Machine Learning–Based Systems for Early Warning of Rainfall-Induced Landslide
Abstract
Landslide disasters have inflicted incalculable losses on China’s national economy, as well as on lives and property. Notably, 90% of landslide disasters are directly induced by rainfall or have indirect associations with it. In Bazhong City, Sichuan Province, China, the proportion of rainfall-induced landslides accounts for more than 70% of all geological disasters in the region. Our research undertook a susceptibility analysis of multimodal landslide data in Bazhou District of Bazhong City, employing four distinct machine learning methods: decision trees (DTs), random forests (RFs), support vector machines (SVMs), and back-propagation neural networks (BPNNs). Additionally, data from the Tropical Rainfall Measuring Mission (TRMM) 3B42 precipitation product were utilized to develop a rainfall intensity-duration (I-D) model for the Bazhou District. The experimental results indicated that the BPNN achieved the highest overall classification accuracy, reaching 92.00%, which was 3.00% to 6.00% higher than those achieved by other algorithms. The kappa coefficient for BPNN was 0.84, surpassing other algorithms by 0.06 to 0.10. Furthermore, our results demonstrated that the rainfall I-D model had a prediction accuracy of 90.91% for rainfall-induced landslides. Finally, a probability quantification model for landslide triggering factors was established based on the previous two research results, aimed at meteorological warning. Comparisons with five recorded landslide events in 2009 revealed that the experimental outcomes of the meteorological early warning model aligned with the actual inspection results. Therefore, this model can serve as a reliable reference for issuing warnings about rainfall-induced landslides in Bazhou District.
Get full access to this article
View all available purchase options and get full access to this article.
Data Availability Statement
Due to restrictions on sharing raw text files containing historical records of landslide locations, we are unable to provide these specific data sets. However, we are pleased to offer comprehensive access to all preprocessed data, in addition to the models and code utilized in our experiments. This includes the preprocessed data for the 600 samples used in our machine learning model analysis. Furthermore, we can provide the preprocessed data set detailing rainfall amounts for the five days leading up to the 63 landslide events, which played a crucial role in the calculation of the rainfall threshold. These two parts of the data are accessible in our Supplemental Materials. Additionally, the code underpinning the findings of this study can be provided by the corresponding author upon reasonable request. This offering is aimed at supporting further research and enabling replication or extension of our study’s findings.
Acknowledgments
This work was supported in part by the Key Science and Technology Project of Yunnan Province under Grant 202202AD08004; and in part by the Science Research Program of Natural Resources Department of Sichuan Province under Grants KJ-2020-3, KJ-2021-12, and KJ-2021-13. All coauthors have seen and approved the final version of the paper and have agreed to its submission for publication. Zezhong Zheng, Kai Zhang, and Na Wang are co-first authors
References
Aniya, M. 1985. “Landslide-susceptibility mapping in the Amahata river basin, Japan.” Ann. Am. Assoc. Geogr. 75 (1): 102–114. https://doi.org/10.1111/j.1467-8306.1985.tb00061.x.
Bai, S., J. Wang, B. Thiebes, C. Cheng, and Y. Yang. 2014. “Analysis of the relationship of landslide occurrence with rainfall: A case study of Wudu County, China.” Arab. J. Geosci. 7 (4): 1277–1285. https://doi.org/10.1007/s12517-013-0939-9.
Barredo, J., A. Benavides, J. Hervás, and C. J. van Westen. 2000. “Comparing heuristic landslide hazard assessment techniques using GIS in the Tirajana basin, Gran Canaria Island, Spain.” Int. J. Appl. Earth Obs. Geoinf. 2 (1): 9–23. https://doi.org/10.1016/S0303-2434(00)85022-9.
Brabb, E. E. 1984. “Innovative approaches to landslide hazard and risk mapping. USGS Publications Warehouse.” Accessed August 31, 1985. https://pubs.er.usgs.gov/publication/70197529.
Breiman, L. 2001. “Random forests.” Mach. Learn. 45 (1): 5–32. https://doi.org/10.1023/A:1010933404324.
Buscema, M. 1998. “Back propagation neural network.” Subst. Use Misuse 33 (2): 233–270. https://doi.org/10.3109/10826089809115863.
Caine, N. 1980. “The rainfall intensity-duration control of shallow landslides and debris flow.” Geogr. Ann. Ser. A Phys. Geogr. 62 (1–2): 23–27. https://doi.org/10.1080/04353676.1980.11879996.
Chen, C., Q. Chen, Z. Duan, J. Zhang, K. Mo, Z. Li, and G. Tang. 2018a. “Multiscale comparative evaluation of the GPM IMERG v5 and TRMM 3B42 v7 precipitation products from 2015 to 2017 over a climate transition area of China.” Remote Sens. 10 (6): 944. https://doi.org/10.3390/rs10060944.
Chen, L. Q., Z. X. Zou, Y. Yuan, and Y. Wang. 2018b. “Displacement prediction of reservoir landslide considering lag effect of inducing factors.” Yangtze River 49 (10): 60–65. https://doi.org/CNKI:SUN:RIVE.0.2018-10-012.
Chen, N., C. Xiong, W. Du, C. Wang, X. Lin, and Z. Chen. 2019. “An improved genetic algorithm coupling a back-propagation neural network model (IGA-BPNN) for water-level predictions.” Water 11 (9): 1795. https://doi.org/10.3390/w11091795.
Chen, W., X. Xie, J. Peng, H. Shahabi, H. Hong, D. T. Bui, Z. Duan, S. Li, and A. X. Zhu. 2018c. “GIS-based landslide susceptibility evaluation using a novel hybrid integration approach of bivariate statistical based random forest method.” Catena 164 (May): 135–149. https://doi.org/10.1016/j.catena.2018.01.012.
Chen, W., X. Xie, J. Wang, B. Pradhan, H. Hong, D. T. Bui, Z. Duan, and J. Ma. 2017. “A comparative study of logistic model tree, random forest, and classification and regression tree models for spatial prediction of landslide susceptibility.” Catena 151 (Apr): 147–160. https://doi.org/10.1016/j.catena.2016.11.032.
Chien-Yuan, C., C. Tien-Chien, Y. Fan-Chieh, and L. Sheng-Chi. 2005. “Analysis of time-varying rainfall infiltration induced landslide.” Environ. Geol. 48 (4–5): 466–479. https://doi.org/10.1007/s00254-005-1289-z.
Chong, X., X. Xiwei, Y. Guihua, and W. Xiyan. 2012. “Susceptibility analysis of impact factors of landslides triggered by Yushu earthquake.” Sci. Technol. Rev. 30 (1): 18–24. https://doi.org/CNKI:SUN:KJDB.0.2012-01-016.
Chung, C. J. F., and A. G. Fabbri. 1999. “Probabilistic prediction models for landslide hazard mapping.” Photogramm. Eng. Remote Sens. 65 (12): 1389–1399. https://doi.org/10.1016/S0924-2716(99)00030-1.
Cortes, C., and V. Vapnik. 1995. “Support-vector networks.” Mach. Learn. 20 (Apr): 273–297. https://doi.org/10.1007/BF00994018.
Dahal, R. K., S. Hasegawa, A. Nonomura, M. Yamanaka, T. Masuda, and K. Nishino. 2008. “GIS-based weights-of-evidence modelling of rainfall-induced landslides in small catchments for landslide susceptibility mapping.” Environ. Geol. 54 (2): 311–324. https://doi.org/10.1007/s00254-007-0818-3.
Ding, Y., et al. 2006. “Discussion on early warning system of geohazards based on weather forecast in Tianjin.” Chin. J. Geol. Hazard Control 2 (17): 126–129. https://doi.org/10.16031/j.cnki.issn.1003-8035.2006.02.029.
Duddu, V. R., S. S. Pulugurtha, A. S. Mane, and C. Godfrey. 2020. “Back-propagation neural network model to predict visibility at a road link-level.” Transp. Res. Interdiscip. Perspect. 8 (Nov): 100250.
Fei, X. Y., J. B. Liu, B. Q. Qu, Z. Liu, and Z. Wang. 2017. “Meteorologic early-warning model for rainfall-induced landslide disaster in Sichuan Province.” Bull. Soil Water Conserv. 37 (5): 315–321. https://doi.org/10.13961/j.cnki.stbctb.2017.05.053.
Finlay, P. J., R. Fell, and P. K. Maguire. 1997. “The relationship between the probability of landslide occurrence and rainfall.” Can. Geotech. J. 34 (6): 811–824. https://doi.org/10.1139/t97-047.
Gong, Q. H., J. X. Zhang, and J. Wang. 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. https://doi.org/10.2174/1874149501812010021.
Guzzetti, F., A. Carrara, M. Cardinali, and P. Reichenbach. 1999. “Landslide hazard evaluation: A review of current techniques and their application in a multi-scale study, Central Italy.” Geomorphology 31 (1–4): 181–216. https://doi.org/10.1016/S0169-555X(99)00078-1.
Guzzetti, F., S. Peruccacci, M. Rossi, and C. P. Stark. 2007. “Rainfall thresholds for the initiation of landslides in central and southern Europe.” Meteorol. Atmos. Phys. 98 (3–4): 239–267. https://doi.org/10.1007/s00703-007-0262-7.
Guzzetti, F., P. Reichenbach, M. Cardinali, M. Galli, and F. Ardizzone. 2005. “Probabilistic landslide hazard assessment at the basin scale.” Geomorphology 72 (1–4): 272–299. https://doi.org/10.1016/j.geomorph.2005.06.002.
Huang, F., J. Chen, W. Liu, J. Huang, H. Hong, and W. Chen. 2022. “Regional rainfall-induced landslide hazard warning based on landslide susceptibility mapping and a critical rainfall threshold.” Geomorphology 408 (Jul): 108236. https://doi.org/10.1016/j.geomorph.2022.108236.
Lee, S., M. J. Lee, H. S. Jung, and S. Lee. 2020. “Landslide susceptibility mapping using naïve Bayes and Bayesian network models in Umyeonsan, Korea.” Geocarto Int. 35 (15): 1665–1679. https://doi.org/10.1080/10106049.2019.1585482.
Li, Y., H. Meng, Y. Dong, and S. E. Hu. 2004. “Main types and characteristics of geo-hazard in China-based on the results of geo-hazard survey in 290 counties.” Chin. J. Geol. Hazard Control 15 (2): 29–34. https://doi.org/10.3969/j.issn.1003-8035.2004.02.005.
Liang, R. E., Z. S. Li, G. J. Miao, Y. H. Wen, and X. P. Li. 2013. “Current situation and prospect of regional geo-hazards meteorological early warning model.” Saf. Environ. Eng. 20 (1): 30–35.
Mandal, S., S. Mondal, S. Mandal, and S. Mondal. 2019. “Artificial neural network (ANN) model and landslide susceptibility.” In Statistical approaches for landslide susceptibility assessment and prediction. Cham, Switzerland: Springer. https://doi.org/10.1007/978-3-319-93897-4.
Mathew, J., D. G. Babu, S. Kundu, K. V. Kumar, and C. C. Pant. 2014. “Integrating intensity–duration-based rainfall threshold and antecedent rainfall-based probability estimate towards generating early warning for rainfall-induced landslides in parts of the Garhwal Himalaya, India.” Landslides 11 (4): 575–588. https://doi.org/10.1007/s10346-013-0408-2.
Michot, V., D. Vila, D. Arvor, T. Corpetti, J. Ronchail, B. M. Funatsu, and V. Dubreuil. 2018. “Performance of TRMM TMPA 3B42 V7 in replicating daily rainfall and regional rainfall regimes in the Amazon basin (1998–2013).” Remote Sens. 10 (12): 1879. https://doi.org/10.3390/rs10121879.
Murarescu, O., G. Muratoreanu, and M. Franculeasa. 2013. “Extreme climatic phenomena and their impact in the shaping the current relief in the Bucegi-Leaota mountain complex.” Sci. Ann. Stefan cel Mare Univ. Suceava Geogr. Ser. 22 (1): 47–55. https://doi.org/10.4316/GEOREVIEW.2013.22.1.70.
Nahayo, L., C. Mupenzi, G. Habiyaremye, E. Kalisa, M. Udahogora, V. Nzabarinda, and L. Li. 2019. “Landslides hazard mapping in Rwanda using bivariate statistical index method.” Environ. Eng. Sci. 36 (8): 892–902. https://doi.org/10.1089/ees.2018.0493.
Polykretis, C., C. Chalkias, and M. Ferentinou. 2019. “Adaptive neuro-fuzzy inference system (ANFIS) modeling for landslide susceptibility assessment in a Mediterranean hilly area.” Bull. Eng. Geol. Environ. 78 (2): 1173–1187. https://doi.org/10.1007/s10064-017-1125-1.
Pourghasemi, H. R., H. R. Moradi, S. M. Fatemi Aghda, C. Gokceoglu, and B. Pradhan. 2014. “GIS-based landslide susceptibility mapping with probabilistic likelihood ratio and spatial multi-criteria evaluation models (north of Tehran, Iran).” Arab J. Geosci. 7 (5): 1857–1878. https://doi.org/10.1007/s12517-012-0825-x.
Reichenbach, P., M. Rossi, B. D. Malamud, M. Mihir, and F. Guzzetti. 2018. “A review of statistically-based landslide susceptibility models.” Earth Sci. Rev. 180 (May): 60–91. https://doi.org/10.1016/j.earscirev.2018.03.001.
Samantaray, S., and A. Sahoo. 2020a. “Estimation of runoff through BPNN and SVM in Agalpur watershed.” In Vol. 2 of Proc., 7th Int. Conf. on Frontiers in Intelligent Computing: Theory and Applications (2018), 268–275. New York: Springer. https://doi.org/10.1007/978-981-13-9920-6_27.
Samantaray, S., and A. Sahoo. 2020b. “Prediction of runoff using BPNN, FFBPNN, CFBPNN algorithm in arid watershed: A case study.” Int. J. Knowl. Based Int. 24 (3): 243–251. https://doi.org/10.3233/KES-200046.
Segoni, S., D. Lagomarsino, R. Fanti, S. Moretti, and N. Casagli. 2015. “Integration of rainfall thresholds and susceptibility maps in the Emilia Romagna (Italy) regional-scale landslide warning system.” Landslides 12 (4): 773–785. https://doi.org/10.1007/s10346-014-0502-0.
Segoni, S., G. Rossi, A. Rosi, and F. Catani. 2014. “Landslides triggered by rainfall: A semi-automated procedure to define consistent intensity–duration thresholds.” Comput. Geosci. 63 (Feb): 123–131. https://doi.org/10.1016/j.cageo.2013.10.009.
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. https://doi.org/10.3390/rs12030434.
Song, G. Q., Y. G. Li, and P. L. Zhong. 2004. “Discussion on the early warning of the geo-hazards based on the weather forecast: An example of Sichuan Province.” Hydrogeol. Eng. Geol. 2 (8): 33–36. https://doi.org/10.16030/j.cnki.issn.1000-3665.2004.02.008.
Stehman, S. V. 1997. “Selecting and interpreting measures of thematic classification accuracy.” Remote Sens. Environ. 62 (1): 77–89. https://doi.org/10.1016/S0034-4257(97)00083-7.
Thiebes, B., B. A. I. Shibiao, X. I. Yanan, T. Glade, and B. E. L. L. Rainer. 2017. “Combining landslide susceptibility maps and rainfall thresholds using a matrix approach.” Rev. de Geomorfologie 19 (1): 58–74. https://doi.org/10.21094/rg.2017.003.
Van Westen, C. J., N. Rengers, and R. Soeters. 2003. “Use of geomorphological information in indirect landslide susceptibility assessment.” Nat. Hazards 30 (3): 399–419. https://doi.org/10.1023/B:NHAZ.0000007097.42735.9e.
Wang, W., Y. Du, K. Chau, H. Chen, C. Liu, and Q. Ma. 2021. “A comparison of BPNN, GMDH, and ARIMA for monthly rainfall forecasting based on wavelet packet decomposition.” Water 13 (20): 2871. https://doi.org/10.3390/w13202871.
Wang, W., S. Zhao, L. Jiao, M. Taylor, B. Zhang, G. Xu, and H. Hou. 2019. “Estimation of PM2.5 concentrations in China using a spatial back propagation neural network.” Sci. Rep. 9 (1): 13788. https://doi.org/10.1038/s41598-019-50177-1.
Wei, P. X., and S. L. Yang. 2011. “Realization and significance of early-warning of geo-hazard in short-time meteorology in Guangdong.” J. Geol. Hazards Environ. Preserv. 22 (2): 54–59. https://doi.org/CNKI:SUN:DZHB.0.2011-02-012.
Wu, W., and R. C. Sidle. 1995. “A distributed slope stability model for steep forested basins.” Water Resour. Res. 31 (8): 2097–2110. https://doi.org/10.1029/95WR01136.
Xie, C. Y. 2011. “Landslides hazard susceptibility evaluation based on weighting model.” J. Cent. South Univ. (Sci. Technol.) 42 (6): 1772–1779. https://doi.org/CNKI:SUN:ZNGD.0.2011-06-044.
Xu, J. C., Y. Q. Shang, K. F. Chen, and J. F. Yang. 2005. “Analysis of shallow landslide stability under intensive rainfall.” Chin. J. Rock Mech. Eng. 24 (18): 3246–3251. https://doi.org/10.3321/j.issn:1000-6915.2005.18.007.
Yan, F., Q. Zhang, S. Ye, and B. Ren. 2019. “A novel hybrid approach for landslide susceptibility mapping integrating analytical hierarchy process and normalized frequency ratio methods with the cloud model.” Geomorphology 327 (Feb): 170–187. https://doi.org/10.1016/j.geomorph.2018.10.024.
Yilmaz, I. 2009. “Landslide susceptibility mapping using frequency ratio, logistic regression, artificial neural networks and their comparison: A case study from Kat landslides (Tokat—Turkey).” Comput. Geosci. 35 (6): 1125–1138. https://doi.org/10.1016/j.cageo.2008.08.007.
Zhang, H. B. 2006. “A model used for geological hazard prediction in Yunnan Province.” Chin. J. Geol. Hazard Control 17 (1): 40–43. https://doi.org/10.3969/j.issn.1003-8035.2006.01.010.
Zhou, C., and D. Li. 2009. “Advances in rainfall-induced landslides mechanism and risk mitigation.” Adv. Earth Sci. 24 (5): 477. https://doi.org/10.3321/j.issn:1001-8166.2009.05.003.
Zou, J., K. T. T. Bui, Y. Xiao, and C. V. Doan. 2018. “Dam deformation analysis based on BPNN merging models.” Geo-Spatial Inf. Sci. 21 (2): 149–157. https://doi.org/10.1080/10095020.2017.1386848.
Information & Authors
Information
Published In
Natural Hazards Review
Volume 25 • Issue 4 • November 2024
Copyright
© 2024 American Society of Civil Engineers.
History
Received: Aug 1, 2023
Accepted: Apr 1, 2024
Published online: Jun 17, 2024
Published in print: Nov 1, 2024
Discussion open until: Nov 17, 2024
ASCE Technical Topics:
- Artificial intelligence and machine learning
- Climates
- Computer programming
- Computing in civil engineering
- Data analysis
- Disaster preparedness
- Disaster risk management
- Disaster warning systems
- Disasters and hazards
- Engineering fundamentals
- Environmental engineering
- Geohazards
- Geotechnical engineering
- Landslides
- Meteorology
- Methodology (by type)
- Natural disasters
- Precipitation
- Rainfall
- Rainfall intensity
- Research methods (by type)
Authors
Metrics & Citations
Metrics
Citations
Download citation
If you have the appropriate software installed, you can download article citation data to the citation manager of your choice. Simply select your manager software from the list below and click Download.