Landslide susceptibility mapping (LSM) is an important decision basis for regional landslide hazard risk management, territorial spatial planning and landslide decision making. The current convolutional neural network (CNN)-based landslide susceptibility mapping models do not adequately take into account the spatial nature of texture features, and vision transformer (ViT)-based LSM models have high requirements for the amount of training data. In this study, we overcome the shortcomings of CNN and ViT by fusing these two deep learning models (bottleneck transformer network (BoTNet) and convolutional vision transformer network (ConViT)), and the fused model was used to predict the probability of landslide occurrence. First, we integrated historical landslide data and landslide evaluation factors and analysed whether there was covariance in the landslide evaluation factors. Then, the testing accuracy and generalisation ability of the CNN, ViT, BoTNet and ConViT models were compared and analysed. Finally, four landslide susceptibility mapping models were used to predict the probability of landslide occurrence in Pingwu County, Sichuan Province, China. Among them, BoTNet and ConViT had the highest accuracy, both at 87.78%, an improvement of 1.11% compared to a single model, while ConViT had the highest F1-socre at 87.64%, an improvement of 1.28% compared to a single model. The results indicate that the fusion model of CNN and ViT has better LSM performance than the single model. Meanwhile, the evaluation results of this study can be used as one of the basic tools for landslide hazard risk quantification and disaster prevention in Pingwu County.

Chinese Academy of Surveying and Mapping Beijing 100036 China

Faculty of Geosciences and Environmental Engineering Southwest Jiaotong University Chengdu 610031 China

Laboratory on Geoinformatics and Cartography Department of Geography Masaryk University 61137 Brno Czech Republic

School of Geomatics Liaoning Technical University Fuxin 123000 China

See more in PubMed

Sun Q., Zhang L., Ding X., Hu J., Liang H. Investigation of Slow-Moving Landslides from ALOS/PALSAR Images with TCPInSAR: A Case Study of Oso, USA. Remote Sens. 2014;7:72–88. doi: 10.3390/rs70100072. DOI

Fell R. Landslide risk assessment and acceptable risk. Can. Geotech. J. 1994;31:261–272. doi: 10.1139/t94-031. DOI

Shahabi H., Hashim M. Landslide susceptibility mapping using GIS-based statistical models and Remote sensing data in tropical environment. Sci. Rep. 2015;5:9899. doi: 10.1038/srep09899. PubMed DOI PMC

Dubey C.S., Chaudhry M., Sharma B.K., Pandey A.C., Singh B. Visualization of 3-D digital elevation model for landslide assessment and prediction in mountainous terrain: A case study of Chandmari landslide, Sikkim, eastern Himalayas. Geosci. J. 2005;9:363–373. doi: 10.1007/BF02910325. DOI

Bai S.B., Wang J., Lü G.N., Zhou P.G., Hou S.S., Xu S.N. GIS-based logistic regression for landslide susceptibility mapping of the Zhongxian segment in the Three Gorges area, China. Geomorphology. 2010;115:23–31. doi: 10.1016/j.geomorph.2009.09.025. DOI

Gantimurova S., Parshin A., Erofeev V. GIS-Based Landslide Susceptibility Mapping of the Circum-Baikal Railway in Russia Using UAV Data. Remote Sens. 2021;13:3629. doi: 10.3390/rs13183629. DOI

Zêzere J.L., Pereira S., Melo R., Oliveira S.C., Garcia R. Mapping landslide susceptibility using data-driven methods. Sci. Total Environ. 2017;589:250–267. doi: 10.1016/j.scitotenv.2017.02.188. PubMed DOI

Sezer E.A., Nefeslioglu H.A., Osna T. An expert-based landslide susceptibility mapping (LSM) module developed for Netcad Architect Software. Comput. Geosci. 2016;98:26–37. doi: 10.1016/j.cageo.2016.10.001. DOI

Chen W., Li W., Hou E., Zhao Z., Deng N., Bai H., Wang D. Landslide susceptibility mapping based on GIS and information value model for the Chencang District of Baoji, China. Arab. J. Geosci. 2014;7:4499–4511. doi: 10.1007/s12517-014-1369-z. DOI

Ali S.A., Parvin F., Vojteková J., Costache R., Linh N.T.T., Pham Q.B., Vojtek M., Gigović L., Ahmad A., Ghorbani M.A. GIS-based landslide susceptibility modeling: A comparison between fuzzy multi-criteria and machine learning algorithms. Geosci. Front. 2021;12:857–876. doi: 10.1016/j.gsf.2020.09.004. DOI

Goetz J.N., Brenning A., Petschko H., Leopold P. Evaluating machine learning and statistical prediction techniques for landslide susceptibility modeling. Comput. Geosci. 2015;81:1–11. doi: 10.1016/j.cageo.2015.04.007. DOI

Ngo P., Panahi M., Khosravi K., Ghorbanzadeh O., Kariminejad N., Cerda A., Lee S. Evaluation of deep learning algorithms for national scale landslide susceptibility mapping of Iran. Geosci. Front. 2021;12:505–519.

Hw A., Lz A., Hl A., Jian H.A., Rwmc B. AI-powered Landslide Susceptibility Assessment in Hong Kong. Eng. Geol. 2021;288:106103.

Lombardo L., Cama M., Conoscenti C., Märker M., Rotigliano E. Binary logistic regression versus stochastic gradient boosted decision trees in assessing landslide susceptibility for multiple-occurring landslide events: Application to the 2009 storm event in Messina (Sicily, southern Italy) Nat. Hazards. 2015;79:1621–1648. doi: 10.1007/s11069-015-1915-3. DOI

Youssef A.M., Pourghasemi H.R., Pourtaghi Z.S., Al-Katheeri M.M. 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. 2016;13:839–856. doi: 10.1007/s10346-015-0614-1. DOI

Chen W., Chai H., Zhao Z., Wang Q., Hong H. Landslide susceptibility mapping based on GIS and support vector machine models for the Qianyang County, China. Environ. Earth Sci. 2016;75:474. doi: 10.1007/s12665-015-5093-0. DOI

Yao X., Tham L.G., Dai F.C. Landslide susceptibility mapping based on Support Vector Machine: A case study on natural slopes of Hong Kong, China. Geomorphology. 2008;101:572–582. doi: 10.1016/j.geomorph.2008.02.011. DOI

Chauhan S., Sharma M., Arora M.K. Landslide susceptibility zonation of the Chamoli region, Garhwal Himalayas, using logistic regression model. Landslides. 2010;7:411–423. doi: 10.1007/s10346-010-0202-3. DOI

Chu M., Thuerey N. Data-Driven Synthesis of Smoke Flows with CNN-based Feature Descriptors. ACM Trans. Graph. 2017;36:1–14. doi: 10.1145/3092818. DOI

Othman A.A., Gloaguen R., Andreani L., Rahnama M. Improving landslide susceptibility mapping using morphometric features in the Mawat area, Kurdistan Region, NE Iraq: Comparison of different statistical models. Geomorphology. 2018;319:147–160. doi: 10.1016/j.geomorph.2018.07.018. DOI

Wang Y., Fang Z., Wang M., Ling P., Hong H. Comparative study of landslide susceptibility mapping with different recurrent neural networks. Comput. Geosci. 2020;138:104445. doi: 10.1016/j.cageo.2020.104445. DOI

Wang H.J., Xiao T., Li X.Y., Zhang L.L., Zhang L.M. A novel physically-based model for updating landslide susceptibility. Eng. Geol. 2019;251:71–80. doi: 10.1016/j.enggeo.2019.02.004. DOI

Lei Y., Chen X., Min M., Xie Y. A Semi-Supervised Laplacian Extreme Learning Machine and Feature Fusion with CNN for Industrial Superheat Identification. Neurocomputing. 2020;381:186–195. doi: 10.1016/j.neucom.2019.11.012. DOI

Chen Y., Ming D., Xiao L., Lv X., Zhou C. Landslide Susceptibility Mapping Using Feature Fusion-Based CPCNN-ML in Lantau Island, Hong Kong. IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens. 2021;14:3625–3639. doi: 10.1109/JSTARS.2021.3066378. DOI

Azarafza M., Akgün H., Atkinson P.M., Derakhshani R. Deep learning-based landslide susceptibility mapping. Sci. Rep. 2021;11:24112. doi: 10.1038/s41598-021-03585-1. PubMed DOI PMC

Yu Y., Liang S., Samali B., Nguyen T.N., Zhai C., Li J., Xie X. Torsional capacity evaluation of RC beams using an improved bird swarm algorithm optimised 2D convolutional neural network. Eng. Struct. 2022;273:115066. doi: 10.1016/j.engstruct.2022.115066. DOI

Yu Y., Samali B., Rashidi M., Mohammadi M., Nguyen T.N., Zhang G. Vision-based concrete crack detection using a hybrid framework considering noise effect. J. Build. Eng. 2022;61:105246. doi: 10.1016/j.jobe.2022.105246. DOI

Vaswani A., Shazeer N., Parmar N., Uszkoreit J., Jones L., Gomez A.N., Kaiser L., Polosukhin I. Attention Is All You Need. arXiv. 2017 doi: 10.48550/arXiv.1706.03762. DOI

Park N., Kim S. How Do Vision Transformers Work? arXiv. 20222202.06709

Cheng E., Li G., Chen H. On the direction of the maximum compressive principal stress before and after the 1976 Songpan-Pingwu earthquake (M = 7.2) of the Sichuan province. Acta Seismol. Sin. 1982;4:137–148.

Piloyan A., Konečný M. Semi-automated classification of landform elements in Armenia based on SRTM DEM using k-means unsupervised classification. Quaest. Geogr. 2017;36:93–103. doi: 10.1515/quageo-2017-0007. DOI

Huang Y., Zhao L. Review on landslide susceptibility mapping using support vector machines. Catena. 2018;165:520–529. doi: 10.1016/j.catena.2018.03.003. DOI

Gaidzik K., Ramirez-Herrera M.T. The importance of input data on landslide susceptibility mapping. Sci. Rep. 2021;11:19334. doi: 10.1038/s41598-021-98830-y. PubMed DOI PMC

Zhang X., Liu L., Wu C., Chen X., Zhang B. Development of a global 30 m impervious surface map using multisource and multitemporal remote sensing datasets with the Google Earth Engine platform. Earth Syst. Sci. Data. 2020;12:1625–1648. doi: 10.5194/essd-12-1625-2020. DOI

Zhang X., Liu L., Chen X., Gao Y., Mi J. GLC_FCS30: Global land-cover product with fine classification system at 30 m using time-series Landsat imagery. Earth Syst. Sci. Data. 2020;13:2753–2776. doi: 10.5194/essd-13-2753-2021. DOI

He K., Zhang X., Ren S., Sun J. Deep Residual Learning for Image Recognition; Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition; Las Vegas, NV, USA. 27–30 June 2016; pp. 770–778.

Wang G., Yu H., Sui Y. Research on Maize Disease Recognition Method Based on Improved ResNet50. Mob. Inf. Syst. 2021;2021:9110866. doi: 10.1155/2021/9110866. DOI

Dosovitskiy A., Beyer L., Kolesnikov A., Weissenborn D., Houlsby N. An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. arXiv. 20202010.11929

Jiang Z., Wang L., Wu Q., Shao Y., Shen M., Jiang W., Dai C. Computer-aided diagnosis of retinopathy based on vision transformer. J. Innov. Opt. Health Sci. 2022;15:2250009. doi: 10.1142/S1793545822500092. DOI

Peter S., Jakob U., Ashish V. Self-Attention with Relative Position Representations. arXiv. 20181803.02155

Tian C., Xu Y., Li Z., Zuo W., Fei L., Liu H. Attention-guided CNN for image denoising. Neural Netw. 2020;124:117–129. doi: 10.1016/j.neunet.2019.12.024. PubMed DOI

Srinivas A., Lin T.-Y., Parmar N., Shlens J., Abbeel P., Vaswani A. Bottleneck Transformers for Visual Recognition. arXiv. 20212101.11605

D’Ascoli S., Touvron H., Leavitt M.L., Morcos A.S., Biroli G., Sagun L. ConViT: Improving Vision Transformers with Soft Convolutional Inductive Biases. arXiv. 2021 doi: 10.1088/1742-5468/ac9830.2103.10697 DOI

Wang J., Li X., Christakos G., Liao Y.L., Zhang T., Gu X., Zheng X. Geographical Detectors-Based Health Risk Assessment and its Application in the Neural Tube Defects Study of the Heshun Region, China. Int. J. Geogr. Inf. Sci. 2010;24:107–127. doi: 10.1080/13658810802443457. DOI

Zhou X., Wen H., Zhang Y., Xu J., Zhang W. Landslide susceptibility mapping using hybrid random forest with GeoDetector and RFE for factor optimization. Geosci. Front. 2021;12:101211. doi: 10.1016/j.gsf.2021.101211. DOI

Du J., Glade T., Woldai T., Chai B., Zeng B. Landslide susceptibility assessment based on an incomplete landslide inventory in the Jilong Valley, Tibet, Chinese Himalayas. Eng. Geol. 2020;270:105572. doi: 10.1016/j.enggeo.2020.105572. DOI

Raghu M., Unterthiner T., Kornblith S., Zhang C., Dosovitskiy A. Do Vision Transformers See Like Convolutional Neural Networks? Adv. Neural Inf. Process. Syst. 2021;34:12116–12128.

Naseer M., Ranasinghe K., Khan S., Hayat M., Khan F.S., Yang M.-H. Intriguing Properties of Vision Transformers. Adv. Neural Inf. Process. Syst. 2021;34:23296–23308.

Geirhos R., Rubisch P., Michaelis C., Bethge M., Wichmann F.A., Brendel W. ImageNet-trained CNNS are biased towards texture; Increasing shape bias improves accuracy and robustness; Proceedings of the International Conference on Learning Representations; New Orleans, LA, USA. 6–9 May 2019.

Wang H., Wu X., Huang Z., Xing E.P. High-frequency Component Helps Explain the Generalization of Convolutional Neural Networks. arXiv. 20201905.13545