, Volume 17, Issue 1, pp 217–229 | Cite as

A deep learning algorithm using a fully connected sparse autoencoder neural network for landslide susceptibility prediction

  • Faming Huang
  • Jing Zhang
  • Chuangbing Zhou
  • Yuhao Wang
  • Jinsong Huang
  • Li ZhuEmail author
Technical Note


The environmental factors of landslide susceptibility are generally uncorrelated or non-linearly correlated, resulting in the limited prediction performances of conventional machine learning methods for landslide susceptibility prediction (LSP). Deep learning methods can exploit low-level features and high-level representations of information from environmental factors. In this paper, a novel deep learning–based algorithm, the fully connected spare autoencoder (FC-SAE), is proposed for LSP. The FC-SAE consists of four steps: raw feature dropout in input layers, a sparse feature encoder in hidden layers, sparse feature extraction in output layers, and classification and prediction. The Sinan County of Guizhou Province in China, with a total of 23,195 landslide grid cells (306 recorded landslides) and 23,195 randomly selected non-landslide grid cells, was used as study case. The frequency ratio values of 27 environmental factors were taken as the input variables of FC-SAE. All 46,390 landslide and non-landslide grid cells were randomly divided into a training dataset (70%) and a test dataset (30%). By analyzing real landslide/non-landslide data, the performances of the FC-SAE and two other conventional machine learning methods, support vector machine (SVM) and back-propagation neural network (BPNN), were compared. The results show that the prediction rate and total accuracies of the FC-SAE are 0.854 and 85.2% which are higher than those of the SVM-only (0.827 and 81.56%) and BPNN (0.819 and 80.86%), respectively. In conclusion, the asymmetric and unsupervised FC-SAE can extract optimal non-linear features from environmental factors successfully, outperforms some conventional machine learning methods, and is promising for LSP.


Landslide susceptibility prediction Deep learning Fully connected sparse autoencoder Support vector machine Back-propagation neural network 



Landslide susceptibility prediction


Fully connected spare autoencoder


Support vector machine


Back-propagation neural network


Landslide susceptibility index


Bare land soil index


Landslide susceptibility map


Negative predictive ratio


Artificial neural network


Frequency ratio


Rectified linear unit


Digital elevation model


Modified normalized difference water index


Normalized difference vegetation index


Positive predictive ratio


Total accuracy



We thank the Sinan Land Resources Bureau, Guizhou Province of China, for providing the landslide inventory information.

Funding information

This research is funded by the Natural Science Foundation of China (Nos. 41807285 and 51679117), the Science and Technology Department of Jiangxi Province Outstanding Youth Fund Project (No. 2018ACB21038), the National Science Foundation of Jiangxi Province, China (No. 20192BAB216034), and the China Postdoctoral Science Foundation (No. 2019M652287).


  1. Ahmed B (2015) Landslide susceptibility mapping using multi-criteria evaluation techniques in Chittagong metropolitan area, Bangladesh. Landslides 12(6):1077–1095CrossRefGoogle Scholar
  2. Althuwaynee OF, Pradhan B, Park HJ, Lee JH (2014) A novel ensemble decision tree-based chi-squared automatic interaction detection (chaid) and multivariate logistic regression models in landslide susceptibility mapping. Landslides 11(6):1063–1078CrossRefGoogle Scholar
  3. Ayinde BO, Inanc T, Zurada JM (2019) Regularizing deep neural networks by enhancing diversity in feature extraction. IEEE Trans Neural Netw Learn Syst PP(99):1–12Google Scholar
  4. Bello GA, Dawes TJW, Duan J, Biffi C, De Marvao A, Howard LSGE, Gibbs JSR, Wilkins MR, Cook SA, Rueckert D (2019) Deep-learning cardiac motion analysis for human survival prediction. Nature Machine Intelligence 1:95–104CrossRefGoogle Scholar
  5. Bengio Y, Courville A, Vincent P (2013) Unsupervised feature learning and deep learning: a review and new perspectives. IEEE Transactions on Pattern Analysis and Machine Intelligence 35:1–30CrossRefGoogle Scholar
  6. Borrelli L, Ciurleo M, Gullà G (2018) Correction to: Shallow landslide susceptibility assessment in granitic rocks using gis-based statistical methods: the contribution of the weathering grade map. Landslides 15(6):1–2Google Scholar
  7. Bui DT, Pradhan B, Lofman O, Revhaug I, Dick OB (2012) Spatial prediction of landslide hazards in Hoa Binh province (Vietnam): a comparative assessment of the efficacy of evidential belief functions and fuzzy logic models. Catena 96:28–40CrossRefGoogle Scholar
  8. Chen W, Pourghasemi HR, Panahi M, Kornejady A, Wang JL, Xie XS, Cao SB (2017) Spatial prediction of landslide susceptibility using an adaptive neuro-fuzzy inference system combined with frequency ratio, generalized additive model, and support vector machine techniques. Geomorphology 297:69–85. CrossRefGoogle Scholar
  9. Chen W, Peng J, Hong H, Shahabi H, Pradhan B, Liu J, Zhu AX, Pei X, Duan Z (2018) Landslide susceptibility modelling using gis-based machine learning techniques for chongren county, Jiangxi province, China. Sci Total Environ 626:230Google Scholar
  10. Cortes C, Vapnik V (1995) Support-vector networks. Mach Learn 20(3):273–297Google Scholar
  11. Feng J, Zhou ZH (2018) Autoencoder by forest. Paper presented at the AAAI-18Google Scholar
  12. Gorsevski PV, Brown MK, Panter K, Onasch CM, Simic A, Snyder J (2016) Landslide detection and susceptibility mapping using lidar and an artificial neural network approach: a case study in the Cuyahoga Valley National Park, Ohio. Landslides 13(3):467–484CrossRefGoogle Scholar
  13. He S, Pan P, Dai L, Wanga H (2012) Application of kernel-based Fisher discriminant analysis to map landslide susceptibility in the Qinggan River delta, Three Gorges, China. Geomorphology 171-172(171):30–41CrossRefGoogle Scholar
  14. Hong H, Pourghasemi HR, Pourtaghi ZS (2016) Landslide susceptibility assessment in Lianhua County (China): a comparison between a random forest data mining technique and bivariate and multivariate statistical models. Geomorphology 259:105–118CrossRefGoogle Scholar
  15. Hong H, Ilia I, Tsangaratos P, Chen W, Xu C (2017) A hybrid fuzzy weight of evidence method in landslide susceptibility analysis on the Wuyuan Area, China. Geomorphology 290:1–16CrossRefGoogle Scholar
  16. Huang F, Huang J, Jiang S, Zhou C (2017a) Landslide displacement prediction based on multivariate chaotic model and extreme learning machine. Eng Geol 218:173–186CrossRefGoogle Scholar
  17. Huang F, Yin K, Huang J, Gui L, Wang P (2017b) Landslide susceptibility mapping based on self-organizing-map network and extreme learning machine. Eng Geol 223:11–22CrossRefGoogle Scholar
  18. Huang F, Chen L, Yin K, Huang J, Gui L (2018a) Object-oriented change detection and damage assessment using high-resolution remote sensing images, Tangjiao Landslide, Three Gorges Reservoir, China. Environ Earth Sci 77(5):183CrossRefGoogle Scholar
  19. Huang F, Yao C, Liu W, Li Y, Liu X (2018b) Landslide susceptibility assessment in the nantian area of China: a comparison of frequency ratio model and support vector machine. Geomat Nat Haz Risk 9(1):919–938. CrossRefGoogle Scholar
  20. Jung EY (2018) Personalized urination activity recognition based on a recurrent neural network using smart band. Int Neurourol J 22(Suppl 2):S91–S100CrossRefGoogle Scholar
  21. Kavzoglu T, Sahin EK, Colkesen I (2014) Landslide susceptibility mapping using gis-based multi-criteria decision analysis, support vector machines, and logistic regression. Landslides 11(3):425–439CrossRefGoogle Scholar
  22. Kirschbaum D, Stanley T, Yatheendradas S (2016) Modeling landslide susceptibility over large regions with fuzzy overlay. Landslides 13(3):485–496CrossRefGoogle Scholar
  23. Le QH, Van NTH, Duc DM, Le TCH, Son PV, Khanh NH, Binh LT (2015) Landslide susceptibility mapping by combining the analytical hierarchy process and weighted linear combination methods: a case study in the upper Lo River catchment (Vietnam). Landslides:1–17Google Scholar
  24. Lee S, Ryu JH, Kim IS (2007) Landslide susceptibility analysis and its verification using likelihood ratio, logistic regression, and artificial neural network models: case study of Youngin, Korea. Landslides 4(4):327–338CrossRefGoogle Scholar
  25. Lin GF, Chang MJ, Huang YC, Ho JY (2017) Assessment of susceptibility to rainfall-induced landslides using improved self-organizing linear output map, support vector machine, and logistic regression. Eng Geol 224:62–74CrossRefGoogle Scholar
  26. Marjanović M, Kovačević M, Bajat B, Voženílek V (2011) Landslide susceptibility assessment using svm machine learning algorithm. Eng Geol 123(3):225–234CrossRefGoogle Scholar
  27. Nefeslioglu HA, Gokceoglu C, Sonmez H (2008) An assessment on the use of logistic regression and artificial neural networks with different sampling strategies for the preparation of landslide susceptibility maps. Eng Geol 97(3):171–191CrossRefGoogle Scholar
  28. Nefeslioglu H, Sezer E, Gokceoglu C, Bozkir A, Duman T (2010) Assessment of landslide susceptibility by decision trees in the metropolitan area of Istanbul, Turkey. Math Probl Eng 2010:1–15CrossRefGoogle Scholar
  29. Nefeslioglu HA, Sezer EA, Gokceoglu C, Ayas Z (2013) A modified analytical hierarchy process (m-ahp) approach for decision support systems in natural hazard assessments. Comput Geosci 59:1–8CrossRefGoogle Scholar
  30. Ozer B, Mutlu B, Nefeslioglu H, Sezer E, Rouai M, Dekayir A, Gokceoglu C (2019) On the use of hierarchical fuzzy inference systems (hfis) in expert-based landslide susceptibility mapping: the central part of the rif mountains (morocco). Bull Eng Geol Environ:1–18Google Scholar
  31. Pradhan B, Lee S, Buchroithner MF (2010) A gis-based back-propagation neural network model and its cross-application and validation for landslide susceptibility analyses. Comput Environ Urban Syst 34(3):216–235CrossRefGoogle Scholar
  32. Tsangaratos P, Ilia I, Hong H, Chen W, Xu C (2016) Applying information theory and gis-based quantitative methods to produce landslide susceptibility maps in Nancheng County, China. Landslides:1–21Google Scholar
  33. Vincent P, Larochelle H, Lajoie I, Bengio Y, Manzagol PA (2010) Stacked denoising autoencoders: learning useful representations in a deep network with a local denoising criterion. J Mach Learn Res 11(12):3371–3408Google Scholar
  34. Wu Y, Tan H, Qin L, Ran B, Jiang Z (2018) A hybrid deep learning based traffic flow prediction method and its understanding. Transp Res C Emerg Technol 90:166–180CrossRefGoogle Scholar
  35. Yang C, Liu J, Huang H, Fang S (2002) The comparison of the estimation of the biomass of tropical forest vegetation with the different forest stand age by using multi-variant linear regression. Paper presented at the Geoscience and Remote Sensing Symposium, 2003. IGARSS ‘03. Proceedings. 2003 IEEE InternationalGoogle Scholar
  36. Yang Z, Lu W, Long Y, Li P (2009) Application and comparison of two prediction models for groundwater levels: a case study in western Jilin province, China. J Arid Environ 73(4):487–492CrossRefGoogle Scholar
  37. Youssef AM, Pourghasemi HR, Pourtaghi ZS, Al-Katheeri MM (2016) 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 13(5):839–856CrossRefGoogle Scholar
  38. Zhang R, Isola P, Efros A A (2017) Split-brain autoencoders: unsupervised learning by cross-channel prediction. Paper presented at the Computer Vision & Pattern RecognitionGoogle Scholar

Copyright information

© Springer-Verlag GmbH Germany, part of Springer Nature 2019

Authors and Affiliations

  1. 1.School of Civil Engineering and ArchitectureNanchang UniversityNanchangChina
  2. 2.School of Information EngineeringNanchang UniversityNanchangChina
  3. 3.ARC Centre of Excellence for Geotechnical Science and EngineeringUniversity of NewcastleNewcastleAustralia

Personalised recommendations