Landslide Susceptibility Assessment via Imbalanced Data Augmentation with Tabular Variational Autoencoder and Quality–Diversity Post-Selection

Landslides are among the most common geological hazards in mountainous regions, posing significant threats to resident safety and infrastructure stability. Due to the complexity of terrain and the difficulty of field surveys, landslide samples in these areas often suffer from class imbalance, which...

Celý popis

Uloženo v:

Podrobná bibliografie
Vydáno v:	Applied sciences Ročník 15; číslo 22; s. 11965
Hlavní autoři:	Xu, Zhengyang, Wang, Shitai, Yin, Min, Zhang, Xiaoyu, Lu, Zengyang, Yu, Songchao, Huang, Junjun
Médium:	Journal Article
Jazyk:	angličtina
Vydáno:	Basel MDPI AG 01.11.2025
Témata:	Accuracy Algorithms China class imbalance data augmentation Datasets Disasters Earthquakes Emergency communications systems Emergency preparedness Geology Hydrology landslide susceptibility Landslides Landslides & mudslides Lithology Precipitation Puerto Rico quality–diversity Rain and rainfall Risk assessment Risk management Surveys Tabular Variational Autoencoder Topography Variables Vegetation Puerto Rico China
ISSN:	2076-3417, 2076-3417
On-line přístup:	Získat plný text
Tagy:	Přidat tag Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!

Abstract	Landslides are among the most common geological hazards in mountainous regions, posing significant threats to resident safety and infrastructure stability. Due to the complexity of terrain and the difficulty of field surveys, landslide samples in these areas often suffer from class imbalance, which undermines the accuracy of susceptibility models. To address this issue, this study constructed a multi-factor landslide database and employed a Tabular Variational Autoencoder (TVAE) to generate synthetic samples. A Quality–Diversity (QD) screening strategy was further integrated to enhance the representativeness and diversity of the augmented data. Experimental results demonstrate that the proposed TVAE–QD method improves model performance, with generated samples showing distributions closer to real data. Compared with the Synthetic Minority Over-sampling Technique (SMOTE) and unfiltered TVAE, the TVAE–QD method achieved higher predictive accuracy and exhibited greater robustness under progressive data augmentation. In the Random Forest (RF) model, the TVAE–QD achieved its best performance at a scale of 350, with an Area Under the Curve (AUC) of 0.923 and a Precision–Recall AUC (PR–AUC) of 0.907, outperforming TVAE and SMOTE. In the Light Gradient Boosting Machine (LightGBM) model, the AUC peaked at 0.911 at a scale of 450, while the PR–AUC reached its maximum of 0.896 at a scale of 200. Shapley Additive Explanations (SHAP) analysis confirmed that data augmentation preserved interpretability: dominant factors such as elevation, rainfall, and the Normalized Difference Vegetation Index (NDVI) remained stable, with only minor adjustments among secondary variables. Overall, the TVAE–QD framework effectively mitigates class imbalance and offers a promising technical solution for landslide risk assessment in mountainous regions.
AbstractList	Landslides are among the most common geological hazards in mountainous regions, posing significant threats to resident safety and infrastructure stability. Due to the complexity of terrain and the difficulty of field surveys, landslide samples in these areas often suffer from class imbalance, which undermines the accuracy of susceptibility models. To address this issue, this study constructed a multi-factor landslide database and employed a Tabular Variational Autoencoder (TVAE) to generate synthetic samples. A Quality–Diversity (QD) screening strategy was further integrated to enhance the representativeness and diversity of the augmented data. Experimental results demonstrate that the proposed TVAE–QD method improves model performance, with generated samples showing distributions closer to real data. Compared with the Synthetic Minority Over-sampling Technique (SMOTE) and unfiltered TVAE, the TVAE–QD method achieved higher predictive accuracy and exhibited greater robustness under progressive data augmentation. In the Random Forest (RF) model, the TVAE–QD achieved its best performance at a scale of 350, with an Area Under the Curve (AUC) of 0.923 and a Precision–Recall AUC (PR–AUC) of 0.907, outperforming TVAE and SMOTE. In the Light Gradient Boosting Machine (LightGBM) model, the AUC peaked at 0.911 at a scale of 450, while the PR–AUC reached its maximum of 0.896 at a scale of 200. Shapley Additive Explanations (SHAP) analysis confirmed that data augmentation preserved interpretability: dominant factors such as elevation, rainfall, and the Normalized Difference Vegetation Index (NDVI) remained stable, with only minor adjustments among secondary variables. Overall, the TVAE–QD framework effectively mitigates class imbalance and offers a promising technical solution for landslide risk assessment in mountainous regions.
Audience	Academic
Author	Yu, Songchao Yin, Min Wang, Shitai Lu, Zengyang Zhang, Xiaoyu Huang, Junjun Xu, Zhengyang
Author_xml	– sequence: 1 givenname: Zhengyang surname: Xu fullname: Xu, Zhengyang – sequence: 2 givenname: Shitai surname: Wang fullname: Wang, Shitai – sequence: 3 givenname: Min surname: Yin fullname: Yin, Min – sequence: 4 givenname: Xiaoyu surname: Zhang fullname: Zhang, Xiaoyu – sequence: 5 givenname: Zengyang surname: Lu fullname: Lu, Zengyang – sequence: 6 givenname: Songchao surname: Yu fullname: Yu, Songchao – sequence: 7 givenname: Junjun surname: Huang fullname: Huang, Junjun
BookMark	eNpNUctu1DAUjVCRKKU7PsASW6b1O_Fy1PIYaSRALWyja-dm8CgTB9sp6o5PQOIP-ZI6HYRqL2wfn3Oufc_L6mQMI1bVa0YvhDD0EqaJKc4ZM1o9q045rfVKSFafPNm_qM5T2tMyDBMNo6fV7y2MXRp8h-RmTg6n7K0ffL4n65QwpQOOmdx5IJuDhQFGhx25hgxkPe-WO8g-jOSnz9_JLdh5gEi-QfSPMAyFlQOOLnQYSSlEvsywmP_99efa32FMS6HPIeXVDQ7oFtGr6nkPQ8Lzf-tZ9fX9u9urj6vtpw-bq_V25Tht1AodcmSGN9gZzZigwklupeikQyWck2i1gMZwo-VyQGmtYSCbrvSIGi3Oqs3Rtwuwb6foDxDv2wC-fQRC3LUQs3cDtg1lDFkNWlErlbW2q1FBX0tt-lo7XrzeHL2mGH7MmHK7D3Ms_0-t4LVStPReFdbFkbWDYurHPuQIrswOD96VMHtf8HWjlVRU87oI3h4FLoaUIvb_n8lou2TePs1cPADLoaNl
Cites_doi	10.1038/s41598-025-97074-4 10.3390/app14145975 10.3390/ijerph16030368 10.3390/ijgi8010004 10.1007/s10064-024-03980-8 10.1080/19475705.2024.2314565 10.1007/s12145-025-01931-9 10.1109/MLDS.2017.21 10.1007/s42452-025-06798-5 10.1016/j.enggeo.2025.108021 10.1007/s00477-025-03118-6 10.1613/jair.953 10.1007/s12145-025-01700-8 10.1007/s11356-025-36615-w 10.1007/s11069-023-06104-9 10.3390/app14146040 10.1080/19475705.2020.1803421 10.3390/rs14235945 10.1016/j.asr.2025.05.020 10.1007/s12665-024-11442-3 10.3390/app15147646 10.3390/ijgi12050197 10.1007/s11069-025-07132-3 10.1016/j.eswa.2024.126084 10.1007/s10064-023-03403-0 10.1007/s11356-024-33287-w 10.1016/S0047-259X(02)00025-8 10.1016/j.asoc.2024.112223 10.1007/s10346-023-02166-9 10.3390/app14125324 10.1016/j.geomorph.2017.04.024 10.1007/s10661-023-12100-0 10.1007/s41748-024-00457-2 10.1007/s42452-020-03307-8 10.1007/s12145-025-01727-x 10.3390/app15147937 10.1016/j.sftr.2025.101119 10.1007/s00477-021-02165-z 10.1016/j.cageo.2021.104966 10.1016/j.eswa.2023.122778 10.1201/9781315140919 10.1007/s11069-024-06833-5 10.1093/biomet/63.3.413 10.1016/j.catena.2024.108639 10.1038/s41598-025-93704-z 10.1007/s10346-022-01998-1 10.3390/app14125042 10.1007/s10064-025-04490-x 10.1016/j.asoc.2023.110429 10.1007/s10064-025-04105-5 10.1109/TAI.2022.3229289 10.31590/ejosat.1077867 10.1007/s11069-020-04264-6 10.1007/s10346-024-02352-3
ContentType	Journal Article
Copyright	COPYRIGHT 2025 MDPI AG 2025 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.
Copyright_xml	– notice: COPYRIGHT 2025 MDPI AG – notice: 2025 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.
DBID	AAYXX CITATION ABUWG AFKRA AZQEC BENPR CCPQU DWQXO PHGZM PHGZT PIMPY PKEHL PQEST PQQKQ PQUKI DOA
DOI	10.3390/app152211965
DatabaseName	CrossRef ProQuest Central (Alumni Edition) ProQuest Central UK/Ireland ProQuest Central Essentials ProQuest Central ProQuest One Community College ProQuest Central Korea ProQuest Central Premium ProQuest One Academic (New) Publicly Available Content Database ProQuest One Academic Middle East (New) ProQuest One Academic Eastern Edition (DO NOT USE) ProQuest One Academic (retired) ProQuest One Academic UKI Edition DOAJ Directory of Open Access Journals
DatabaseTitle	CrossRef Publicly Available Content Database ProQuest Central ProQuest One Academic Middle East (New) ProQuest One Academic UKI Edition ProQuest Central Essentials ProQuest Central Korea ProQuest One Academic Eastern Edition ProQuest Central (Alumni Edition) ProQuest One Community College ProQuest Central (New) ProQuest One Academic ProQuest One Academic (New)
DatabaseTitleList	CrossRef Publicly Available Content Database
Database_xml	– sequence: 1 dbid: DOA name: DOAJ Directory of Open Access Journals url: https://www.doaj.org/ sourceTypes: Open Website – sequence: 2 dbid: PIMPY name: Publicly Available Content Database url: http://search.proquest.com/publiccontent sourceTypes: Aggregation Database
DeliveryMethod	fulltext_linktorsrc
Discipline	Engineering Sciences (General) Geology
EISSN	2076-3417
ExternalDocumentID	oai_doaj_org_article_8011e17a650b45bbbd7e5af7469f76c2 A865450627 10_3390_app152211965
GeographicLocations	Puerto Rico China
GeographicLocations_xml	– name: China – name: Puerto Rico
GroupedDBID	.4S 2XV 5VS 7XC 8CJ 8FE 8FG 8FH AADQD AAFWJ AAYXX ADBBV ADMLS AFFHD AFKRA AFPKN AFZYC ALMA_UNASSIGNED_HOLDINGS APEBS ARCSS BCNDV BENPR CCPQU CITATION CZ9 D1I D1J D1K GROUPED_DOAJ IAO IGS ITC K6- K6V KC. KQ8 L6V LK5 LK8 M7R MODMG M~E OK1 P62 PHGZM PHGZT PIMPY PROAC TUS ABUWG AZQEC DWQXO PKEHL PQEST PQQKQ PQUKI
ID	FETCH-LOGICAL-c2085-ece2e1928ed9611303c42b43d4ce53cc4eb63a892964c4ebe4bb91a48d5220963
IEDL.DBID	DOA
ISSN	2076-3417
IngestDate	Mon Dec 01 19:27:30 EST 2025 Wed Nov 26 12:51:28 EST 2025 Tue Dec 02 03:53:41 EST 2025 Thu Nov 13 04:27:19 EST 2025
IsDoiOpenAccess	true
IsOpenAccess	true
IsPeerReviewed	true
IsScholarly	true
Issue	22
Language	English
LinkModel	DirectLink
MergedId	FETCHMERGED-LOGICAL-c2085-ece2e1928ed9611303c42b43d4ce53cc4eb63a892964c4ebe4bb91a48d5220963
Notes	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14
OpenAccessLink	https://doaj.org/article/8011e17a650b45bbbd7e5af7469f76c2
PQID	3275503415
PQPubID	2032433
ParticipantIDs	doaj_primary_oai_doaj_org_article_8011e17a650b45bbbd7e5af7469f76c2 proquest_journals_3275503415 gale_infotracacademiconefile_A865450627 crossref_primary_10_3390_app152211965
PublicationCentury	2000
PublicationDate	20251101
PublicationDateYYYYMMDD	2025-11-01
PublicationDate_xml	– month: 11 year: 2025 text: 20251101 day: 01
PublicationDecade	2020
PublicationPlace	Basel
PublicationPlace_xml	– name: Basel
PublicationTitle	Applied sciences
PublicationYear	2025
Publisher	MDPI AG
Publisher_xml	– name: MDPI AG
References	Kim (ref_36) 2023; 82 ref_50 Li (ref_55) 2020; 104 ref_13 ref_12 ref_11 Wang (ref_45) 2024; 166 Chundawat (ref_43) 2024; 5 Li (ref_53) 2025; 84 Xu (ref_52) 2024; 32 Yang (ref_6) 2024; 83 Aitchison (ref_47) 1976; 63 Aksoy (ref_58) 2023; 195 Zhang (ref_38) 2022; 158 Lu (ref_44) 2024; 15 ref_25 Jiang (ref_21) 2024; 22 Ado (ref_18) 2025; 32 Khan (ref_35) 2024; 244 Lu (ref_1) 2025; 8 Yong (ref_15) 2022; 36 ref_28 Chen (ref_19) 2025; 18 Gao (ref_24) 2020; 2 ref_26 Chawla (ref_32) 2002; 16 Sato (ref_57) 2025; 249 Orefice (ref_10) 2024; 121 Zhang (ref_51) 2025; 84 ref_34 ref_31 Qian (ref_20) 2025; 76 Byeon (ref_42) 2025; 265 Schmaltz (ref_56) 2017; 290 Ali (ref_30) 2025; 10 ref_39 Wang (ref_4) 2025; 18 Zhao (ref_14) 2024; 31 Pande (ref_2) 2025; 7 Chen (ref_54) 2023; 118 Feng (ref_33) 2025; 350 Chen (ref_17) 2025; 121 Wu (ref_23) 2024; 83 Gupta (ref_22) 2022; 20 ref_46 Zhao (ref_16) 2025; 18 Zhao (ref_27) 2020; 11 ref_41 Li (ref_48) 2003; 86 ref_40 ref_3 Pham (ref_37) 2023; 143 Min (ref_29) 2023; 21 ref_49 ref_9 ref_8 ref_5 ref_7
References_xml	– ident: ref_5 doi: 10.1038/s41598-025-97074-4 – ident: ref_41 doi: 10.3390/app14145975 – ident: ref_31 doi: 10.3390/ijerph16030368 – ident: ref_39 doi: 10.3390/ijgi8010004 – volume: 83 start-page: 461 year: 2024 ident: ref_23 article-title: Impact of sampling for landslide susceptibility assessment using interpretable machine learning models publication-title: Bull. Eng. Geol. Environ. doi: 10.1007/s10064-024-03980-8 – volume: 15 start-page: 2314565 year: 2024 ident: ref_44 article-title: Landslide susceptibility analysis using random forest model with SMOTE-ENN resampling algorithm publication-title: Geomat. Nat. Hazards Risk doi: 10.1080/19475705.2024.2314565 – volume: 18 start-page: 440 year: 2025 ident: ref_4 article-title: The impact of different sampling strategies on landslide susceptibility assessment: An explainable hybrid BO-XGBoost model publication-title: Earth Sci. Inform. doi: 10.1007/s12145-025-01931-9 – ident: ref_28 doi: 10.1109/MLDS.2017.21 – volume: 7 start-page: 1109 year: 2025 ident: ref_2 article-title: Integrating social vulnerability to improve landslide susceptibility assessment quality: A hybrid machine learning approach publication-title: Discov. Appl. Sci. doi: 10.1007/s42452-025-06798-5 – volume: 350 start-page: 108021 year: 2025 ident: ref_33 article-title: Prediction of landslide dam stability and influencing factors analysis publication-title: Eng. Geol. doi: 10.1016/j.enggeo.2025.108021 – ident: ref_3 doi: 10.1007/s00477-025-03118-6 – volume: 16 start-page: 321 year: 2002 ident: ref_32 article-title: SMOTE: Synthetic minority over-sampling technique publication-title: J. Artif. Intell. Res. doi: 10.1613/jair.953 – volume: 18 start-page: 190 year: 2025 ident: ref_16 article-title: Landslide susceptibility assessment using information quantity and machine learning integrated models: A case study of Sichuan province, southwestern China publication-title: Earth Sci. Inform. doi: 10.1007/s12145-025-01700-8 – volume: 32 start-page: 15746 year: 2025 ident: ref_18 article-title: Hyper-parameter optimization for enhanced machine learning-based landslide susceptibility mapping publication-title: Environ. Sci. Pollut. Res. Int. doi: 10.1007/s11356-025-36615-w – volume: 118 start-page: 2543 year: 2023 ident: ref_54 article-title: An innovative method for landslide susceptibility mapping supported by fractal theory, GeoDetector, and random forest: A case study in Sichuan Province, SW China publication-title: Nat. Hazards doi: 10.1007/s11069-023-06104-9 – ident: ref_12 doi: 10.3390/app14146040 – volume: 11 start-page: 1542 year: 2020 ident: ref_27 article-title: Using the rotation and random forest models of ensemble learning to predict landslide susceptibility publication-title: Geomat. Nat. Hazards Risk doi: 10.1080/19475705.2020.1803421 – volume: 32 start-page: 1640 year: 2024 ident: ref_52 article-title: Comparative analysis of landslide susceptibility assessment accuracy in different evaluation units publication-title: J. Eng. Geol. – ident: ref_25 doi: 10.3390/rs14235945 – volume: 76 start-page: 699 year: 2025 ident: ref_20 article-title: Optimizing the application of machine learning models in predicting landslide susceptibility using the information value model in Junlian County of Sichuan Basin publication-title: Adv. Space Res. doi: 10.1016/j.asr.2025.05.020 – volume: 83 start-page: 132 year: 2024 ident: ref_6 article-title: Effect of landslide spatial representation and raster resolution on the landslide susceptibility assessment publication-title: Environ. Earth Sci. doi: 10.1007/s12665-024-11442-3 – ident: ref_9 doi: 10.3390/app15147646 – ident: ref_26 doi: 10.3390/ijgi12050197 – volume: 121 start-page: 8367 year: 2025 ident: ref_17 article-title: Spatial prediction and mapping of landslide susceptibility using machine learning models publication-title: Nat. Hazards doi: 10.1007/s11069-025-07132-3 – volume: 8 start-page: 281 year: 2025 ident: ref_1 article-title: Landslide susceptibility assessment based on an interpretable coupled FR-RF model: A case study of Longyan City, Fujian Province, Southeast China publication-title: China Geol. – volume: 265 start-page: 126084 year: 2025 ident: ref_42 article-title: Explainable hybrid tabular Variational Autoencoder and feature Tokenizer Transformer for depression prediction publication-title: Expert Syst. Appl. doi: 10.1016/j.eswa.2024.126084 – volume: 82 start-page: 381 year: 2023 ident: ref_36 article-title: Application of classification coupled with PCA and SMOTE, for obtaining safety factor of landslide based on HRA publication-title: Bull. Eng. Geol. Environ. doi: 10.1007/s10064-023-03403-0 – volume: 31 start-page: 32043 year: 2024 ident: ref_14 article-title: Landslide susceptibility assessment based on frequency ratio and semi-supervised heterogeneous ensemble learning model publication-title: Environ. Sci. Pollut. Res. Int. doi: 10.1007/s11356-024-33287-w – volume: 86 start-page: 266 year: 2003 ident: ref_48 article-title: Nonparametric estimation of distributions with categorical and continuous data publication-title: J. Multivar. Anal. doi: 10.1016/S0047-259X(02)00025-8 – volume: 166 start-page: 112223 year: 2024 ident: ref_45 article-title: Challenges and opportunities of generative models on tabular data publication-title: Appl. Soft Comput. doi: 10.1016/j.asoc.2024.112223 – volume: 21 start-page: 291 year: 2023 ident: ref_29 article-title: Strategy of oversampling geotechnical parameters through geostatistical, SMOTE, and CTGAN methods for assessing susceptibility of landslide publication-title: Landslides doi: 10.1007/s10346-023-02166-9 – ident: ref_8 doi: 10.3390/app14125324 – volume: 290 start-page: 250 year: 2017 ident: ref_56 article-title: The influence of forest cover on landslide occurrence explored with spatio-temporal information publication-title: Geomorphology doi: 10.1016/j.geomorph.2017.04.024 – ident: ref_40 – volume: 195 start-page: 1525 year: 2023 ident: ref_58 article-title: Determination of landslide susceptibility with Analytic Hierarchy Process (AHP) and the role of forest ecosystem services on landslide susceptibility publication-title: Env. Monit Assess doi: 10.1007/s10661-023-12100-0 – ident: ref_49 doi: 10.1007/s41748-024-00457-2 – volume: 2 start-page: 1512 year: 2020 ident: ref_24 article-title: Three oversampling methods applied in a comparative landslide spatial research in Penang Island, Malaysia publication-title: SN Appl. Sci. doi: 10.1007/s42452-020-03307-8 – volume: 18 start-page: 225 year: 2025 ident: ref_19 article-title: Optimizing landslide susceptibility mapping using integrated forest by penalizing attributes model with ensemble algorithms publication-title: Earth Sci. Inform. doi: 10.1007/s12145-025-01727-x – ident: ref_13 doi: 10.3390/app15147937 – volume: 10 start-page: 101119 year: 2025 ident: ref_30 article-title: Classification of imbalanced travel mode choice dataset with SMOTE and prediction using interpretable machine learning publication-title: Sustain. Futures doi: 10.1016/j.sftr.2025.101119 – volume: 36 start-page: 2399 year: 2022 ident: ref_15 article-title: Review of landslide susceptibility assessment based on knowledge mapping publication-title: Stoch. Environ. Res. Risk Assess. doi: 10.1007/s00477-021-02165-z – volume: 158 start-page: 104966 year: 2022 ident: ref_38 article-title: Combining a class-weighted algorithm and machine learning models in landslide susceptibility mapping: A case study of Wanzhou section of the Three Gorges Reservoir, China publication-title: Comput. Geosci. doi: 10.1016/j.cageo.2021.104966 – ident: ref_50 – volume: 244 start-page: 122778 year: 2024 ident: ref_35 article-title: A review of ensemble learning and data augmentation models for class imbalanced problems: Combination, implementation and evaluation publication-title: Expert Syst. Appl. doi: 10.1016/j.eswa.2023.122778 – ident: ref_46 doi: 10.1201/9781315140919 – volume: 121 start-page: 2613 year: 2024 ident: ref_10 article-title: Regional assessment of coastal landslide susceptibility in Liguria, Northern Italy, using MaxEnt publication-title: Nat. Hazards doi: 10.1007/s11069-024-06833-5 – volume: 63 start-page: 413 year: 1976 ident: ref_47 article-title: Multivariate binary discrimination by the kernel method publication-title: Biometrika doi: 10.1093/biomet/63.3.413 – volume: 249 start-page: 108639 year: 2025 ident: ref_57 article-title: Variation in the frequency and characteristics of landslides in response to changes in forest cover and rainfall in Japan over the last century: A literature review publication-title: Catena doi: 10.1016/j.catena.2024.108639 – ident: ref_11 doi: 10.1038/s41598-025-93704-z – volume: 20 start-page: 933 year: 2022 ident: ref_22 article-title: Handling data imbalance in machine learning based landslide susceptibility mapping: A case study of Mandakini River Basin, North-Western Himalayas publication-title: Landslides doi: 10.1007/s10346-022-01998-1 – ident: ref_7 doi: 10.3390/app14125042 – volume: 84 start-page: 481 year: 2025 ident: ref_53 article-title: Susceptibility assessment and driving factor analysis of geological hazards in complex landform areas: Insights from Sichuan, China publication-title: Bull. Eng. Geol. Environ. doi: 10.1007/s10064-025-04490-x – volume: 143 start-page: 110429 year: 2023 ident: ref_37 article-title: Examining the role of class imbalance handling strategies in predicting earthquake-induced landslide-prone regions publication-title: Appl. Soft Comput. doi: 10.1016/j.asoc.2023.110429 – volume: 84 start-page: 95 year: 2025 ident: ref_51 article-title: Comparative study on landslide susceptibility assessment of different models: A case study of alpine mountainous region in Xinjiang publication-title: Bull. Eng. Geol. Environ. doi: 10.1007/s10064-025-04105-5 – volume: 5 start-page: 300 year: 2024 ident: ref_43 article-title: A Universal Metric for Robust Evaluation of Synthetic Tabular Data publication-title: IEEE Trans. Artif. Intell. doi: 10.1109/TAI.2022.3229289 – ident: ref_34 doi: 10.31590/ejosat.1077867 – volume: 104 start-page: 2115 year: 2020 ident: ref_55 article-title: Influence of human activity on landslide susceptibility development in the Three Gorges area publication-title: Nat. Hazards doi: 10.1007/s11069-020-04264-6 – volume: 22 start-page: 189 year: 2024 ident: ref_21 article-title: Investigating landslide data balancing for susceptibility mapping using generative and machine learning models publication-title: Landslides doi: 10.1007/s10346-024-02352-3
SSID	ssj0000913810
Score	2.3347876
Snippet	Landslides are among the most common geological hazards in mountainous regions, posing significant threats to resident safety and infrastructure stability. Due...
SourceID	doaj proquest gale crossref
SourceType	Open Website Aggregation Database Index Database
StartPage	11965
SubjectTerms	Accuracy Algorithms China class imbalance data augmentation Datasets Disasters Earthquakes Emergency communications systems Emergency preparedness Geology Hydrology landslide susceptibility Landslides Landslides & mudslides Lithology Precipitation Puerto Rico quality–diversity Rain and rainfall Risk assessment Risk management Surveys Tabular Variational Autoencoder Topography Variables Vegetation
SummonAdditionalLinks	– databaseName: ProQuest Central dbid: BENPR link: http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1Lb9NAEB5BClI5AA1UDRS0BxBwsIjt9euEUtoCUhVVtKDeVvuYVJHapNhOpdz4CUj8w_6Szmw2IRe4cLS9fkgznvlmduYbgFdl36RVnsjIaVtRgIIy0kViolwTto2dLUfONwofFcNheXZWHYeEWxPKKpc20RtqN7WcI3-fJgWBabK52YerHxFPjeLd1TBC4y5sMFOZ7MDG3sHw-Osqy8Ksl2XcX1S8pxTf874wuSxezf5kzRd5yv6_GWbvbQ4f_e93PoaHAWeKwUIxtuAOTrrwYI19sAv3P_mpvvMubIU_vBFvAw31uyfw64i7gC_GDsXJrPHVL76Qdi4GKzZPcT3W4sul4fpIi07s61aLwez8MnQ0TQTnecWpNlztKr5TYB6Sj7SqnTKJpsNa0IvEgsxjfvPz9_6yVETwJOHoxE_qoZuewrfDg9OPn6MwvyGyPPkzQosJEoIs0VV5zM7SysTI1EmLWWqtRJOnuqx455cPUBpTxVqWjgREoVW6DZ3JdII7IAymBLyYOw0LWY5QS0vYgx7vZObSvuvB66Uk1dWCpkNReMMSV-sS78Eei3m1hsm1_Ylpfa7Cv6rIaccYF5rAq5GZMcYVmOlRIfNqVOQ26cEbVhLFJqCttdWhk4E-lcm01KDMCZcy_3MPdpdKooJtaNQfDXn278vPYTPhacO-83EXOm09wxdwz16346Z-GVT9FhqkC_I priority: 102 providerName: ProQuest
Title	Landslide Susceptibility Assessment via Imbalanced Data Augmentation with Tabular Variational Autoencoder and Quality–Diversity Post-Selection
URI	https://www.proquest.com/docview/3275503415 https://doaj.org/article/8011e17a650b45bbbd7e5af7469f76c2
Volume	15
hasFullText	1
inHoldings	1
isFullTextHit
isPrint
journalDatabaseRights	– providerCode: PRVAON databaseName: DOAJ Directory of Open Access Journals customDbUrl: eissn: 2076-3417 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0000913810 issn: 2076-3417 databaseCode: DOA dateStart: 20110101 isFulltext: true titleUrlDefault: https://www.doaj.org/ providerName: Directory of Open Access Journals – providerCode: PRVHPJ databaseName: ROAD: Directory of Open Access Scholarly Resources customDbUrl: eissn: 2076-3417 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0000913810 issn: 2076-3417 databaseCode: M~E dateStart: 20110101 isFulltext: true titleUrlDefault: https://road.issn.org providerName: ISSN International Centre – providerCode: PRVPQU databaseName: AUTh Library subscriptions: ProQuest Central customDbUrl: eissn: 2076-3417 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0000913810 issn: 2076-3417 databaseCode: BENPR dateStart: 20110101 isFulltext: true titleUrlDefault: https://www.proquest.com/central providerName: ProQuest – providerCode: PRVPQU databaseName: Publicly Available Content Database customDbUrl: eissn: 2076-3417 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0000913810 issn: 2076-3417 databaseCode: PIMPY dateStart: 20110101 isFulltext: true titleUrlDefault: http://search.proquest.com/publiccontent providerName: ProQuest
link	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV3NTtwwEB4h4NAeENBWXaDIB6rSQ1QSO3_HpYCKRFcroBU9Wf6ZrVYqC9rNInHjEZD6hn2SzjhelEvVC0dHTmJ5xp5v7JlvAPaqAyvrIlOJN64mBwVVYsrMJoUhbJt6V418SBQ-KweD6uqqHnZKfXFMWEsP3E7cJ9pBU0xLQ0jCqtxa60vMzagkt25UFi7svoR6Os5U2IPrlKmr2kh3SX493weTqWI-M7YjHRsUqPr_tSEHK3OyDmsRHop-O6wNWMLJJrzskAZuwkZcjjOxHzmjP76CxzNO2f019igu5rMQqhKiXu9F_4l6U9yNjTi9thzM6NCLI9MY0Z__vI7pRxPBh7Li0lgOTRXfyYuOJ4XUq7lhxkuPU0E_Ei3zxv2fh99Hi7gOwWV_k4tQVodeeg3fTo4vP39JYrGFxHGZzgQdZkhwr0JfFylbNqcyq6RXDnPpnEJbSFPVfE3LDVTW1qlRladZJT9IvoHlyc0E34KwKAklMdEZlqoaoVGOgAJ93qvcywPfg_eL6de3LaeGJl-ExaS7YurBIcvmqQ8zYYcHpB866of-n3704ANLVvN6babGmZh2QENl5ivdrwoCkUzW3IOdhfB1XMgzLbOSfDgy9fnWc4xmG15kXEA4JDPuwHIzneM7WHV3zXg23YWVw-PB8Hw36DK1hqdfhz_-AkJ1_QQ
linkProvider	Directory of Open Access Journals
linkToHtml	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMw1V3LbtNAFL0qKaiwABqKCBSYBRWwsIjt8WuBUCCURk2jSA2orIZ5pYpEk-I4RdnxCUj8Bx_Fl3CvPQ7ZwK4Lln5HzvG9Z2buPQfgSdpWYRYH3DNSZzhAsdyTSaC8WCK39Y1Ox6ZsFO4ng0F6cpINN-Bn3QtDZZV1TCwDtZlpmiN_EQYJkmmMudGr8y8euUbR6mptoVHB4tAuv-KQbf6y18X_dy8I9t-O3hx4zlXA0-RH6VltA4u8JrUmi30K4ZoHioeGaxuFWnOr4lCmGa1H0oblSmW-5KlBqoKEP8T7XoFNjmBPG7A57B0NP65mdUhlM_XbVYV9GGZtWofGFEk6apS_1nJfaRHwt0RQZrf9W__be7kNNx2PZp0K-NuwYadNuLGmrtiEa-9K1-JlE7ZdBJuzZ05m-_kd-N6nLufPE2PZ8WJeVveUhcJL1lmplbKLiWS9M0X1n9oa1pWFZJ3F6Znr2JoymsdmI6mompd9kPnETa7iWcWMREKNzRk-iFViJctf335061IYRk7J3nHpRIQX7cD7S3ljd6ExnU3tPWDKhkgsSRvOJjwdW8k1ciu8veGRCdumBXs1csR5JUMicPhGCBPrCGvBa4LV6hwSDy93zPJT4WKRQFLiWz-RSM4Vj5RSJrGRHCc8zsZJrIMWPCVQCgpxRS61dJ0a-FNJLEx00hh5N-lbt2C3BqVwsW8u_iDy_r8PP4atg9FRX_R7g8MHcD0gZ-Wyy3MXGkW-sA_hqr4oJvP8kfvMGHy6bAT_Bo7iZ_I
linkToPdf	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMw1V1Nb9NAEB2VFhAcgAYQgQJ7oAIOVmN7_XVAKBACUUMUqaUqp2W_XEWiSbGdotz4CUj8G34Ov4QZZx1ygVsPHJPYjmW_nXm7O_MewJO0o8IsDrhnpM5wgmK5J5NAebFEbusbneambhQeJqNRenycjTfgZ9MLQ2WVTUysA7WZaVoj3wuDBMk0xtxoL3dlEeNe_-XZF48cpGintbHTWEJk3y6-4vStfDHo4bveDYL-m8PX7zznMOBp8qb0rLaBRY6TWpPFPoVzzQPFQ8O1jUKtuVVxKNOM9ibpg-VKZb7kqUHaguQ_xOtegi2k5BzH2NZ48H78cbXCQ4qbqd9ZVtuHYdahPWlMl6SpRrlsLQ_WdgF_Swp1puvf_J-f0S244fg16y4HxDZs2GkLrq-pLrbgytvazXjRgm0X2Ur2zMlvP78N34fU_fx5Yiw7mJd11U9dQLxg3ZWKKTufSDY4VVQXqq1hPVlJ1p2fnLpOrimj9W12KBVV-bIjWUzcoiseVc1IPNTYguEfsaWIyeLXtx-9pkSGkYOyd1A7FOFJd-DDhTyxu7A5nU3tPWDKhkg4STPOJjzNreQaORde3vDIhB3Tht0GReJsKU8icFpHaBPraGvDK4LY6hgSFa-_mBUnwsUogWTFt34ikbQrHimlTGIjmSc8zvIk1kEbnhJABYW-qpBaug4OvFUSERPdNEY-TrrXbdhpACpcTCzFH3Te__fPj-EqwlYMB6P9B3AtIMPluvlzBzarYm4fwmV9Xk3K4pEbcQw-XTSAfwN_I3Cy
openUrl	ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Landslide+Susceptibility+Assessment+via+Imbalanced+Data+Augmentation+with+Tabular+Variational+Autoencoder+and+Quality%E2%80%93Diversity+Post-Selection&rft.jtitle=Applied+sciences&rft.au=Xu%2C+Zhengyang&rft.au=Wang%2C+Shitai&rft.au=Yin%2C+Min&rft.au=Zhang%2C+Xiaoyu&rft.date=2025-11-01&rft.pub=MDPI+AG&rft.issn=2076-3417&rft.eissn=2076-3417&rft.volume=15&rft.issue=22&rft_id=info:doi/10.3390%2Fapp152211965&rft.externalDocID=A865450627
thumbnail_l	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2076-3417&client=summon
thumbnail_m	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2076-3417&client=summon
thumbnail_s	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2076-3417&client=summon