Skip to main content

Advertisement

SpringerLink
Log in

Comparative analysis of the TabNet algorithm and traditional machine learning algorithms for landslide susceptibility assessment in the Wanzhou Region of China

  • Original Paper
  • Published:
Natural Hazards Aims and scope Submit manuscript

Abstract

Landslides, widespread and highly dangerous geological disasters, pose significant risks to humankind and the ecological environment. Consequently, predicting landslides is vital for disaster prevention and mitigation strategies. At present, the predominant methods for predicting landslide susceptibility are evolving from conventional machine learning techniques to deep learning approaches. At present, the predominant methods for predicting landslide susceptibility are evolving from conventional machine learning techniques to deep learning approaches. Prior studies have shown that in the context of landslide susceptibility, these models frequently underperform relative to tree-based machine learning algorithms. This shortcoming has restricted the application of deep learning in this domain. To overcome this challenge, this study presents the TabNet algorithm, which combines the interpretability and selective feature extraction of tree models with the representation learning and comprehensive training capabilities of neural network models. This paper explores the potential of employing the TabNet algorithm for landslide susceptibility analysis in China’s WanZhou region and evaluates its performance against traditional machine learning techniques. The experimental data indicate that the TabNet algorithm achieves a recall score of 0.898 and an AUC of 0.915, demonstrating a generalization capability that is comparable to that of classical machine learning algorithms.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10

Similar content being viewed by others

Availability of data and materials

Scholars who need raw data for further study of the article should contact the corresponding author of the article to obtain data for the study area.

Code availability

Go to the GitHub link https://github.com/Dr-yanzhiwei/TabNet_for_wanzhou.

Notes

  1. Landsat-8, launched by NASA in 2013, plays a crucial role within the Landsat program. It incorporates two sensors, namely OLI and TIRS, and provides global coverage every 16 days.

  2. For the Pearson factor correlation diagram, see the github link at the end of the article.

References

  • AghaKouchak A, Huning LS, Chiang F, Sadegh M, Vahedifard F, Mazdiyasni O et al (2018) How do natural hazards cascade to cause disasters? Nature Publishing Group, London

    Book  Google Scholar 

  • Arik SÖ, Pfister T (2021) Tabnet: attentive interpretable tabular learning. In: Proceedings of the AAAI conference on artificial intelligence, vol 35, pp 6679–6687

  • Azarafza M, Azarafza M, Akgün H, Atkinson PM, Derakhshani R (2021) Deep learning-based landslide susceptibility mapping. Sci Rep 11(1):24112

    Article  ADS  CAS  PubMed  PubMed Central  Google Scholar 

  • Ba Q, Chen Y, Deng S, Yang J, Li H (2018) A comparison of slope units and grid cells as mapping units for landslide susceptibility assessment. Earth Sci Inf 11:373–388

    Article  Google Scholar 

  • Biau G, Scornet E (2016) A random forest guided tour. Test 25:197–227

    Article  MathSciNet  Google Scholar 

  • Bogaard TA, Greco R (2016) Landslide hydrology: from hydrology to pore pressure. Wiley Interdiscip Rev Water 3(3):439–459

    Article  Google Scholar 

  • Boulesteix A-L, Bender A, Lorenzo Bermejo J, Strobl C (2012) Random forest Gini importance favours SNPs with large minor allele frequency: impact, sources and recommendations. Brief Bioinform 13(3):292–304

    Article  PubMed  Google Scholar 

  • Buckland M, Gey F (1994) The relationship between recall and precision. J Am Soc Inf Sci 45(1):12–19

    Article  Google Scholar 

  • Cai H, Chen T, Niu R, Plaza A (2021) Landslide detection using densely connected convolutional networks and environmental conditions. IEEE J Sel Top Appl Earth Observ Remote Sens 14:5235–5247

    Article  ADS  Google Scholar 

  • Cemiloglu A, Zhu L, Mohammednour AB, Azarafza M, Nanehkaran YA (2023) Landslide susceptibility assessment for Maragheh county, Iran, using the logistic regression algorithm. Land. https://doi.org/10.3390/land12071397

    Article  Google Scholar 

  • Cohen I, Huang Y, Chen J, Benesty J, Benesty J, Chen J et al (2009) Pearson correlation coefficient. In: Noise reduction in speech processing, 1–4

  • Craney TA, Surles JG (2002) Model-dependent variance inflation factor cutoff values. Qual Eng 14(3):391–403

    Article  Google Scholar 

  • DeMaris A (1995) A tutorial in logistic regression. J Marriage Fam 57:956–968

    Article  Google Scholar 

  • Fawcett T (2006) An introduction to roc analysis. Pattern Recogn Lett 27(8):861–874

    Article  ADS  MathSciNet  Google Scholar 

  • Fernández A, Garcia S, Herrera F, Chawla NV (2018) Smote for learning from imbalanced data: progress and challenges, marking the 15-year anniversary. J Artif Intell Res 61:863–905

    Article  MathSciNet  Google Scholar 

  • Ghorbanzadeh O, Xu Y, Zhao H, Wang J, Zhong Y, Zhao D et al (2022) The outcome of the 2022 landslide4sense competition: advanced landslide detection from multisource satellite imagery. IEEE J Sel Top Appl Earth Observ Remote Sens 15:9927–9942

    Article  ADS  Google Scholar 

  • Gong Q, Zhang J, Wang J (2018) Application of GIS-based back propagation artificial neural networks and logistic regression for shallow landslide susceptibility mapping in South China-take Meijiang river basin as an example. Open Civ Eng J 12(1):21–34

    Article  Google Scholar 

  • Gong W, Juang CH, Wasowski J (2021) Geohazards and human settlements: Lessons learned from multiple relocation events in Badong, China-engineering geologist’s perspective. Eng Geol 285:106051

    Article  Google Scholar 

  • Henderson P, Ferrari V (2017) End-to-end training of object class detectors for mean average precision. In: Computer vision–ACCV 2016: 13th Asian conference on computer vision, Taipei, Taiwan, Nov 20–24, 2016, revised selected papers, part v 13, pp 198–213

  • Hong H, Liu J, Bui DT, Pradhan B, Acharya TD, Pham BT, Ahmad BB (2018) Landslide susceptibility mapping using j48 decision tree with adaboost, bagging and rotation forest ensembles in the Guangchang area (China). CATENA 163:399–413

    Article  Google Scholar 

  • Huang Y, Zhao L (2018) Review on landslide susceptibility mapping using support vector machines. CATENA 165:520–529. https://doi.org/10.1016/j.catena.2018.03.003

    Article  Google Scholar 

  • Huang F, Wang Y, Dong Z, Wu L, Guo Z, Zhang T (2019) Regional landslide susceptibility mapping based on grey relational degree model. Earth Sci 44(2):664–676

    Google Scholar 

  • Huang F, Zhang J, Zhou C, Wang Y, Huang J, Zhu L (2020a) A deep learning algorithm using a fully connected sparse autoencoder neural network for landslide susceptibility prediction. Landslides 17:217–229

    Article  Google Scholar 

  • Huang X, Khetan A, Cvitkovic M, Karnin Z (2020b) Tabtransformer: tabular data modeling using contextual embeddings. arXiv preprint arXiv:2012.06678

  • Huang C, Zhou Q, Zhou L, Cao Y (2021) Ancient landslide in Wanzhou district analysis from 2015 to 2018 based on ALOS-2 data by QPS-InSAR. Nat Hazards 109:1777–1800

    Article  Google Scholar 

  • Huang F, Chen J, Liu W, Huang J, Hong H, Chen W (2022) Regional rainfall-induced landslide hazard warning based on landslide susceptibility mapping and a critical rainfall threshold. Geomorphology 408:108236

    Article  Google Scholar 

  • Iverson RM, George DL, Allstadt K, Reid ME, Collins BD, Vallance JW et al (2015) Landslide mobility and hazards: implications of the 2014 Oso disaster. Earth Planet Sci Lett 412:197–208

    Article  ADS  CAS  Google Scholar 

  • Joseph LP, Joseph EA, Prasad R (2022) Explainable diabetes classification using hybrid Bayesian optimized TabNet architecture. Comput Biol Med 151:106178

    Article  PubMed  Google Scholar 

  • Kawamura Y, Dewan AM, Veenendaal B, Hayashi M, Shibuya T, Kitahara I, Ishii K (2014) Using GIS to develop a mobile communications network for disaster-damaged areas. Int J Digit Earth 7(4):279–293

    Article  Google Scholar 

  • Ke G, Meng Q, Finley T, Wang T, Chen W, Ma W et al (2017) Lightgbm: A highly efficient gradient boosting decision tree. In: Advances in neural information processing systems, vol 30

  • Lan H, Wu F, Zhou CH, Wang S (2002) Analysis on susceptibility of GIS based landslide triggering factors in Yunnan Xiaojiang watershed. Chin J Rock Mech Eng 21(10):1500–1506

    Google Scholar 

  • LaValley MP (2008) Logistic regression. Circulation 117(18):2395–2399

    Article  PubMed  Google Scholar 

  • Lee S, Lee M-J, Jung H-S, Lee S (2020) Landslide susceptibility mapping using Naïve Bayes and Bayesian network models in Umyeonsan, Korea. Geocarto Int 35(15):1665–1679

    Article  ADS  Google Scholar 

  • Liu S, Wang L, Zhang W, He Y, Pijush S (2023) A comprehensive review of machine learning based methods in landslide susceptibility mapping. Geol J 58:2283–2301

    Article  ADS  Google Scholar 

  • Lv L, Chen T, Dou J, Plaza A (2022) A hybrid ensemble-based deep-learning framework for landslide susceptibility mapping. Int J Appl Earth Observ Geoinf 108:102713

    Google Scholar 

  • Maćkiewicz A, Ratajczak W (1993) Principal components analysis (PCA). Comput Geosci 19(3):303–342

    Article  ADS  Google Scholar 

  • Masrur A, Yu M, Luo W, Dewan A (2020) Space-time patterns, change, and propagation of Covid-19 risk relative to the intervention scenarios in Bangladesh. Int J Environ Res Public Health 17(16):5911

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  • Merghadi A, Yunus AP, Dou J, Whiteley J, ThaiPham B, Bui DT, Abderrahmane B (2020) Machine learning methods for landslide susceptibility studies: a comparative overview of algorithm performance. Earth Sci Rev 207:103225

    Article  Google Scholar 

  • Moayedi H, Mehrabi M, Mosallanezhad M, Rashid ASA, Pradhan B (2019) Modification of landslide susceptibility mapping using optimized PSO-ANN technique. Eng Comput 35:967–984

    Article  Google Scholar 

  • Mutlu B, Nefeslioglu HA, Sezer EA, Akcayol MA, Gokceoglu C (2019) An experimental research on the use of recurrent neural networks in landslide susceptibility mapping. ISPRS Int J Geo-Inf 8(12):578

    Article  Google Scholar 

  • Nanehkaran YA, Chen B, Cemiloglu A, Chen J, Anwar S, Azarafza M, Derakhshani R (2023) Riverside landslide susceptibility overview: leveraging artificial neural networks and machine learning in accordance with the united nations (un) sustainable development goals. Water. https://doi.org/10.3390/w15152707

    Article  Google Scholar 

  • Nikoobakht S, Azarafza M, Akgün H, Derakhshani R (2022) Landslide susceptibility assessment by using convolutional neural network. Appl Sci. https://doi.org/10.3390/app12125992

    Article  Google Scholar 

  • Pandey VK, Sharma KK, Pourghasemi HR, Bandooni SK (2019) Sedimentological characteristics and application of machine learning techniques for landslide susceptibility modelling along the highway corridor Nahan to Rajgarh (Himachal Pradesh), India. CATENA 182:104150

    Article  Google Scholar 

  • Passman MA, McLafferty RB, Lentz MF, Nagre SB, Iafrati MD, Bohannon WT et al (2011) Validation of venous clinical severity score (VCSS) with other venous severity assessment tools from the American venous forum, national venous screening program. J Vasc Surg 54(6):2S-9S

    Article  PubMed  Google Scholar 

  • Pourghasemi HR, Pradhan B, Gokceoglu C (2012) Application of fuzzy logic and analytical hierarchy process (AHP) to landslide susceptibility mapping at Haraz Watershed, Iran. Nat Hazards 63:965–996

    Article  Google Scholar 

  • Ranjan G, Verma AK, Radhika S (2019) K-nearest neighbors and grid search cv based real time fault monitoring system for industries. In: 2019 IEEE 5th international conference for convergence in technology (i2ct), pp 1–5

  • Ri J, Kim H (2020) G-mean based extreme learning machine for imbalance learning. Digit Signal Process 98:102637

    Article  Google Scholar 

  • Sameen MI, Pradhan B, Lee S (2020) Application of convolutional neural networks featuring bayesian optimization for landslide susceptibility assessment. CATENA 186:104249

    Article  Google Scholar 

  • Shah C, Du Q, Xu Y (2022) Enhanced TabNet: attentive interpretable tabular learning for hyperspectral image classification. Remote Sens 14(3):716

    Article  ADS  Google Scholar 

  • Shao X, Ma S, Xu C, Zhang P, Wen B, Tian Y et al (2019) Planet image-based inventorying and machine learning-based susceptibility mapping for the landslides triggered by the 2018 Mw6.6 Tomakomai, Japan earthquake. Remote Sens 11(8):978

    Article  ADS  Google Scholar 

  • Shirvani Z (2020) A holistic analysis for landslide susceptibility mapping applying geographic object-based random forest: a comparison between protected and non-protected forests. Remote Sens 12(3):434

    Article  ADS  Google Scholar 

  • Song Y, Yang D, Wu W, Zhang X, Zhou J, Tian Z et al (2023) Evaluating landslide susceptibility using sampling methodology and multiple machine learning models. ISPRS Int J Geo-Inf. https://doi.org/10.3390/ijgi12050197

    Article  Google Scholar 

  • Speiser JL, Miller ME, Tooze J, Ip E (2019) A comparison of random forest variable selection methods for classification prediction modeling. Expert Syst Appl 134:93–101

    Article  PubMed  PubMed Central  Google Scholar 

  • Swets JA (1988) Measuring the accuracy of diagnostic systems. Science 240(4857):1285–1293

    Article  ADS  MathSciNet  CAS  PubMed  Google Scholar 

  • Tang H, Wasowski J, Juang CH (2019) Geohazards in the three gorges reservoir area, China—lessons learned from decades of research. Eng Geol 261:105267

    Article  Google Scholar 

  • Thara D, PremaSudha B, Xiong F (2019) Auto-detection of epileptic seizure events using deep neural network with different feature scaling techniques. Pattern Recogn Lett 128:544–550

    Article  Google Scholar 

  • Wang M, Qiao J-P (2013) Reservoir-landslide hazard assessment based on GIS: a case study in Wanzhou section of the three gorges reservoir. J Mt Sci 10:1085–1096

    Article  Google Scholar 

  • Yacouby R, Axman D (2020) Probabilistic extension of precision, recall, and f1 score for more thorough evaluation of classification models. In: Proceedings of the first workshop on evaluation and comparison of NLP systems, pp 79–91

  • Yan F, Zhang Q, Ye S, Ren B (2019) A novel hybrid approach for landslide susceptibility mapping integrating analytical hierarchy process and normalized frequency ratio methods with the cloud model. Geomorphology 327:170–187

    Article  ADS  Google Scholar 

  • Yan J, Xu T, Yu Y, Xu H (2021) Rainfall forecast model based on the TabNet model. Water 13(9):1272

    Article  Google Scholar 

  • Zeng T, Wu L, Peduto D, Glade T, Hayakawa YS, Yin K (2023) Ensemble learning framework for landslide susceptibility mapping: different basic classifier and ensemble strategy. Geosci Front 14:101645

    Article  Google Scholar 

  • Zhang W, He Y, Wang L, Liu S, Meng X (2023) Landslide susceptibility mapping using random forest and extreme gradient boosting: a case study of Fengjie, Chongqing. Geol J 58:2372–2387

    Article  ADS  Google Scholar 

  • Zhou C, Yin K, Cao Y, Ahmed B, Li Y, Catani F, Pourghasemi HR (2018) Landslide susceptibility modeling applying machine learning methods: a case study from Longju in the three gorges reservoir area, China. Comput Geosci 112:23–37

    Article  ADS  Google Scholar 

Download references

Acknowledgements

Project Supported by Scientific and Technological Research Program of Chongqing Municipal Education Commission (Grant No. KJZD-M202300502).

Funding

Scientific and Technological Research Program of Chongqing Municipal Education Commission (Grant No. KJZD-M202300502).

Author information

Authors and Affiliations

  1. College of Computer and Information Science, Chongqing Normal University, Chongqing, 401331, China

    Song Yingze, Zhang Xin, Zhou Jie & Yang Degang

  2. School of Information and Engineering, East China University of Technology, Nanchang, 330013, Jiangxi, China

    Song Yingxu

Authors
  1. Song Yingze
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Song Yingxu
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Zhang Xin
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Zhou Jie
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Yang Degang
    View author publications

    You can also search for this author in PubMed Google Scholar

Contributions

All authors contributed to the study conception and design. YS: Conceptualization of this study, Methodology, Software, Data curation, Writing—original draft. YS: Methodology, Formal analysis, Resources, Supervision. XZ: Formal analysis, Investigation. JZ: Methodology, Data curation. DY: Formal analysis, Resources, Supervision, Funding acquisition.

Corresponding author

Correspondence to Yang Degang.

Ethics declarations

Conflict of interest

The authors have no relevant financial or non-financial interests to disclose.

Ethics approval

Not applicable.

Consent to participate

Not applicable.

Consent for publication

Not applicable.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Yingze, S., Yingxu, S., Xin, Z. et al. Comparative analysis of the TabNet algorithm and traditional machine learning algorithms for landslide susceptibility assessment in the Wanzhou Region of China. Nat Hazards (2024). https://doi.org/10.1007/s11069-024-06521-4

Download citation

  • Received:

  • Accepted:

  • Published:

  • DOI: https://doi.org/10.1007/s11069-024-06521-4

Keywords

Search

Navigation