Browse > Article
http://dx.doi.org/10.7780/kjrs.2022.38.6.2.12

Landslide Susceptibility Mapping Using Deep Neural Network and Convolutional Neural Network  

Gong, Sung-Hyun (Department of Geoinformatics, University of Seoul)
Baek, Won-Kyung (Department of Geoinformatics, University of Seoul)
Jung, Hyung-Sup (Department of Geoinformatics, University of Seoul)
Publication Information
Korean Journal of Remote Sensing / v.38, no.6_2, 2022 , pp. 1723-1735 More about this Journal
Abstract
Landslides are one of the most prevalent natural disasters, threating both humans and property. Also landslides can cause damage at the national level, so effective prediction and prevention are essential. Research to produce a landslide susceptibility map with high accuracy is steadily being conducted, and various models have been applied to landslide susceptibility analysis. Pixel-based machine learning models such as frequency ratio models, logistic regression models, ensembles models, and Artificial Neural Networks have been mainly applied. Recent studies have shown that the kernel-based convolutional neural network (CNN) technique is effective and that the spatial characteristics of input data have a significant effect on the accuracy of landslide susceptibility mapping. For this reason, the purpose of this study is to analyze landslide vulnerability using a pixel-based deep neural network model and a patch-based convolutional neural network model. The research area was set up in Gangwon-do, including Inje, Gangneung, and Pyeongchang, where landslides occurred frequently and damaged. Landslide-related factors include slope, curvature, stream power index (SPI), topographic wetness index (TWI), topographic position index (TPI), timber diameter, timber age, lithology, land use, soil depth, soil parent material, lineament density, fault density, normalized difference vegetation index (NDVI) and normalized difference water index (NDWI) were used. Landslide-related factors were built into a spatial database through data preprocessing, and landslide susceptibility map was predicted using deep neural network (DNN) and CNN models. The model and landslide susceptibility map were verified through average precision (AP) and root mean square errors (RMSE), and as a result of the verification, the patch-based CNN model showed 3.4% improved performance compared to the pixel-based DNN model. The results of this study can be used to predict landslides and are expected to serve as a scientific basis for establishing land use policies and landslide management policies.
Keywords
Landslides; Susceptibility map; Deep learning; Deep neural network; Convolutional neural network;
Citations & Related Records
Times Cited By KSCI : 6  (Citation Analysis)
연도 인용수 순위
1 Lee, S., 2019. Current and Future Status of GIS-based Landslide Susceptibility Mapping: A Literature Review, Korean Journal of Remote Sensing, 35(1): 179-193. https://doi.org/10.7780/kjrs.2019.35.1.12   DOI
2 Liu, W., Z. Wang, X. Liu, N. Zeng, Y. Liu, and F.E. Alsaadi, 2017 A survey of deep neural network architectures and their applications, Neurocomputing, 234: 11-26. https://doi.org/10.1016/j.neucom.2016.12.038   DOI
3 Oh, H.J., 2010. Landslide Detection and Landslide Susceptibility Mapping using Aerial Photos and Artificial Neural Networks, Korean Journal of Remote Sensing, 26(1): 47-57. https://doi.org/10.7780/kjrs.2010.26.1.47   DOI
4 Pourghasemi, H.R., Z.T. Yansari, P. Panagos, and B. Pradhan, 2018. Analysis and evaluation of landslide susceptibility: A review on articles published during 2005-2016 (periods of 2005-2012 and 2013-2016), Arabian Journal of Geosciences, 11: 193. http://dx.doi.org/10.1007/s12517-018-3531-5   DOI
5 Ramli, M.F., N. Yusof, M.K. Yusoff, H. Juahir, and H.Z.M. Shafri, 2010. Lineament mapping and its application in landslide hazard assessment: a review, Bulletin of Engineering Geology and the Environment, 69(2): 215-233. https://doi.org/10.1007/s10064-009-0255-5   DOI
6 Lee, S., W.K. Baek, H.S. Jung, and S. Lee, 2020. Susceptibility mapping on urban landslides using deep learning approaches in mt. Umyeon, Applied Sciences, 10(22): 8189. https://doi.org/10.3390/app10228189   DOI
7 Pham, B.T., I. Prakash, S.K. Singh, A. Shirzadi, H. Shahabi, and D.T. Bui, 2019. Landslide susceptibility modeling using Reduced Error Pruning Trees and different ensemble techniques: Hybrid machine learning approaches, Catena, 175: 203-218. https://doi.org/10.1016/j.catena.2018.12.018   DOI
8 Lee, S., M.J. Lee, and H.S. Jung, 2017. Data mining approaches for landslide susceptibility mapping in Umyeonsan, Seoul, South Korea, Applied Sciences, 7: 683. https://doi.org/10.3390/app7070683   DOI
9 Urmi, R.B.R. and D.H. Jang, 2020. Life risk assessment of landslide disaster in Jinbu area using logistic regression model, Journal of The Korean Geomorphological Association, 27(2): 65-85. https://doi.org/10.16968/jkga.27.2.65   DOI
10 Yaa'cob, N., Z.N.A. Abd Rashid, N. Tajudin, and M. Kassim, 2020. Landslide possibilities using remote sensing and geographical information system (GIS), Proc. of 10th IGRSM International Conference and Exhibition on Geospatial & Remote Sensing, Kuala Lumpur, Malaysia, Oct. 20-21, vol. 540, pp. 1-10. https://doi.org/10.1088/1755-1315/540/1/012084   DOI
11 Kincal, C., A. Akgun, and M.Y. Koca, 2009. Landslide susceptibility assessment in the Izmir (West Anatolia, Turkey) city center and its near vicinity by the logistic regression method, Environmental Earth Sciences, 59(4): 745-756. https://doi.org/10.1007/s12665-009-0070-0   DOI
12 Du, S.S., Y. Wang, X. Zhai, S. Balakrishnan, R.R. Salakhutdinov, and A. Singh, 2018. How many samples are needed to estimate a convolutional neural network?, Proc. of the 32nd International Conference on Neural Information Processing Systems, Montreal, QC, Dec. 3, pp. 371-381. https://dl.acm.org/doi/10.5555/3326943.3326978   DOI
13 Gao, B.C., 1996. NDWI-A normalized difference water index for remote sensing of vegetation liquid water from space, Remote Sensing of Environment, 58(3): 257-266. https://doi.org/10.1016/s0034-4257(96)00067-3   DOI
14 Hua, Y., X. Wang, Y. Li, P. Xu, and W. Xia, 2021. Dynamic development of landslide susceptibility based on slope unit and deep neural networks, Landslides, 18(1): 281-302. https://doi.org/10.1007/s10346-020-01444-0   DOI
15 LeCun, Y., Y. Bengio, and G. Hinton, 2015. Deep learning, Nature, 521: 436-444. https://doi.org/10.1038/nature14539   DOI
16 Lee, H.G. and G.H. Kim, 2012. Landslide risk assessment in Inje using logistic regression model, Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography, 30(3): 313-321. https://doi.org/10.7848/ksgpc.2012.30.3.313   DOI
17 Wang, Y., L. Feng, S. Li, F. Ren, and Q. Du, 2020. A hybrid model considering spatial heterogeneity for landslide susceptibility mapping in Zhejiang Province, China, Catena, 188: 104425. https://doi.org/10.1016/j.catena.2019.104425   DOI
18 Cruden, D. and D. Varnes, 1996. Landslide types and processes, Special Report, Transportation Research Board, National Academy of Science, 247: 36-75.
19 Davis, J. and M. Goadrich, 2006. The relationship between Precision-Recall and ROC curves, Proc. of the 23rd International Conference on Machine Learning, Pittsburgh, PA, Jun. 25-29, pp. 233-240. https://doi.org/10.1145/1143844.1143874   DOI
20 Florinsky, I.V., 2012. Digital Terrain Analysis in Soil Science and Geology, Elsevier Press, Amsterdam, Netherland. https://doi.org/10.1016/b978-0-12-385036-2.00023-7   DOI
21 Lee, S.R., M.J. Lee, and J.S. Won, 2005. Landslide Susceptibility Analysis and Vertification using Artificial Neural Network in the Kangneung Area, Economic and Environmental Geology, 38(1): 33-43. https://doi.org/10.1080/01431160701264227   DOI
22 Shorten, C. and T.M. Khoshgoftaar, 2019. A survey on image data augmentation for deep learning, Journal of Big Data, 6(1): 1-48. https://doi.org/10.1186/s40537-019-0197-0   DOI
23 Tien Bui, D., H. Shahabi, A. Shirzadi, K. Chapi, M. Alizadeh, W. Chen, A. Mohammadi, B.B. Ahmad, M. Panahi, and H. Hong, 2018. Landslide detection and susceptibility mapping by airsar data using support vector machine and index of entropy models in cameron highlands, malaysia, Remote Sensing, 10: 1527. https://doi.org/10.3390/rs10101527   DOI
24 Woo, C.S., C.W. Lee, and Y. Jeong, 2008. Study on application of topographic position index for prediction of the landslide occurrence, Journal of the Korean Society of Environmental Restoration Technology, 11(2): 1-9.
25 Korea Forest Service, 2013. Detailed strategy for primary policy, Korea Forest Service, Seoul, Republic of Korea, pp. 12-16 (in Korean).
26 Froude, M.J. and D.N. Petley, 2018. Global fatal landslide occurrence from 2004 to 2016, Natural Hazards and Earth System Sciences, 18(8): 2161-2181. https://doi.org/10.5194/nhess-18-2161-2018   DOI
27 Gariano, S.L. and F. Guzzetti, 2016. Landslides in a changing climate, Earth-Science Reviews, 162: 227-252. https://doi.org/10.1016/j.earscirev.2016.08.011   DOI
28 Ghorbanzadeh, O., T. Blaschke, K. Gholamnia, S.R. Meena, D. Tiede, and J. Aryal, 2019. Evaluation of different machine learning methods and deep-learning convolutional neural networks for landslide detection, Remote Sensing, 11: 196. https://doi.org/10.3390/rs11020196   DOI
29 Jones, H.G., 1983. Estimation of an effective soil water potential at the root surface of transpiring plants, Plant, Cell & Environment, 6(8): 671-674. https://doi.org/10.1111/1365-3040.ep11589241   DOI
30 Kim, J.H. and W.Y. Kim, 2013. Review of research trends on landslide hazards, The Journal of Engineering Geology, 23(3): 305-314 (in Korean with English abstract). https://doi.org/10.9720/kseg.2013.3.305   DOI
31 Lee, S. and H.J. Oh, 2019. Landslide susceptibility prediction using evidential belief function, weight of evidence and artificial neural network models, Korean Journal of Remote Sensing, 35(2): 299-316. https://doi.org/10.7780/kjrs.2019.35.2.9   DOI
32 Lee, S., M. Lee, and J. Won, 2004. Study on landslide using GIS and remote sensing at the Kangneung area (II) - landslide susceptibility mapping and cross-validation using the probability technique, Journal of Korean Society of Economic and Environmental Geology, 37(5): 521-532
33 Lee, S. and M.J. Lee, 2017. Susceptibility mapping of Umyeonsan using logistic regression (LR) model and post-validation through field investigation, Korean Journal of Remote Sensing, 33(6-2): 1047-1060. https://doi.org/10.7780/kjrs.2017.33.6.2.2   DOI