Abstract
The occurrence of landslides is affected by various environmental factors. When predicting landslides, conventional neural networks optimize parameters using global connectivity, which limits their efficiency in extracting features of contributing factors. In this study, we developed an attention-constrained neural network with overall cognition (OC-ACNN) to focus on important features from the complex data. The method has four steps: (1) extract the overall cognition as the prior input based on historical landslide distribution and contributing factors, (2) embed an attention mechanism in hidden layers to allocate more weight to noteworthy features, (3) update weights and fit the nonlinear relationship by the back-propagation neural network (BPNN), and (4) generate prediction results using a classifier. This model was applied to the Sichuan-Tibet Highway, considering 10 predisposing factors and 1449 historical landslides. The evaluation results indicate that OC-ACNN (0.822) had a higher predictive capability than multiple linear regression (MLR, 0.734) and BPNN (0.789) in terms of the area under the receiver operating characteristic curve (AUC). Further, we compared different attention patterns and score functions for use with the proposed model. The results show that OC-ACNN offered greater predictive performance than Self-ACNN (without OC, 0.803) and that the improved cosine (0.822) score function had better results and stability than others (0.819 highest).
Similar content being viewed by others
References
Aditian A, Kubota T, Shinohara Y (2018) Comparison of GIS-based landslide susceptibility models using frequency ratio, logistic regression, and artificial neural network in a tertiary region of Ambon, Indonesia. Geomorphology 318:101–111. https://doi.org/10.1016/j.geomorph.2018.06.006
Arabameri A, Saha S, Roy J et al (2020) Landslide susceptibility evaluation and management using different machine learning methods in The Gallicash River Watershed. Iran Remote Sens 12:475. https://doi.org/10.3390/rs12030475
Bahdanau D, Cho KH, Bengio Y (2015) Neural machine translation by jointly learning to align and translate. In: 3rd International Conference on Learning Representations, ICLR 2015 - Conference Track Proceedings
Behling R, Roessner S, Golovko D, Kleinschmit B (2016) Derivation of long-term spatiotemporal landslide activity—a multi-sensor time series approach. Remote Sens Environ 186:88–104. https://doi.org/10.1016/j.rse.2016.07.017
Chaudhari S, Mithal V, Polatkan G, Ramanath R (2021) An attentive survey of attention models. ACM Trans Intell Syst Technol 12:1–32. https://doi.org/10.1145/3465055
Chen HX, Zhang LM (2014) A physically-based distributed cell model for predicting regional rainfall-induced shallow slope failures. Eng Geol 176:79–92. https://doi.org/10.1016/j.enggeo.2014.04.011
Chen W, Pourghasemi HR, Panahi M et al (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. https://doi.org/10.1016/j.geomorph.2017.09.007
Choi CE, Cui Y, Au KYK et al (2018) Case Study: Effects of a partial-debris dam on riverbank erosion in the Parlung Tsangpo River. China Water (switzerland) 10:250. https://doi.org/10.3390/w10030250
Dao DV, Jaafari A, Bayat M et al (2020) A spatially explicit deep learning neural network model for the prediction of landslide susceptibility. CATENA 188:104451. https://doi.org/10.1016/j.catena.2019.104451
Di Napoli M, Marsiglia P, Di Martire D et al (2020) Landslide susceptibility assessment of wildfire burnt areas through earth-observation techniques and a machine learning-based approach. Remote Sens 12:2505. https://doi.org/10.3390/rs12152505
Du G, Zhang Y, Yang Z et al (2019) Landslide susceptibility mapping in the region of eastern Himalayan syntaxis, Tibetan Plateau, China: a comparison between analytical hierarchy process information value and logistic regression-information value methods. Bull Eng Geol Environ 78:4201–4215. https://doi.org/10.1007/s10064-018-1393-4
Fallah-Zazuli M, Vafaeinejad A, Alesheykh AA et al (2019) Mapping landslide susceptibility in the Zagros Mountains, Iran: a comparative study of different data mining models. Earth Sci Informatics 12:615–628. https://doi.org/10.1007/s12145-019-00389-w
Fortin JG, Anctil F, Parent LE (2014) Comparison of multiple-layer perceptrons and least squares support vector machines for remote-sensed characterization of in-field LAI patterns – a case study with potato. Can J Remote Sens 40:75–84. https://doi.org/10.1080/07038992.2014.928182
Ghorbanzadeh O, Blaschke T, Gholamnia K et al (2019) Evaluation of different machine learning methods and deep-learning convolutional neural networks for landslide detection. Remote Sens 11:196. https://doi.org/10.3390/rs11020196
Guo W, Wei H, Zhao J, Zhang K (2015) Theoretical and numerical analysis of learning dynamics near singularity in multilayer perceptrons. Neurocomputing 151:390–400. https://doi.org/10.1016/j.neucom.2014.09.026
He Q, Shahabi H, Shirzadi A et al (2019) Landslide spatial modelling using novel bivariate statistical based Naive Bayes, RBF Classifier, and RBF Network machine learning algorithms. Sci Total Env 663:1–15. https://doi.org/10.1016/j.scitotenv.2019.01.329
Hong H, Liu J, Zhu AX (2019) Landslide susceptibility evaluating using artificial intelligence method in the Youfang district (China). Environ Earth Sci 78:488. https://doi.org/10.1007/s12665-019-8415-9
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 259:105–118. https://doi.org/10.1016/j.geomorph.2016.02.012
Huang F, Yin K, Huang J et al (2017) Landslide susceptibility mapping based on self-organizing-map network and extreme learning machine. Eng Geol 223:11–22. https://doi.org/10.1016/j.enggeo.2017.04.013
Huang F, Zhang J, Zhou C et al (2019) A deep learning algorithm using a fully connected sparse autoencoder neural network for landslide susceptibility prediction. Landslides 17:217–229. https://doi.org/10.1007/s10346-019-01274-9
Huang R, Pei X, Fan X et al (2012) The characteristics and failure mechanism of the largest landslide triggered by the Wenchuan earthquake, May 12, 2008, China. Landslides 9:131–142. https://doi.org/10.1007/s10346-011-0276-6
Hungr O, Leroueil S, Picarelli L (2014) The Varnes classification of landslide types, an update. Landslides 11:167–194. https://doi.org/10.1007/S10346-013-0436-Y/FIGURES/33
Kalantar B, Ueda N, Saeidi V et al (2020) Landslide susceptibility mapping: machine and ensemble learning based on remote sensing big data. Remote Sens 12:1737. https://doi.org/10.3390/rs12111737
Lee S, Hong SM, Jung HS (2017) A support vector machine for landslide susceptibility mapping in Gangwon Province. Korea Sustain 9:48. https://doi.org/10.3390/su9010048
Lee S, Pradhan B (2006) Landslide hazard mapping at Selangor, Malaysia using frequency ratio and logistic regression models. Landslides 4:33–41. https://doi.org/10.1007/s10346-006-0047-y
Lee S, Talib JA (2005) Probabilistic landslide susceptibility and factor effect analysis. Environ Geol 47:982–990. https://doi.org/10.1007/s00254-005-1228-z
Leynaud D, Mulder T, Hanquiez V et al (2017) Sediment failure types, preconditions and triggering factors in the Gulf of Cadiz. Landslides 14:233–248. https://doi.org/10.1007/s10346-015-0674-2
Li D, Huang F, Yan L et al (2019) Landslide susceptibility prediction using particle-swarm-optimized multilayer perceptron: comparisons with multilayer-perceptron-only, BP neural network, and information value models. Appl Sci 9:3664. https://doi.org/10.3390/app9183664
Luong MT, Pham H, Manning CD (2015) Effective approaches to attention-based neural machine translation. Conf Proc - EMNLP 2015 Conf Empir Methods Nat Lang Process 1412–1421. https://doi.org/10.18653/v1/d15-1166
Nhu V-H, Hoang N-D, Nguyen H et al (2020) Effectiveness assessment of Keras based deep learning with different robust optimization algorithms for shallow landslide susceptibility mapping at tropical area. CATENA 188:104458. https://doi.org/10.1016/j.catena.2020.104458
Park S, Kim J (2019) Landslide susceptibility mapping based on random forest and boosted regression tree models, and a comparison of their performance. Appl Sci 9:942. https://doi.org/10.3390/app9050942
Pourghasemi HR, Rossi M (2017) Landslide susceptibility modeling in a landslide prone area in Mazandarn Province, north of Iran: a comparison between GLM, GAM, MARS, and M-AHP methods. Theor Appl Climatol 130:609–633. https://doi.org/10.1007/s00704-016-1919-2
Pradhan B (2010) Landslide susceptibility mapping of a catchment area using frequency ratio, fuzzy logic and multivariate logistic regression approaches. J Indian Soc Remote Sens 38:301–320. https://doi.org/10.1007/s12524-010-0020-z
Pradhan B, Lee S (2010) Regional landslide susceptibility analysis using back-propagation neural network model at Cameron Highland, Malaysia. Landslides 7:13–30. https://doi.org/10.1007/s10346-009-0183-2
Sameen MI, Pradhan B, Lee S (2020) Application of convolutional neural networks featuring Bayesian optimization for landslide susceptibility assessment. CATENA 186:104249. https://doi.org/10.1016/j.catena.2019.104249
Sharma S, Mahajan AK (2019) A comparative assessment of information value, frequency ratio and analytical hierarchy process models for landslide susceptibility mapping of a Himalayan watershed, India. Bull Eng Geol Environ 78:2431–2448. https://doi.org/10.1007/s10064-018-1259-9
Tien Bui D, Tuan TA, Klempe H et al (2016) Spatial prediction models for shallow landslide hazards: a comparative assessment of the efficacy of support vector machines, artificial neural networks, kernel logistic regression, and logistic model tree. Landslides 13:361–378. https://doi.org/10.1007/s10346-015-0557-6
Vaswani A, Shazeer N, Parmar N et al (2017) Attention is all you need. In: Advs in Neural Information Processing Sys 5999–6009
Wang H, Cui P, Liu D et al (2019) Evolution of a landslide-dammed lake on the southeastern Tibetan Plateau and its influence on river longitudinal profiles. Geomorphology 343:15–32. https://doi.org/10.1016/j.geomorph.2019.06.023
Wang W, He Z, Han Z et al (2020) Mapping the susceptibility to landslides based on the deep belief network: a case study in Sichuan Province, China. Nat Hazards 103:3239–3261. https://doi.org/10.1007/s11069-020-04128-z
Wu C, Guo Y, Su L (2021) Risk assessment of geological disasters in Nyingchi. Tibet Open Geosci 13:219–232. https://doi.org/10.1515/GEO-2020-0208
Xie Z, Chen G, Meng X et al (2017) A comparative study of landslide susceptibility mapping using weight of evidence, logistic regression and support vector machine and evaluated by SBAS-InSAR monitoring: Zhouqu to Wudu segment in Bailong River Basin. China Environ Earth Sci 76:313. https://doi.org/10.1007/s12665-017-6640-7
Xu Q, Fan X-M, Huang R-Q, Van WC (2009) Landslide dams triggered by the Wenchuan Earthquake, Sichuan Province, south west China. Bull Eng Geol Environ 68:373–386. https://doi.org/10.1007/s10064-009-0214-1
Ye C, Cui P, Pirasteh S et al (2016) GiT-based structural geologic feature analysis of the southern segment of Longmenshan fault zone for earthquake evidence. J Mt Sci 13:906–916. https://doi.org/10.1007/s11629-015-3796-z
Ye C, Li Y, Cui P et al (2019) Landslide detection of hyperspectral remote sensing data based on deep learning with constrains. IEEE J Sel Top Appl Earth Obs Remote Sens 12:5047–5060. https://doi.org/10.1109/jstars.2019.2951725
Yi Y, Zhang Z, Zhang W et al (2020) Landslide susceptibility mapping using multiscale sampling strategy and convolutional neural network: a case study in Jiuzhaigou region. CATENA 195:104851. https://doi.org/10.1016/j.catena.2020.104851
Zhou J, Cui P, Hao M (2016) Comprehensive analyses of the initiation and entrainment processes of the 2000 Yigong catastrophic landslide in Tibet, China. Landslides 13:39–54. https://doi.org/10.1007/s10346-014-0553-2
Funding
This work was supported in part by the Second Tibetan Plateau Scientific Expedition and Research Program (STEP) under Grant 2019QZKK0902, the National Natural Science Foundation of China under Grant 42071411, the Strategic Priority Research Program of the Chinese Academy of Sciences under Grant XDA23090203, and the key research and development program of Sichuan Province (22ZDYF2824).
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interests
The authors declare no competing interests.
Rights and permissions
About this article
Cite this article
Wei, R., Ye, C., Ge, Y. et al. An attention-constrained neural network with overall cognition for landslide spatial prediction. Landslides 19, 1087–1099 (2022). https://doi.org/10.1007/s10346-021-01841-z
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10346-021-01841-z