A Heterogeneous Sampling Strategy to Model Earthquake-Triggered Landslides

Abstract

Regional modeling of landslide hazards is an essential tool for the assessment and management of risk in mountain environments. Previous studies that have focused on modeling earthquake-triggered landslides report high prediction accuracies. However, it is common to use a validation strategy with an equal number of landslide and non-landslide samples, scattered homogeneously across the study area. Consequently, there are overestimations in the epicenter area, and the spatial pattern of modeled locations does not agree well with real events. In order to improve landslide hazard mapping, we proposed a spatially heterogeneous non-landslide sampling strategy by considering local ratios of landslide to non-landslide area. Coseismic landslides triggered by the 2008 Wenchuan Earthquake on the eastern Tibetan Plateau were used as an example. To assess the performance of the new strategy, we trained two random forest models that shared the same hyperparameters. The first was trained using samples from the new heterogeneous strategy, and the second used the traditional approach. In each case the spatial match between modeled and measured (interpreted) landslides was examined by scatterplot, with a 2 km-by-2 km fishnet. Although the traditional approach achieved higher AUC_ROC (0.95) accuracy than the proposed one (0.85), the coefficient of determination (R²) for the new strategy (0.88) was much higher than for the traditional strategy (0.55). Our results indicate that the proposed strategy outperforms the traditional one when comparing against landslide inventory data. Our work demonstrates that higher prediction accuracies in landslide hazard modeling may be deceptive, and validation of the modeled spatial pattern should be prioritized. The proposed method may also be used to improve the mapping of precipitation-induced landslides. Application of the proposed strategy could benefit precise assessment of landslide risks in mountain environments.

Keywords

Earthquake-triggered landslides / Landslide hazard modeling / Machine learning / Model validation / Sampling strategy / Tibetan Plateau

References

[1] Allstadt KE, Jibson RW, Thompson EM, Massey CI, Wald DJ, Godt JW, Rengers FK. Improving near-real-time coseismic landslide models: Lessons learned from the 2016 Kaikōura, New Zealand, Earthquake. Bulletin of the Seismological Society of America, 2018, 108(3B): 1649-1664

[2] Breiman L. Random forests. Machine Learning, 2001, 45: 5-32

[3] Bui DT, Tsangaratos P, Nguyen VT, Liem NV, Trinh PT. Comparing the prediction performance of a deep learning neural network model with conventional machine learning models in landslide susceptibility assessment. CATENA, 2020, 188: 104426

[4] Cao, Z. 2014. Study on optimization of random forests algorithm. Ph.D. dissertation. Capital University of Economics and Business, Beijing, China (in Chinese).

[5] Catani F, Lagomarsino D, Segoni S, Tofani V. Landslide susceptibility estimation by random forests technique: Sensitivity and scaling issues. Natural Hazards and Earth System Sciences, 2013, 13(11): 2815-2831

[6] Chen W, Zhang S, Li R, Shahabi H. Performance evaluation of the GIS-based data mining techniques of best-first decision tree, random forest, and naïve Bayes tree for landslide susceptibility modeling. Science of the Total Environment, 2018, 644: 1006-1018

[7] Cheng Y, Yu TT, Son NT. Random forests for landslide prediction in Tsengwen river watershed central Taiwan. Remote Sensing, 2021, 13(2): 199

[8] Cui P, Lin Y, Chen C. Destruction of vegetation due to geo-hazards and its environmental impacts in the Wenchuan earthquake areas. Ecological Engineering, 2012, 44: 61-69

[9] Emberson R, Hovius N, Galy A, Marc O. Chemical weathering in active mountain belts controlled by stochastic bedrock landsliding. Nature Geoscience, 2016, 9(1): 42-45

[10] Fell R, Corominas J, Bonnard C, Cascini L, Leroi E, Savage WZ. Guidelines for landslide susceptibility, hazard and risk zoning for land use planning. Engineering Geology, 2008, 102(3–4): 85-98

[11] Ham J, Chen Y, Crawford MM, Ghosh J. Investigation of the random forest framework for classification of hyperspectral data. IEEE Transactions on Geoscience and Remote Sensing, 2005, 43(3): 492-501

[12] He X. Multivariate statistical analysis, 2008, Beijing: People’s University of China Press

[13] He Q, Wang M, Liu K. Rapidly assessing earthquake-induced landslide susceptibility on a global scale using random forest. Geomorphology, 2021, 391: 107889

[14] Hong H, Tsangaratos P, Ilia I, Chen W, Xu C. Mikos M, Tiwari B, Yin Y, Sassa K. Comparing the performance of a Logistic Regression and a Random Forest Model in landslide susceptibility assessments The case of Wuyaun Area, China. Advancing culture of living with landslides, 2017, Cham, Switzerland: Springer 1043-1050.

[15] Hu W, Huang R, McSaveney M, Yao L, Xu Q, Feng M, Zhang X. Superheated steam, hot CO₂ and dynamic recrystallization from frictional heat jointly lubricated a giant landslide: Field and experimental evidence. Earth and Planetary Science Letters, 2019, 510: 85-93

[16] Huang R, Fan X. The landslide story. Nature Geoscience, 2013, 6(5): 325-326

[17] Jibson RW, Harp EL, Michael JA. A method for producing digital probabilistic seismic landslide hazard maps. Engineering Geology, 2000, 58(3–4): 271-289

[18] Johnston EC, Davenport FV, Wang L, Caers JK, Muthukrishnan S, Burke M, Diffenbaugh NS. Quantifying the effect of precipitation on landslide hazard in urbanized and non-urbanized areas. Geophysical Research Letters, 2021

[19] Jones JN, Boulton SJ, Bennett GL, Stokes M, Whitworth MR. Temporal variations in landslide distributions following extreme events: Implications for landslide susceptibility modeling. Journal of Geophysical Research Earth Surface, 2021

[20] Kirschbaum D, Stanley T, Zhou Y. Spatial and temporal analysis of a global landslide catalog. Geomorphology, 2015, 249: 4-15

[21] Larsen IJ, Montgomery DR. Landslide erosion coupled to tectonics and river incision. Nature Geoscience, 2012, 5(7): 468-473

[22] Liao M, Wen H, Yang L. Identifying the essential conditioning factors of landslide susceptibility models under different grid resolutions using hybrid machine learning: A case of Wushan and Wuxi counties China. Catena, 2022

[23] Liu M, Liu J, Xu S, Zhou T, Ma Y, Zhang F, Konečný M. Landslide susceptibility mapping with the fusion of multi-feature SVM model based FCM sampling strategy: A case study from Shaanxi Province. International Journal of Image and Data Fusion, 2021, 12(4): 349-366

[24] Lombardo L, Bakka H, Tanyas H, van Westen C, Mai PM, Huser R. Geostatistical modeling to capture seismic-shaking patterns from earthquake-induced landslides. Journal of Geophysical Research: Earth Surface, 2019, 124: 1958-1980

[25] Marteau PF. Random partitioning forest for point-wise and collective anomaly detection—Application to network intrusion detection. IEEE Transactions on Information Forensics and Security, 2021, 16: 2157-2172

[26] Micheletti N, Foresti L, Robert S, Leuenberger M, Pedrazzini A, Jaboyedoff M, Kanevski M. Machine learning feature selection methods for landslide susceptibility mapping. Mathematical Geosciences, 2013, 46(1): 33-57

[27] Nowicki Jessee MA, Hamburger MW, Allstadt K, Wald DJ, Robeson SM, Tanyas H, Hearne M, Thompson EM. A global empirical model for near-real-time assessment of seismically induced landslides. Journal of Geophysical Research: Earth Surface, 2018, 123: 1835-1859

[28] Nowicki MA, Wald DJ, Hamburger MW, Hearne M, Thompson EM. Development of a globally applicable model for near real-time prediction of seismically induced landslides. Engineering Geology, 2014, 173: 54-65

[29] Petley D. Global patterns of loss of life from landslides. Geology, 2012, 40(10): 927-930

[30] Pokharel B, Althuwaynee OF, Aydda A, Kim SW, Lim S, Park HJ. Spatial clustering and modelling for landslide susceptibility mapping in the north of the Kathmandu Valley. Nepal. Landslides, 2021, 18(4): 1403-1419

[31] Qi W, Xu C, Xu X. AutoGluon: A revolutionary framework for landslide hazard analysis. Natural Hazards Research, 2021, 1(3): 103-108

[32] Shao X, Ma S, Xu C, Zhou Q. Effects of sampling intensity and non-slide/slide sample ratio on the occurrence probability of coseismic landslides. Geomorphology, 2020

[33] Shu, H., M. Hürlimann, R. Molowny-Horas, M. González, J. Pinyol, C. Abancó, and J. Ma. 2019. Relation between land cover and landslide susceptibility in Val d’Aran, Pyrenees (Spain): Historical aspects, present situation and forward prediction. Science of the Total Environment 693: Article 133557

[34] Tanyas H, Görüm T, Kirschbaum D, Lombardo L. Could road constructions be more hazardous than an earthquake in terms of mass movement?. Natural Hazards, 2022, 112: 639-663

[35] Tanyas H, Rossi M, Alvioli M, van Westen CJ, Marchesini I. A global slope unit-based method for the near real-time prediction of earthquake-induced landslides. Geomorphology, 2019, 327: 126-146

[36] van Westen CJ, Castellanos E, Kuriakose SL. Spatial data for landslide susceptibility, hazard, and vulnerability assessment: An overview. Engineering Geology, 2008, 102: 112-131

[37] van Westen CJ, van Asch TWJ, Soeters R. Landslide hazard and risk zonation—Why is it still so difficult?. Bulletin of Engineering Geology and the Environment, 2006, 65: 167-184

[38] Wang W, He Z, Han Z, Li Y, Dou J, Huang J. Mapping the susceptibility to landslides based on the deep belief network: A case study in Sichuan Province, China. Natural Hazards, 2020, 103: 3239-3261

[39] Xu C, Xu X, Dai F, Saraf AK. Comparison of different models for susceptibility mapping of earthquake triggered landslides related with the 2008 Wenchuan earthquake in China. Computers & Geosciences, 2012, 46: 317-329

[40] Xu C, Xu X, Yao X, Dai F. Three (nearly) complete inventories of landslides triggered by the May 12, 2008 Wenchuan Mw 7.9 earthquake of China and their spatial distribution statistical analysis. Landslides, 2014, 11: 441-461

[41] Yang C, Liu L-L, Huang F, Huang L, Wang X-M. Machine learning-based landslide susceptibility assessment with optimized ratio of landslide to non-landslide samples. Gondwana Research, 2022

[42] Ye T, Huang C, Deng Z. Spatial database of the 1: 2,500,000 digital geologic map of the People’s Republic of China. Geology in China, 2017, 44(S1): 19-24 (in Chinese)

[43] Yin Y, Wang F, Sun P. Landslide hazards triggered by the 2008 Wenchuan earthquake, Sichuan. China. Landslides, 2009, 6(2): 139-152

[44] Youssef AM, Pourghasemi HR, Pourtaghi ZS, Al-Katheeri MM. Landslide susceptibility mapping using random forest, boosted regression tree, classification and regression tree, and general linear models and comparison of their performance at Wadi Tayyah Basin, Asir Region. Saudi Arabia. Landslides, 2015, 13(5): 839-856