Restricted accessResearch articleFirst published online 2025-12
Research on the evaluation of landslide susceptibility based on the integration of endogenic and exogenic driving forces: A case study of Diqing Tibetan Autonomous Prefecture in the Hengduan Mountains
The Hengduan Mountains (HMs), located on the southeastern edge of the Tibetan Plateau, are marked by complex terrain and frequent natural hazards. Accurate delineation of landslide susceptibility zones in this region is essential for enhancing local safety. This research centers on the Diqing Tibetan Autonomous Prefecture (DTAP), the core area of the HMs, and analyzes landslide susceptibility influenced by both endogenic and exogenic factors. Nineteen conditioning factors were selected, including two novel indicators of endogenic forces: distance from hot springs and gravitational acceleration. A Random Forest (RF) model combined with Shapley Additive Explanations (SHAP) was used to assess susceptibility. The RF-SHAP model achieved an accuracy of 93.65%. Notably, gravitational acceleration and distance from hot springs ranked second and ninth, respectively, in SHAP-based importance. These findings demonstrate the model’s effectiveness for landslide susceptibility mapping in tectonically active regions and offer practical insights for disaster prevention and mitigation.
AjinRSSahaSSahaA, et al. (2022) Enhancing the accuracy of the REPTree by integrating the hybrid ensemble meta-classifiers for modelling the landslide susceptibility of Idukki district, South-Western India. Journal of the Indian Society of Remote Sensing50(11): 2245–2265.
2.
AjinRSSegoniSFantiR (2024) Optimization of SVR and CatBoost models using metaheuristic algorithms to assess landslide susceptibility. Scientific Reports14(1): 24851.
3.
AliNChenJFuX, et al. (2024) Integrating machine learning ensembles for landslide susceptibility mapping in Northern Pakistan. Remote Sensing16(6): 988.
4.
BelgiuMDrăguţL (2016) Random forest in remote sensing: a review of applications and future directions. ISPRS Journal of Photogrammetry and Remote Sensing114: 24–31.
5.
BiauGScornetE (2016) A random forest guided tour. TEST25(2): 197–227.
6.
BienTXIqbalMJamalA, et al. (2023) Integration of rotation forest and multiboost ensemble methods with forest by penalizing attributes for spatial prediction of landslide susceptible areas. Stochastic Environmental Research and Risk Assessment37(12): 4641–4660.
7.
BingliHLijunSChongleiZ, et al. (2024) Mobility characteristics of rainfall-triggered shallow landslides in a forest area in Mengdong, China. Landslides21(9): 2101–2117.
8.
BrabbEE (1985) Innovative approaches to landslide hazard and risk mapping. Proceedings of the IVth International Conference and Field Workshop in Landslides, Tokyo, Japan24(1): A16.
ChenC-WIidaTYamadaR (2017) Effects of active fault types on earthquake-induced deep-seated landslides: a study of historical cases in Japan. Geomorphology295: 680–689.
11.
ChenWPengJHongH, et al. (2018) Landslide susceptibility modelling using GIS-based machine learning techniques for Chongren County, Jiangxi Province, China. Science of the Total Environment626: 1121–1135.
12.
ChenC-WSatoMYamadaR, et al. (2022) Modeling of earthquake-induced landslide distributions based on the active fault parameters. Engineering Geology303: 106640.
13.
CuiPChenX-QZhuY-Y, et al. (2011) The Wenchuan earthquake (May 12, 2008), Sichuan Province, China, and resulting geohazards. Natural Hazards56(1): 19–36.
14.
DaiFCXuCYaoX, et al. (2011) Spatial distribution of landslides triggered by the 2008 Ms 8.0 Wenchuan earthquake, China. Journal of Asian Earth Sciences40(4): 883–895.
15.
DelgadoJGarridoJLópez-CasadoC, et al. (2011) On far field occurrence of seismically induced landslides. Engineering Geology123(3): 204–213.
16.
DengHWuXZhangW, et al. (2022) Slope-Unit scale landslide susceptibility mapping based on the random forest model in deep valley areas. Remote Sensing14(17): 4245.
17.
DewantoBGPriadiRHelianiLS, et al. (2022) The 2022 Mw 6.1 pasaman barat, Indonesia earthquake, confirmed the existence of the Talamau segment fault based on teleseismic and satellite gravity data. Quaternary5(4): 45.
18.
DubeySSattarAGoyalMK, et al. (2023) Mass movement hazard and exposure in the Himalaya. Earth’s Future11(9): e2022EF003253.
19.
EllisAJMahonWAJ (1964) Natural hydrothermal systems and experimental hot-water/rock interactions. Geochimica et Cosmochimica Acta28(8): 1323–1357.
20.
FanLLehmannPOrD (2016) Effects of soil spatial variability at the hillslope and catchment scales on characteristics of rainfall-induced landslides. Water Resources Research52(3): 1781–1799.
21.
GorokhovichYVustianiukA (2021) Implications of slope aspect for landslide risk assessment: a case study of Hurricane Maria in Puerto Rico in 2017. Geomorphology391: 107874.
22.
GuidottiRMonrealeARuggieriS, et al. (2019) A survey of methods for explaining black box models. ACM Computing Surveys51(5): 1–42.
23.
GuoDHamadaM (2013) Qualitative and quantitative analysis on landslide influential factors during Wenchuan earthquake: a case study in Wenchuan County. Engineering Geology152(1): 202–209.
24.
GuptaKSatyamN (2024) Optimizing seismic hazard inputs for co-seismic landslide susceptibility mapping: a probabilistic analysis. Natural Hazards120(9): 8459–8481.
25.
HabumugishaJMChenNRahmanM, et al. (2022) Landslide susceptibility mapping with deep learning algorithms. Sustainability14(3): 1734.
26.
Hammad KhaliqABasharatMTalhaRM, et al. (2023) Spatiotemporal landslide susceptibility mapping using machine learning models: a case study from district Hattian Bala, NW Himalaya, Pakistan. Ain Shams Engineering Journal14(3): 101907.
27.
HarrisonJWLuciusMAFarrellJL, et al. (2021) Prediction of stream nitrogen and phosphorus concentrations from high-frequency sensors using random forests regression. Science of the Total Environment763: 143005.
28.
HirtCClaessensSFecherT, et al. (2013) New ultrahigh-resolution picture of Earth’s gravity field. Geophysical Research Letters40(16): 4279–4283.
29.
HongHPourghasemiHRPourtaghiZS (2016) Landslide susceptibility assessment in Lianhua County (China): a comparison between a random forest data mining technique and bivariate and multivariate statistical models. Geomorphology259: 105–118.
30.
HuXShenYHuK, et al. (2024) Quantifying the impact of earthquakes and geological factors on spatial heterogeneity of debris-flow prone areas: a case study in the Hengduan Mountains. Journal of Mountain Science21(5): 1522–1533.
31.
HuangFChenJDuZ, et al. (2020) Landslide susceptibility prediction considering regional soil erosion based on machine-learning models. ISPRS International Journal of Geo-Information9(6): 377.
32.
HuangZPengLLiS, et al. (2023) GIS-based landslide susceptibility mapping in the Longmen Mountain area (China) using three different machine learning algorithms and their comparison. Environmental Science and Pollution Research International30(38): 88612–88626.
33.
JiangGHuSShiY, et al. (2019) Terrestrial heat flow of continental China: updated dataset and tectonic implications. Tectonophysics753: 36–48.
34.
JiaoYZhaoDDingY, et al. (2019) Performance evaluation for four GIS-based models purposed to predict and map landslide susceptibility: a case study at a World Heritage site in Southwest China. Catena183: 104221.
35.
JoshiLMKotliaBSKothyariGC, et al. (2021) Neotectonic landform development and associated mass movements along Eastern Ramganga Valley in the Kumaun Himalaya, India. Geotectonics55(4): 543–562.
36.
KexinZGuocanWYadongX, et al. (2013) Sedimentary evolution of the Qinghai–Tibet plateau in cenozoic and its response to the uplift of the plateau. Acta Geologica Sinica - English Edition87(2): 555–575.
37.
KohnoMHiguchiY (2023) Landslide susceptibility assessment in the Japanese Archipelago based on a landslide distribution map. ISPRS International Journal of Geo-Information12(2): 37.
38.
KulsoomIHuaWHussainS, et al. (2023) SBAS-InSAR based validated landslide susceptibility mapping along the karakoram highway: a case study of Gilgit-Baltistan, Pakistan. Scientific Reports13(1): 3344.
39.
LeeS-ICelikSLogsdonBA, et al. (2018) A machine learning approach to integrate big data for precision medicine in acute myeloid leukemia. Nature Communications9(1): 42.
40.
LeirMEngPGeoP, et al. (n.d.) Regional Landslide Hazard Susceptibility Mapping for Pipelines in British Columbia. Richmond, BC, Canada: Canadian Geotechnical Society.
41.
LiJWangWChenG, et al. (2023) Secondary-factor division optimization based on ET-GA to improve the accuracy of LSA obtained using SSA-DBN compared to the original division method: a case study in southern Sichuan, China. Bulletin of Engineering Geology and the Environment82(8): 325.
42.
LiAZhangZHongZ, et al. (2024) Spatial suitability evaluation based on multisource data and random forest algorithm: a case study of Yulin, China. Frontiers in Environmental Science12: 1338931.
43.
LiuQZhangBTangA (2023) Landslide risk of regional roads: consider the road mileage of expected losses. Transportation Research Part D: Transport and Environment120: 103771.
44.
LiuBGuoHLiJ, et al. (2024) Application and interpretability of ensemble learning for landslide susceptibility mapping along the Three Gorges Reservoir area, China. Natural Hazards120(5): 4601–4632.
45.
LiuXShaoSShaoS (2024) Landslide susceptibility prediction and mapping in Loess Plateau based on different machine learning algorithms by hybrid factors screening: case study of Xunyi County, Shaanxi Province, China. Advances in Space Research74(1): 192–210.
46.
LundbergSMLeeS-I (2017) A unified approach to interpreting model predictions. In:Advances in Neural Informaltion Processing Systems 30 (eds GuyonILuxburgUVWallachHFergusRVishwanathanSGarnettR), California, 4–9 December2017, pp. 4765–4774. New York: Curran Associates, inc.
47.
LundbergSMNairBVavilalaMS, et al. (2018) Explainable machine-learning predictions for the prevention of hypoxaemia during surgery. Nature Biomedical Engineering2(10): 749–760.
48.
MoosaviVNiaziY (2016) Development of hybrid wavelet packet-statistical models (WP-SM) for landslide susceptibility mapping. Landslides13(1): 97–114.
49.
PanGWangLLiR, et al. (2012) Tectonic evolution of the Qinghai-Tibet plateau. Journal of Asian Earth Sciences53: 3–14.
50.
PhamQBEkmekcioğluÖAliSA, et al. (2023) Examining the role of class imbalance handling strategies in predicting earthquake-induced landslide-prone regions. Applied Soft Computing143: 110429.
51.
PradhanBDikshitALeeS, et al. (2023) An explainable AI (XAI) model for landslide susceptibility modeling. Applied Soft Computing142: 110324.
52.
QiuHXuYTangB, et al. (2024) Interpretable landslide susceptibility evaluation based on model optimization. Land13(5): 639.
53.
RenSZhangYLiJ, et al. (2023) A new type of sliding zone soil and its severe effect on the formation of giant landslides in the Jinsha River tectonic suture zone, China. Natural Hazards117(2): 1847–1868.
54.
SameenMIPradhanBLeeS (2020) Application of convolutional neural networks featuring Bayesian optimization for landslide susceptibility assessment. Catena186: 104249.
55.
SegoniSAjinRSNocentiniN, et al. (2024) Insights gained from the review of landslide susceptibility assessment studies in Italy. Remote Sensing16(23): 4491.
56.
SerikovaSPokrovskyOSLaudonH, et al. (2019) High carbon emissions from thermokarst lakes of Western Siberia. Nature Communications10(1): 1552.
57.
SunDWenHWangD, et al. (2020) A random forest model of landslide susceptibility mapping based on hyperparameter optimization using Bayes algorithm. Geomorphology362: 107201.
58.
SunXChenJHanX, et al. (2020) Landslide susceptibility mapping along the upper Jinsha River, south-western China: a comparison of hydrological and curvature watershed methods for slope unit classification. Bulletin of Engineering Geology and the Environment79(9): 4657–4670.
59.
SunDWuXWenH, et al. (2023) A LightGBM-based landslide susceptibility model considering the uncertainty of non-landslide samples. Geomatics, Natural Hazards and Risk14(1): 2213807.
60.
TaloorAKKothyariGCDumkaRK, et al. (2023) Crustal deformation study of Kashmir basin: insights from PSInSAR based time series analysis. Journal of Applied Geophysics211: 104979.
61.
TaloorAKAbrahamAParsadG (2024) Landslide susceptibility modelling in the Doda Kishtwar Ramban (DKR) region of Jammu and Kashmir using remote sensing and geographic information system. Quaternary Science Advances14: 100189.
62.
TangXZhangJPangZ, et al. (2017) The eastern Tibetan Plateau geothermal belt, western China: geology, geophysics, genesis, and hydrothermal system. Tectonophysics717: 433–448.
63.
TanyaşHLombardoL (2019) Variation in landslide-affected area under the control of ground motion and topography. Engineering Geology260: 105229.
64.
TapponnierPPeltzerGArmijoR (1986) On the mechanics of the collision between India and Asia. Geological Society, London, Special Publications19(1): 113–157.
65.
TrinhTLuuBTNguyenDH, et al. (2023) A study of non-landslide samples and weights for mapping landslide susceptibility using regression and clustering methods. Earth Science Informatics16(4): 4009–4034.
66.
VelayudhamJKannaujiyaSSarkarT, et al. (2021) Comprehensive study on evaluation of Kaliasaur Landslide attributes in Garhwal Himalaya by the execution of geospatial, geotechnical and geophysical methods. Quaternary Science Advances3: 100025.
67.
WangXNieGWangD (2010) Relationships between ground motion parameters and landslides induced by Wenchuan earthquake. Earthquake Science23(3): 233–242.
68.
WangYSunDWenH, et al. (2020) Comparison of random forest model and frequency ratio model for landslide susceptibility mapping (LSM) in Yunyang county (Chongqing, China). International Journal of Environmental Research and Public Health17(12): 4206.
69.
WuWZhangQSinghVP, et al. (2022) A data-driven model on google Earth engine for landslide susceptibility assessment in the Hengduan mountains, the Qinghai–Tibetan plateau. Remote Sensing14(18): 4662.
70.
XuX-ZLiuZ-YXiaoP-Q, et al. (2015) Gravity erosion on the steep loess slope: behavior, trigger and sensitivity. Catena135: 231–239.
71.
YangFWangGHuD, et al. (2022) Influence of water-rock interaction on permeability and heat conductivity of granite under high temperature and pressure conditions. Geothermics100: 102347.
72.
YiDYiLYangZ, et al. (2024) Coupled thermo-hydro-mechanical-phase field modelling for hydraulic fracturing in thermo-poroelastic media. Computers and Geotechnics166: 105949.
73.
YuHPeiWZhangJ, et al. (2023) Landslide susceptibility mapping and driving mechanisms in a Vulnerable region based on multiple machine learning models. Remote Sensing15(7): 1886.
74.
ZengTWuLPedutoD, et al. (2023) Ensemble learning framework for landslide susceptibility mapping: different basic classifier and ensemble strategy. Geoscience Frontiers14(6): 101645.
75.
ZhangJMaXZhangJ, et al. (2023) Insights into geospatial heterogeneity of landslide susceptibility based on the SHAP-XGBoost model. Journal of Environmental Management332: 117357.
76.
ZhaoBDaiQZhuoL, et al. (2021) Assessing the potential of different satellite soil moisture products in landslide hazard assessment. Remote Sensing of Environment264: 112583.
77.
ZhaoBDaiQZhuoL, et al. (2022) Accounting for satellite rainfall uncertainty in rainfall-triggered landslide forecasting. Geomorphology398: 108051.
78.
ZhaoJZhangQWangD, et al. (2022) Machine learning-based evaluation of susceptibility to geological hazards in the Hengduan mountains region, China. International Journal of Disaster Risk Science13(2): 305–316.
79.
ZhaoLMaHDongJ, et al. (2023) A Comparative study of landslide susceptibility mapping using bagging PU learning in class-prior probability shift datasets. Remote Sensing15(23): 5547.
80.
ZhiyongFChangdongLWenminY (2023) Landslide susceptibility assessment through TrAdaBoost transfer learning models using two landslide inventories. Catena222: 106799.
81.
ZhouSSunQZhangH, et al. (2023) Elemental dissolution characteristics of granite and gabbro under high-temperature water-rock interactions. Science of the Total Environment897: 165455.
Supplementary Material
Please find the following supplemental material available below.
For Open Access articles published under a Creative Commons License, all supplemental material carries the same license as the article it is associated with.
For non-Open Access articles published, all supplemental material carries a non-exclusive license, and permission requests for re-use of supplemental material or any part of supplemental material shall be sent directly to the copyright owner as specified in the copyright notice associated with the article.
