE International, Waikoloa, HI, USA.","DOI":"10.1109\/IGARSS39084.2020.9323230"},{"key":"ref_24","first-page":"592","article-title":"Landslide disaster prediction based on support vector machine theory\u2014A case study of Qingyuan district, Zhejiang province","volume":"5","author":"Ma","year":"2003","journal-title":"J. Zhejiang Univ. Sci."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"7385","DOI":"10.1007\/s10064-021-02415-y","article-title":"Hybrid-optimized logistic regression model of landslide susceptibility along mountain highway","volume":"80","author":"Zhang","year":"2021","journal-title":"Bull. Eng. Geol. Environ. Off. J. IAEG"},{"key":"ref_26","first-page":"98","article-title":"Risk assessment and test of landslide in Wenchuan earthquake based on logistic regression model","volume":"3","author":"Xu","year":"2013","journal-title":"Hydrogeol. Eng. Geol."},{"key":"ref_27","unstructured":"Xu, C., Dai, F.C., Yao, X., Zhao, Z., and Xiao, J.A. (2011, January 13). Assessment of Landslide Susceptibility in Wenchuan Earthquake Based on GIS and Deterministic Coefficient Analysis Method. Proceedings of the Chinese Academy of Sciences (2010) Academic Annual Conference Proceedings (MIDDLE), Beijing, China."},{"key":"ref_28","first-page":"83","article-title":"Evaluation of geological hazard susceptibility in Hehuang valley of Qinghai Province","volume":"27","author":"Zhao","year":"2021","journal-title":"J. Geomech."},{"key":"ref_29","unstructured":"Wu, W.Y. (2018). Landslide Susceptibility Analysis of Ludian Earthquake in Yunnan Province. [Master\u2019s Thesis, Institute of Earthquake Prediction, China Earthquake Administration]."},{"key":"ref_30","first-page":"222","article-title":"Application of several clustering optimization machine learning methods in landslide susceptibility evaluation in Lingtai County","volume":"53","author":"Qiu","year":"2020","journal-title":"Northwest Geol."},{"key":"ref_31","first-page":"61","article-title":"Assessment of landslide susceptibility in Fengjie County of the Three Gorges Reservoir Area based on ROC curve and deterministic coefficient method integrated model","volume":"27","author":"Liu","year":"2020","journal-title":"Saf. Environ. Eng."},{"key":"ref_32","first-page":"81","article-title":"Big data under the background of ROC curve is introduced and application","volume":"14","author":"Li","year":"2021","journal-title":"Sci. Trib."},{"key":"ref_33","unstructured":"Alu, S., Zhang, J.Q., and Tong, Z.J. (2018, January 20\u201321). Study on the Influence of Natural and Human Factors on the Evaluation Results in Landslide Hazard Susceptibility Evaluation. Proceedings of the 8th Annual Meeting of Risk Analysis Professional Committee of China Disaster Prevention Association, Xi\u2019an, China."},{"key":"ref_34","first-page":"806","article-title":"Comparative study on the distribution law of landslides in Wenchuan, Lushan and Ludian earthquakes","volume":"25","author":"Chen","year":"2017","journal-title":"J. Eng. Geol."}],"container-title":["Remote Sensing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2072-4292\/14\/13\/2968\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T23:36:56Z","timestamp":1760139416000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2072-4292\/14\/13\/2968"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,6,21]]},"references-count":34,"journal-issue":{"issue":"13","published-online":{"date-parts":[[2022,7]]}},"alternative-id":["rs14132968"],"URL":"https:\/\/doi.org\/10.3390\/rs14132968","relation":{},"ISSN":["2072-4292"],"issn-type":[{"value":"2072-4292","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,6,21]]}}}