Abstract
The early warning of debris flows based on rainfall monitoring is an important method for reducing risk. Statistical analysis of the relationship between rainfall characteristics and debris flow events is one of the principal methods of building a threshold model. Therefore, extracting more features from rainfall data is important for improving the prediction accuracy of debris flows. Based on rainfall monitoring records for the Goulin** debris flow catchment in central China, 46 rainfall events triggering debris flows and 321 rainfall events not triggering debris flows were analyzed. One hundred forty-three rainfall features were extracted from the rainfall data using tsfresh (a time series data processing Python package). Using a machine learning method, we tested the accuracy of the model in predicting debris flows in the two cases of using rainfall intensity–duration (I–D) (2 features), and using all features (143 features). The results showed that the accuracy of the model using I–D features was 0.94, and the AUC was 0.938; while the accuracy of the model using 143 features was 0.98, and the AUC was 0.975. Calculation of the importance of the features indicated that 7 rainfall features are important in determining the prediction accuracy of the model. The two most important features are the absolute energy (the sum over the squared values of each rainfall value in a rainfall event) and the sum values (the cumulative rainfall). Together they account for 91.4% of the total importance, and they can correctly identify 82.6% of the rainfall events that triggered debris flows without false alarms. Our results indicate that the use of more rainfall features can improve the accuracy and performance of the debris flow prediction model, which has an important reference value for improving the early warning of debris flows.
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs10346-022-01893-9/MediaObjects/10346_2022_1893_Fig1_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs10346-022-01893-9/MediaObjects/10346_2022_1893_Fig2_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs10346-022-01893-9/MediaObjects/10346_2022_1893_Fig3_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs10346-022-01893-9/MediaObjects/10346_2022_1893_Fig4_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs10346-022-01893-9/MediaObjects/10346_2022_1893_Fig5_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs10346-022-01893-9/MediaObjects/10346_2022_1893_Fig6_HTML.png)
Similar content being viewed by others
References
Abancó C, Hürlimann M, Moya J, Berenguer M (2016) Critical rainfall conditions for the initiation of torrential flows. Results from the Rebaixader catchment (Central Pyrenees). J Hydrol 541:218–229. https://doi.org/10.1016/j.jhydrol.2016.01.019
Abraham MT, Satyam N, Rosi A et al (2020) The selection of rain gauges and rainfall parameters in estimating intensity-duration thresholds for landslide occurrence: case study from Wayanad (India). Water 12:1000. https://doi.org/10.3390/w12041000
Aleotti P (2004) A warning system for rainfall-induced shallow failures. Eng Geol 73:247–265. https://doi.org/10.1016/j.enggeo.2004.01.007
Baum RL, Godt JW (2010) Early warning of rainfall-induced shallow landslides and debris flows in the USA. Landslides 7:259–272. https://doi.org/10.1007/s10346-009-0177-0
Bel C, Liébault F, Navratil O et al (2017) Rainfall control of debris-flow triggering in the Réal Torrent, Southern French Prealps. Geomorphology 291:17–32. https://doi.org/10.1016/j.geomorph.2016.04.004
Bernard M, Gregoretti C (2021) The use of rain gauge measurements and radar data for the model‐based prediction of runoff‐generated debris‐flow occurrence in early warning systems. Water Resour Res 57:e2020WR027893. https://doi.org/10.1029/2020WR027893
Berti M, Martina MLV, Franceschini S et al (2012) Probabilistic rainfall thresholds for landslide occurrence using a Bayesian approach. J Geophys Res Earth Surf 117:F04006. https://doi.org/10.1029/2012JF002367
Borga M, Stoffel M, Marchi L et al (2014) Hydrogeomorphic response to extreme rainfall in headwater systems: flash floods and debris flows. J Hydrol 518:194–205. https://doi.org/10.1016/j.jhydrol.2014.05.022
Caine N (1980) The rainfall intensity-duration control of shallow landslides and debris flows. Geogr Ann Ser A 62:23–27. https://doi.org/10.1080/04353676.1980.11879996
Cannon SH (1988) Regional rainfall-threshold conditions for abundant debris-flow activity. In: Ellen SD, Wieczorek GF (eds) Landslides, floods, and marine effects of the storm of January 3–5, 1982, in the San Francisco Bay region, California. US Geological Survey Professional Paper, pp 35–42
Chawla NV, Bowyer KW, Hall LO, Kegelmeyer WP (2002) SMOTE: synthetic minority over-sampling technique. J Artif Intell Res 16:321–357. https://doi.org/10.1613/jair.953
Chen CY (2020) Event-based rainfall warning regression model for landslide and debris flow issuing. Environ Earth Sci 79:127. https://doi.org/10.1007/s12665-020-8877-9
Chen JC, Jan CD, Huang WS (2013) Characteristics of rainfall triggering of debris flows in the Chenyulan watershed. Taiwan Nat Hazards Earth Syst Sci 13:1015–1023. https://doi.org/10.5194/nhess-13-1015-2013
Chmiel M, Walter F, Wenner M et al (2021) Machine learning improves debris flow warning. Geophys Res Lett 48:e2020GL090874. https://doi.org/10.1029/2020GL090874
Christ M, Braun N, Neuffer J, Kempa-Liehr AW (2018) Time Series FeatuRe Extraction on basis of Scalable Hypothesis tests (tsfresh – a Python package). Neurocomputing 307:72–77. https://doi.org/10.1016/j.neucom.2018.03.067
Christ M, Kempa-Liehr AW, Feindt M (2016) Distributed and parallel time series feature extraction for industrial big data applications. Ar**v e-prints arxiv:1610.07717
Cui P, Zhou GGD, Zhu XH, Zhang JQ (2013) Scale amplification of natural debris flows caused by cascading landslide dam failures. Geomorphology 182:173–189. https://doi.org/10.1016/j.geomorph.2012.11.009
Cui P, Zhu YY, Chen J et al (2007) Relationships between antecedent rainfall and debris flows in Jiangjia Ravine, China. In: International Conference on Debris-Flow Hazards Mitigation: Mechanics, Prediction, and Assessment, Proceedings. pp 3–10
Dunkerley D (2008) Identifying individual rain events from pluviograph records: a review with analysis of data from an Australian dryland site. Hydrol Process 22:5024–5036. https://doi.org/10.1002/hyp.7122
Frattini P, Crosta G, Sosio R (2009) Approaches for defining thresholds and return periods for rainfall-triggered shallow landslides. Hydrol Process 23:1444–1460. https://doi.org/10.1002/hyp.7269
Gariano SL, Melillo M, Peruccacci S, Brunetti MT (2020) How much does the rainfall temporal resolution affect rainfall thresholds for landslide triggering? Nat Hazards 100:655–670. https://doi.org/10.1007/s11069-019-03830-x
Giannecchini R (2005) Rainfall triggering soil slips in the southern Apuan Alps (Tuscany, Italy). Adv Geosci 2:21–24. https://doi.org/10.5194/adgeo-2-21-2005
Glade T (2005) Linking debris-flow hazard assessments with geomorphology. Geomorphology 66:189–213. https://doi.org/10.1016/j.geomorph.2004.09.023
Godt JW, Baum RL, Savage WZ et al (2008) Transient deterministic shallow landslide modeling: requirements for susceptibility and hazard assessments in a GIS framework. Eng Geol 102:214–226. https://doi.org/10.1016/j.enggeo.2008.03.019
Guo X, Cui P, Chen X et al (2021) Spatial uncertainty of rainfall and its impact on hydrological hazard forecasting in a small semiarid mountainous watershed. J Hydrol 595:126049. https://doi.org/10.1016/j.jhydrol.2021.126049
Guzzetti F, Peruccacci S, Rossi M, Stark CP (2007) Rainfall thresholds for the initiation of landslides in central and southern Europe. Meteorol Atmos Phys 98:239–267. https://doi.org/10.1007/s00703-007-0262-7
Guzzetti F, Peruccacci S, Rossi M, Stark CP (2008) The rainfall intensity-duration control of shallow landslides and debris flows: an update. Landslides 5:3–17. https://doi.org/10.1007/s10346-007-0112-1
Hirschberg J, Badoux A, McArdell BW et al (2021) Evaluating methods for debris-flow prediction based on rainfall in an Alpine catchment. Nat Hazards Earth Syst Sci 21:2773–2789. https://doi.org/10.5194/nhess-21-2773-2021
Hong Y, Hiura H, Shino K et al (2005) The influence of intense rainfall on the activity of large-scale crystalline schist landslides in Shikoku Island, Japan. Landslides 2:97–105. https://doi.org/10.1007/s10346-004-0043-z
Hu W, Xu Q, Wang GH et al (2015) Sensitivity of the initiation of debris flow to initial soil moisture. Landslides 12:1139–1145. https://doi.org/10.1007/s10346-014-0529-2
Iverson RM (1997) The physics of debris flows. Rev Geophys 35:245–296. https://doi.org/10.1029/97RG00426
Jakob M, Bovis M, Oden M (2005) The significance of channel recharge rates for estimating debris-flow magnitude and frequency. Earth Surf Process Landforms 30:755–766. https://doi.org/10.1002/esp.1188
Jiang Z, Fan X, Siva Subramanian S et al (2021) Probabilistic rainfall thresholds for debris flows occurred after the Wenchuan earthquake using a Bayesian technique. Eng Geol 280:105965. https://doi.org/10.1016/j.enggeo.2020.105965
Jomelli V, Pavlova I, Eckert N et al (2015) A new hierarchical Bayesian approach to analyse environmental and climatic influences on debris flow occurrence. Geomorphology 250:407–421. https://doi.org/10.1016/j.geomorph.2015.05.022
Kanjanakul C, Chub-uppakarn T, Chalermyanont T (2016) Rainfall thresholds for landslide early warning system in Nakhon Si Thammarat. Arab J Geosci 9:584. https://doi.org/10.1007/s12517-016-2614-4
Lee ML, Ng KY, Huang YF, Li WC (2014) Rainfall-induced landslides in Hulu Kelang area, Malaysia. Nat Hazards 70:353–375. https://doi.org/10.1007/s11069-013-0814-8
Leonarduzzi E, Molnar P (2020) Deriving rainfall thresholds for landsliding at the regional scale: daily and hourly resolutions, normalisation, and antecedent rainfall. Nat Hazards Earth Syst Sci 20:2905–2919. https://doi.org/10.5194/nhess-20-2905-2020
Li Y, Meng X, Guo P et al (2021) Constructing rainfall thresholds for debris flow initiation based on critical discharge and S-hydrograph. Eng Geol 280:105962. https://doi.org/10.1016/j.enggeo.2020.105962
Liu D, Leng X, Wei F et al (2018) Visualized localization and tracking of debris flow movement based on infrasound monitoring. Landslides 15:879–893. https://doi.org/10.1007/s10346-017-0898-4
Long K, Zhang S, Wei F et al (2020) A hydrology-process based method for correlating debris flow density to rainfall parameters and its application on debris flow prediction. J Hydrol 589:125124. https://doi.org/10.1016/j.jhydrol.2020.125124
Ma T, Li C, Lu Z, Wang B (2014) An effective antecedent precipitation model derived from the power-law relationship between landslide occurrence and rainfall level. Geomorphology 216:187–192. https://doi.org/10.1016/j.geomorph.2014.03.033
Marra F, Nikolopoulos EI, Creutin JD, Borga M (2016) Space–time organization of debris flows-triggering rainfall and its effect on the identification of the rainfall threshold relationship. J Hydrol 541:246–255. https://doi.org/10.1016/j.jhydrol.2015.10.010
Nembrini S, König IR, Wright MN (2018) The revival of the Gini importance? Bioinformatics 34:3711–3718. https://doi.org/10.1093/bioinformatics/bty373
Nikolopoulos EI, Crema S, Marchi L et al (2014) Impact of uncertainty in rainfall estimation on the identification of rainfall thresholds for debris flow occurrence. Geomorphology 221:286–297. https://doi.org/10.1016/j.geomorph.2014.06.015
Qi T, Meng X, Qing F et al (2021a) Distribution and characteristics of large landslides in a fault zone: a case study of the NE Qinghai-Tibet Plateau. Geomorphology 379:107592. https://doi.org/10.1016/j.geomorph.2021.107592
Qi T, Zhao Y, Meng X et al (2021b) Distribution modeling and factor correlation analysis of landslides in the large fault zone of the western Qinling Mountains: a machine learning algorithm. Remote Sens 13:4990. https://doi.org/10.3390/rs13244990
Qing F, Zhao Y, Meng X et al (2020) Application of machine learning to debris flow susceptibility map** along the China-Pakistan Karakoram Highway. Remote Sens 12:2933. https://doi.org/10.3390/rs12182933
Quinlan JR (1986) Induction of decision trees. Mach Learn 1:81–106. https://doi.org/10.1023/A:1022643204877
Rosi A, Segoni S, Canavesi V et al (2021) Definition of 3D rainfall thresholds to increase operative landslide early warning system performances. Landslides 18:1045–1057. https://doi.org/10.1007/s10346-020-01523-2
Saadatkhah N, Kassim A, Lee LM (2015) Hulu Kelang, Malaysia regional map** of rainfall-induced landslides using TRIGRS model. Arab J Geosci 8:3183–3194. https://doi.org/10.1007/s12517-014-1410-2
Tang C, Rengers N, van Asch TWJ et al (2011) Triggering conditions and depositional characteristics of a disastrous debris flow event in Zhouqu city, Gansu Province, northwestern China. Nat Hazards Earth Syst Sci 11:2903–2912. https://doi.org/10.5194/nhess-11-2903-2011
Tang H, McGuire LA, Kean JW, Smith JB (2020) The impact of sediment supply on the initiation and magnitude of runoff‐generated debris flows. Geophys Res Lett 47:e2020GL087643. https://doi.org/10.1029/2020GL087643
Tien Bui D, Pradhan B, Lofman O et al (2013) Regional prediction of landslide hazard using probability analysis of intense rainfall in the Hoa Binh province. Vietnam Nat Hazards 66:707–730. https://doi.org/10.1007/s11069-012-0510-0
Tsunetaka H, Hotta N, Imaizumi F et al (2021) Variation in rainfall patterns triggering debris flow in the initiation zone of the Ichino-sawa torrent, Ohya landslide. Japan Geomorphology 375:107529. https://doi.org/10.1016/j.geomorph.2020.107529
Wei Z, lei, Sun H yue, Xu H di, et al (2019) The effects of rainfall regimes and rainfall characteristics on peak discharge in a small debris flow-prone catchment. J Mt Sci 16:1646–1660. https://doi.org/10.1007/s11629-018-5260-3
Wieczorek GF, Glade T (2007) Climatic factors influencing occurrence of debris flows. In: Debris-flow Hazards and Related Phenomena. pp 325–362
Wieczorek GF, Guzzetti F (2000) A review of rainfall thresholds tor triggering landslides. In: Mediterranean Storms 1999 - Proceedings EGS Plinius Conference, Maratea, Italy, October 1999
Wu MH, Wang JP, Chen IC (2019) Optimization approach for determining rainfall duration-intensity thresholds for debris flow forecasting. Bull Eng Geol Environ 78:2495–2501. https://doi.org/10.1007/s10064-018-1314-6
**ong M, Meng X, Wang S et al (2016) Effectiveness of debris flow mitigation strategies in mountainous regions. Prog Phys Geogr 40:768–793. https://doi.org/10.1177/0309133316655304
Yang H, Wei F, Ma Z et al (2020) Rainfall threshold for landslide activity in Dazhou, southwest China. Landslides 17:61–77. https://doi.org/10.1007/s10346-019-01270-z
Zhang G, Cui P, Yin Y et al (2019) Real-time monitoring and estimation of the discharge of flash floods in a steep mountain catchment. Hydrol Process 33:3195–3212. https://doi.org/10.1002/hyp.13551
Zhang SJ, Xu CX, Wei FQ et al (2020) A physics-based model to derive rainfall intensity-duration threshold for debris flow. Geomorphology 351:106930. https://doi.org/10.1016/j.geomorph.2019.106930
Zhao Y (2021) Rainfall_Features.zip. In: ResearchGate. https://doi.org/10.13140/RG.2.2.17184.30723
Zhao Y, Meng X, Qi T et al (2022) AI-based rainfall prediction model for debris flows. Eng Geol 296:106456. https://doi.org/10.1016/j.enggeo.2021.106456
Zhao Y, Meng X, Qi T et al (2020) AI-based identification of low-frequency debris flow catchments in the Bailong River basin. China Geomorphology 359:107125. https://doi.org/10.1016/j.geomorph.2020.107125
Zhao Y, Meng X, Qi T et al (2021) Modeling the spatial distribution of debris flows and analysis of the controlling factors: a machine learning approach. Remote Sens 13:4813. https://doi.org/10.3390/RS13234813
Zhuang J, Cui P, Wang G et al (2015) Rainfall thresholds for the occurrence of debris flows in the Jiangjia Gully, Yunnan Province, China. Eng Geol 195:335–346. https://doi.org/10.1016/j.enggeo.2015.06.006
Funding
This work was supported by the Second Tibetan Plateau Scientific Expedition and Research Program (STEP) (2021QZKK0201); the Major Scientific and Technological Projects of Gansu Province (19ZD2FA002); the National Natural Science Foundation of China (42130709, 42077230, 41907224); the Natural Science Foundation of Gansu Province (21JR7RA442); the Construction Project of Gansu Technological Innovation Center (18JR2JA006); and the Geohazard prevention project of Gansu Province (CNPC-B-FS2021012).
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The authors declare no competing interests.
Rights and permissions
About this article
Cite this article
Zhao, Y., Meng, X., Qi, T. et al. Extracting more features from rainfall data to analyze the conditions triggering debris flows. Landslides 19, 2091–2099 (2022). https://doi.org/10.1007/s10346-022-01893-9
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10346-022-01893-9