{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,26]],"date-time":"2026-03-26T00:31:36Z","timestamp":1774485096102,"version":"3.50.1"},"reference-count":45,"publisher":"MDPI AG","issue":"12","license":[{"start":{"date-parts":[[2023,6,20]],"date-time":"2023-06-20T00:00:00Z","timestamp":1687219200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100005806","name":"Temple University","doi-asserted-by":"publisher","award":["143487-23030-02"],"award-info":[{"award-number":["143487-23030-02"]}],"id":[{"id":"10.13039\/100005806","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Remote Sensing"],"abstract":"<jats:p>Landslide susceptibility mapping (LSM) characterizes landslide potential, which is essential for assessing landslide risk and developing mitigation strategies. Despite the significant progress in LSM research over the past two decades, several long-standing issues, such as uncertainties related to training samples and model selection, remain inadequately addressed in the literature. In this study, we employed a physically based susceptibility model, PISA-m, to generate four different non-landslide data scenarios and combine them with mapped landslides from Magoffin County, Kentucky, for model training. We utilized two Bayesian network model structures, Na\u00efve Bayes (NB) and Tree-Augmented Na\u00efve Bayes (TAN), to produce LSMs based on regional geomorphic conditions. After internal validation, we evaluated the robustness and reliability of the models using an independent landslide inventory from Owsley County, Kentucky. The results revealed considerable differences between the most effective model in internal validation (AUC = 0.969), which used non-landslide samples extracted exclusively from low susceptibility areas predicted by PISA-m, and the models\u2019 unsatisfactory performance in external validation, as manifested by the identification of only 79.1% of landslide initiation points as high susceptibility areas. The obtained results from both internal and external validation highlighted the potential overfitting problem, which has largely been overlooked by previous studies. Additionally, our findings also indicate that TAN models consistently outperformed NB models when training datasets were the same due to the ability to account for variables\u2019 dependencies by the former.<\/jats:p>","DOI":"10.3390\/rs15123200","type":"journal-article","created":{"date-parts":[[2023,6,21]],"date-time":"2023-06-21T02:01:33Z","timestamp":1687312893000},"page":"3200","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":32,"title":["An Assessment of Negative Samples and Model Structures in Landslide Susceptibility Characterization Based on Bayesian Network Models"],"prefix":"10.3390","volume":"15","author":[{"given":"Sahand","family":"Khabiri","sequence":"first","affiliation":[{"name":"Department of Civil & Environmental Engineering, Temple University, Philadelphia, PA 19122, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8674-8532","authenticated-orcid":false,"given":"Matthew M.","family":"Crawford","sequence":"additional","affiliation":[{"name":"Kentucky Geological Survey, University of Kentucky, Lexington, KY 40506, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7302-6795","authenticated-orcid":false,"given":"Hudson J.","family":"Koch","sequence":"additional","affiliation":[{"name":"Kentucky Geological Survey, University of Kentucky, Lexington, KY 40506, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1254-2507","authenticated-orcid":false,"given":"William C.","family":"Haneberg","sequence":"additional","affiliation":[{"name":"Kentucky Geological Survey, University of Kentucky, Lexington, KY 40506, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8080-1988","authenticated-orcid":false,"given":"Yichuan","family":"Zhu","sequence":"additional","affiliation":[{"name":"Department of Civil & Environmental Engineering, Temple University, Philadelphia, PA 19122, USA"}]}],"member":"1968","published-online":{"date-parts":[[2023,6,20]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"1337","DOI":"10.1007\/s12517-010-0238-7","article-title":"A Recent Scenario of Mass Wasting and Its Impact on the Transportation in Alborz Mountains, Iran Using Geo-Information Technology","volume":"4","author":"Farrokhnia","year":"2011","journal-title":"Arab. J. Geosci."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"2161","DOI":"10.5194\/nhess-18-2161-2018","article-title":"Global Fatal Landslide Occurrence from 2004 to 2016","volume":"18","author":"Froude","year":"2018","journal-title":"Nat. Hazards Earth Syst. Sci."},{"key":"ref_3","unstructured":"Crawford, M.M. (2014). Kentucky Geological Survey Information Circular, University of Kentucky."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"146","DOI":"10.1016\/j.enggeo.2017.11.012","article-title":"Assessment of Active Landslides Using Field Electrical Measurements","volume":"233","author":"Crawford","year":"2017","journal-title":"Eng. Geol."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"272","DOI":"10.1016\/j.geomorph.2005.06.002","article-title":"Probabilistic Landslide Hazard Assessment at the Basin Scale","volume":"72","author":"Guzzetti","year":"2005","journal-title":"Geomorphology"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"qjegh2020-177","DOI":"10.1144\/qjegh2020-177","article-title":"Using Landslide-Inventory Mapping for a Combined Bagged-Trees and Logistic-Regression Approach to Determining Landslide Susceptibility in Eastern Kentucky, USA","volume":"54","author":"Crawford","year":"2021","journal-title":"Q. J. Eng. Geol. Hydrogeol."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"361","DOI":"10.1007\/s10346-015-0557-6","article-title":"Spatial Prediction Models for Shallow Landslide Hazards: A Comparative Assessment of the Efficacy of Support Vector Machines, Artificial Neural Networks, Kernel Logistic Regression, and Logistic Model Tree","volume":"13","author":"Bui","year":"2016","journal-title":"Landslides"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"7501","DOI":"10.1002\/2015WR016909","article-title":"An Advanced Process-Based Distributed Model for the Investigation of Rainfall-Induced Landslides: The Effect of Process Representation and Boundary Conditions","volume":"51","author":"Anagnostopoulos","year":"2015","journal-title":"Water Resour. Res."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"122","DOI":"10.1016\/j.envsoft.2016.04.002","article-title":"Parallelization of the TRIGRS Model for Rainfall-Induced Landslides Using the Message Passing Interface","volume":"81","author":"Alvioli","year":"2016","journal-title":"Environ. Model. Softw."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"853","DOI":"10.1002\/(SICI)1096-9837(199609)21:9<853::AID-ESP676>3.0.CO;2-C","article-title":"An Approach towards Deterministic Landslide Hazard Analysis in GIS. A Case Study from Manizales (Colombia)","volume":"21","author":"Terlien","year":"1996","journal-title":"Earth Surf. Process. Landf."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"60","DOI":"10.1016\/j.earscirev.2018.03.001","article-title":"A Review of Statistically-Based Landslide Susceptibility Models","volume":"180","author":"Reichenbach","year":"2018","journal-title":"Earth Sci. Rev."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"103225","DOI":"10.1016\/j.earscirev.2020.103225","article-title":"Machine Learning Methods for Landslide Susceptibility Studies: A Comparative Overview of Algorithm Performance","volume":"207","author":"Merghadi","year":"2020","journal-title":"Earth Sci. Rev."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"13419","DOI":"10.1080\/10106049.2022.2076928","article-title":"An Interpretable Model for the Susceptibility of Rainfall-Induced Shallow Landslides Based on SHAP and XGBoost","volume":"37","author":"Zhou","year":"2022","journal-title":"Geocarto Int."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"2747","DOI":"10.1080\/10106049.2020.1837262","article-title":"Rainfall Induced Landslide Susceptibility Mapping Using Novel Hybrid Soft Computing Methods Based on Multi-Layer Perceptron Neural Network Classifier","volume":"37","author":"Sahana","year":"2022","journal-title":"Geocarto Int."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"166","DOI":"10.1016\/j.geomorph.2006.04.007","article-title":"Estimating the Quality of Landslide Susceptibility Models","volume":"81","author":"Guzzetti","year":"2006","journal-title":"Geomorphology"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"95","DOI":"10.5194\/nhess-14-95-2014","article-title":"Assessing the Quality of Landslide Susceptibility Maps\u2014Case Study Lower Austria","volume":"14","author":"Petschko","year":"2014","journal-title":"Nat. Hazards Earth Syst. Sci."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"164","DOI":"10.1016\/j.catena.2016.06.004","article-title":"Comparison of a Logistic Regression and Na\u00efve Bayes Classifier in Landslide Susceptibility Assessments: The Influence of Models Complexity and Training Dataset Size","volume":"145","author":"Tsangaratos","year":"2016","journal-title":"Catena"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"287","DOI":"10.1016\/j.geomorph.2013.08.013","article-title":"Landslide Susceptibility Mapping Based on Rough Set Theory and Support Vector Machines: A Case of the Three Gorges Area, China","volume":"204","author":"Peng","year":"2014","journal-title":"Geomorphology"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"425","DOI":"10.1007\/s10346-013-0391-7","article-title":"Landslide Susceptibility Mapping Using GIS-Based Multi-Criteria Decision Analysis, Support Vector Machines, and Logistic Regression","volume":"11","author":"Kavzoglu","year":"2014","journal-title":"Landslides"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"106975","DOI":"10.1016\/j.geomorph.2019.106975","article-title":"Machine Learning and Fractal Theory Models for Landslide Susceptibility Mapping: Case Study from the Jinsha River Basin","volume":"351","author":"Hu","year":"2020","journal-title":"Geomorphology"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"2919","DOI":"10.1007\/s10346-020-01473-9","article-title":"Landslide Susceptibility Prediction Based on a Semi-Supervised Multiple-Layer Perceptron Model","volume":"17","author":"Huang","year":"2020","journal-title":"Landslides"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"332","DOI":"10.1016\/j.scitotenv.2019.01.221","article-title":"Assessment of Advanced Random Forest and Decision Tree Algorithms for Modeling Rainfall-Induced Landslide Susceptibility in the Izu-Oshima Volcanic Island, Japan","volume":"662","author":"Dou","year":"2019","journal-title":"Sci. Total Environ."},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"McDowell, R.C. (1986). The Geology of Kentucky: A Text to Accompany the Geologic Map of Kentucky, US Geological Survey. Professional Paper 1151-H.","DOI":"10.3133\/pp1151H"},{"key":"ref_24","first-page":"217","article-title":"Landslide Inventory and Susceptibility Models, Prestonsburg 7.5-Min Quadrangle, Kentucky, USA","volume":"Volume 1","author":"Chapella","year":"2019","journal-title":"Proceedings of the IAEG\/AEG Annual Meeting Proceedings"},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Crawford, M.M., Dortch, J.M., Koch, H.J., Zhu, Y., Haneberg, W.C., Wang, Z., and Bryson, L.S. (2022). Landslide Risk Assessment in Eastern Kentucky, USA: Developing a Regional Scale, Limited Resource Approach. Remote Sens., 14.","DOI":"10.3390\/rs14246246"},{"key":"ref_26","unstructured":"Burns, W.J., and Madin, I.P. (2009). Protocol for Inventory Mapping of Landslide Deposits from Light Detection and Ranging (Lidar) Imagery, Oregon Department of Geology and Mineral Industries. DOGAMI Special Paper."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"27","DOI":"10.2113\/10.1.27","article-title":"A Rational Probabilistic Method for Spatially Distributed Landslide Hazard Assessment","volume":"10","author":"Haneberg","year":"2004","journal-title":"Environ. Eng. Geosci."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"209","DOI":"10.2113\/gseegeosci.6.3.209","article-title":"Deterministic and Probabilistic Approaches to Geologic Hazard Assessment","volume":"6","author":"Haneberg","year":"2000","journal-title":"Environ. Eng. Geosci."},{"key":"ref_29","unstructured":"Hammond, C. (1992). Level I Stability Analysis (LISA) Documentation for Version 2.0, US Department of Agriculture, Forest Service, Intermountain Research Station."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"112","DOI":"10.1016\/j.enggeo.2008.03.010","article-title":"Spatial Data for Landslide Susceptibility, Hazard, and Vulnerability Assessment: An Overview","volume":"102","author":"Castellanos","year":"2008","journal-title":"Eng. Geol."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"974638","DOI":"10.1155\/2012\/974638","article-title":"Landslide Susceptibility Assessment in Vietnam Using Support Vector Machines, Decision Tree, and Naive Bayes Models","volume":"2012","author":"Pradhan","year":"2012","journal-title":"Math. Probl. Eng."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"240","DOI":"10.1016\/j.envsoft.2016.07.005","article-title":"A Comparative Study of Different Machine Learning Methods for Landslide Susceptibility Assessment: A Case Study of Uttarakhand Area (India)","volume":"84","author":"Pham","year":"2016","journal-title":"Environ. Model. Softw."},{"key":"ref_33","first-page":"338","article-title":"Landslide Susceptibility Assessment at a Part of Uttarakhand Himalaya, India Using GIS\u2013Based Statistical Approach of Frequency Ratio Method","volume":"4","author":"Pham","year":"2015","journal-title":"Int. J. Eng. Res. Technol."},{"key":"ref_34","unstructured":"Koller, D., and Friedman, N. (2009). Probabilistic Graphical Models: Principles and Techniques, MIT Press."},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"309","DOI":"10.1007\/BF00994110","article-title":"A Bayesian Method for the Induction of Probabilistic Networks from Data","volume":"9","author":"Cooper","year":"1992","journal-title":"Mach. Learn."},{"key":"ref_36","doi-asserted-by":"crossref","unstructured":"Nhu, V.H., Shirzadi, A., Shahabi, H., Singh, S.K., Al-Ansari, N., Clague, J.J., Jaafari, A., Chen, W., Miraki, S., and Dou, J. (2020). Shallow Landslide Susceptibility Mapping: A Comparison between Logistic Model Tree, Logistic Regression, Na\u00efve Bayes Tree, Artificial Neural Network, and Support Vector Machine Algorithms. Int. J. Environ. Res. Public Health, 17.","DOI":"10.3390\/ijerph17082749"},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"9","DOI":"10.1186\/s40562-022-00218-x","article-title":"Evaluation of the Landslide Susceptibility and Its Spatial Difference in the Whole Qinghai-Tibetan Plateau Region by Five Learning Algorithms","volume":"9","author":"Sajadi","year":"2022","journal-title":"Geosci. Lett."},{"key":"ref_38","first-page":"54","article-title":"Sentiment Analysis of Review Datasets Using Naive Bayes and K-NN Classifier","volume":"8","author":"Dey","year":"2016","journal-title":"Int. J. Inf. Eng. Electron. Bus."},{"key":"ref_39","doi-asserted-by":"crossref","unstructured":"Heckerman, D. (1998). A Tutorial on Learning with Bayesian Networks, Springer.","DOI":"10.1007\/978-94-011-5014-9_11"},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"131","DOI":"10.1023\/A:1007465528199","article-title":"Bayesian Network Classifiers","volume":"29","author":"Friedman","year":"1997","journal-title":"Mach. Learn."},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"575","DOI":"10.1080\/01621459.1984.10478083","article-title":"Cross-Validation of Regression Models","volume":"79","author":"Picard","year":"1984","journal-title":"J. Am. Stat. Assoc."},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"104396","DOI":"10.1016\/j.catena.2019.104396","article-title":"Application of Alternating Decision Tree with AdaBoost and Bagging Ensembles for Landslide Susceptibility Mapping","volume":"187","author":"Wu","year":"2020","journal-title":"Catena"},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"1665","DOI":"10.1080\/10106049.2019.1585482","article-title":"Landslide Susceptibility Mapping Using Na\u00efve Bayes and Bayesian Network Models in Umyeonsan, Korea","volume":"35","author":"Lee","year":"2020","journal-title":"Geocarto Int."},{"key":"ref_44","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.scitotenv.2019.01.329","article-title":"Landslide Spatial Modelling Using Novel Bivariate Statistical Based Na\u00efve Bayes, RBF Classifier, and RBF Network Machine Learning Algorithms","volume":"663","author":"He","year":"2019","journal-title":"Sci. Total Environ."},{"key":"ref_45","doi-asserted-by":"crossref","first-page":"799","DOI":"10.1093\/bjsw\/32.6.799","article-title":"Social Work: Gender, Care and Justice","volume":"32","author":"Orme","year":"2002","journal-title":"Br. J. Soc. Work."}],"container-title":["Remote Sensing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2072-4292\/15\/12\/3200\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T19:57:15Z","timestamp":1760126235000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2072-4292\/15\/12\/3200"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,20]]},"references-count":45,"journal-issue":{"issue":"12","published-online":{"date-parts":[[2023,6]]}},"alternative-id":["rs15123200"],"URL":"https:\/\/doi.org\/10.3390\/rs15123200","relation":{},"ISSN":["2072-4292"],"issn-type":[{"value":"2072-4292","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,6,20]]}}}