Probabilistic early warning model for rainfall-induced landslides based on Bayesian approach
SONG Yufei1，CAO Yanbo1，2，FAN Wen1，2，YU Ningyu1，ZUO Chen3，TAO Hong4
(1. School of Geological Engineering，Chang'an University，Xi'an，Shaanxi 710069，China；2. China Electronic Research Institute of Engineering Investigations and Design，Xi'an，Shaanxi 710054，China；3. College of Transportation Engineering，Chang'an University，Xi'an，Shaanxi 710069，China；4. Shaanxi Institute of Geo-environment Monitoring，
Xi'an，Shaanxi 710054，China)
Abstract：To improve the early warning accuracy of rainfall-induced landslides，the Qinba Mountains region in southern Shaanxi province is taken as an example. At first，artificial neural network(ANN) and logistic regression model(LR) were used to establish the landslide susceptibility model，and the established susceptibility model was tested and corrected by frequency ratio model(FR) to express the spatial probability of landslide occurrence；Secondly，sensitivity analysis method was employed to select the optimal rainfall variables and the attenuation coefficient K，and then，two-dimensional Bayesian approach was be used to establish probabilistic threshold model，which can be used to calculate the temporal probability of landslide. The model was tested by the rainfall data from 2016 to 2020；Then，the spatial probability and temporal probability of rainfall-induced landslides were coupled base on Bayesian formula，and a probabilistic early warning model for rainfall-induced landslide(PLEWM) was proposed. To test the performance advantages of PLEWM，PLEWM and traditional early warning model were separately used to issue warning information day-by-day for the rainy season(July to September) from 2016 to 2020. It is proposed to use the investment of operating LEWM(Invest)，losses caused by landslides (Loss)，correct alert rate，missed alert rate and false alert rate as warning model performance indicators，to compare the performance differences between the PLEWM and traditional early warning model. The results show that：(1) EE-D is the optimal combination for rainfall threshold model in the study area，and the optimal attenuation coefficient K is 0.816. (2) Probabilistic threshold model predicts that 213.71 triggering rainfalls will occur from 2016 to 2020，and 201 actually recorded，with a cumulative error of 10.07%，the predicted triggering rainfall and the actual recorded in each probability intervals are distributed along a diagonal line with a slope of 1. (3) According to the statistics of the warning information issued in the rainy season from 2016 to 2020，The Invest and Loss of the PLEWM are 62.86% and 63.48% of traditional early warning model，respectively. The correct alert rate，missed alert rate and false alert rate are 63.99%，34.71% and 1.3% respectively，which are better than the traditional warning model；During the condition of long-lasting and high-intensity rainfall，the performance of PLEWM is significantly higher than traditional warning model.
[1] PETLEY D. Global patterns of loss of life from landslides[J]. Geology，2012，40(10)：927–930.
[2] FROUDE M J，PETLEY D N. Global fatal landslide occurrence from 2004 to 2016[J]. Nat Hazards Earth Syst Sci，2018，18(8)：2 161–2 181.
[3] GUZZETTI F，GARIANO S L，PERUCCACCI S，et al. Geographical landslide early warning systems[J]. Earth-Science Reviews，2020，102973(1)：1–29.
[4] WILSON R. The rise and fall of a debris‐flow warning system for the San Francisco bay region，California[M]. New Jersey：John Wiley and Sons，2005：493–516.
[5] 刘传正，温铭生，唐 灿. 中国地质灾害气象预警初步研究[J]. 地质通报，2004，23(4)：303–309.(LIU Chuanzheng，WEN Mingsheng，TANG Can. Meteorological early warning of geo-hazards in China based on raining forecast[J]. Geological Bulletin of China，2004，23(4)：303–309.(in Chinese))
[6] PICIULLO L，CALVELLO M，CEPEDA JOSé M. Territorial early warning systems for rainfall-induced landslides[J]. Earth-Science Reviews，2018，179(1)：228–247.
[7] PARK J Y，LEE S R，LEE D H，et al. A regional-scale landslide early warning methodology applying statistical and physically based approaches in sequence[J]. Engineering Geology，2019，260：1–14.
[8] FATHANI T F，KARNAWATI D，WILOPO W. An integrated methodology to develop a standard for landslide early warning systems[J]. Nat Hazards Earth Syst Sci，2016，16(9)：2 123–2 135.
[9] BAUM R L，GODT J W. Early warning of rainfall-induced shallow landslides and debris flows in the USA[J]. Landslides，2010，7(3)：259–272.
[10] CALVELLO M，PICIULLO L. Assessing the performance of regional landslide early warning models：the EDuMaP method[J]. Natural Hazards and Earth System Sciences，2016，16(1)：103–122.
[11] 许 强，汤明高，徐开祥，等. 滑坡时空演化规律及预警预报研究[J]. 岩石力学与工程学报，2008，27(6)：1 104–1 112.(XU Qiang，TANG Minggao，XU Kaixiang，et al. Research on space-time evolution laws and early warning-prediction of landslides[J]. Chinese Journal of Rock Mechanics and Engineering，2008，27(6)：1 104–1 112.(in Chinese))
[12] 许 强. 对滑坡监测预警相关问题的认识与思考[J]. 工程地质学报，2020，28(2)：360–374.(XU Qiang. Understanding the landslide monitoring and early warning：Consideration to practical issues[J]. Journal of Engineering Geology，2020，28(2)：360–374.(in Chinese))
[13] GUZZETTI F，PERUCCACCI S，ROSSI M，et al. Rainfall thresholds for the initiation of landslides in central and southern Europe[J]. Meteorology and Atmospheric Physics，2007，98(3/4)：239–267.
[14] PERUCCACCI S，BRUNETTI M T，GARIANO S L，et al. Rainfall thresholds for possible landslide occurrence in Italy[J]. Geomorphology，2017，290(1)：39–57.
[15] GARIANO S L，BRUNETTI M T，IOVINE G，et al. Calibration and validation of rainfall thresholds for shallow landslide forecasting in Sicily，southern Italy[J]. Geomorphology，2015，228(1)：653–665.
[16] JAISWAL P，VAN WESTEN C J. Estimating temporal probability for landslide initiation along transportation routes based on rainfall thresholds[J]. Geomorphology，2009，112(1-2)：96–105.
[17] 黄发明，曹中山，姚 池，等. 基于决策树和有效降雨强度的滑坡危险性预警[J]. 浙江大学学报：工学版，2021，55(3)：472–482.(HUANG Faming，CAO Zhongshan，YAO Chi，et al. Landslides hazard warning based on decision tree and effective rainfall intensity[J]. Journal of Zhejiang University：Engineering Science，2021，55(3)：472–482.(in Chinese))
[18] 中华人民共和国行业标准编写组. DB 61/ T 589—2013 地质灾害预报技术规程[S]. [S. l.]：[s. n.]，2013.(The Professional Standards Compilation Group of People?s Republic of China. DB 61/ T 589—2013. Forecasting of geological disasters technical regulations[S]. [S. l.]：[s. n.]，2013.(in Chinese))
[19] TIRANTI D，RABUFFETTI D. Estimation of rainfall thresholds triggering shallow landslides for an operational warning system implementation[J]. Landslides，2010，7(4)：471–481.
[20] DAS I，STEIN A，KERLE N，et al. Probabilistic landslide hazard assessment using homogeneous susceptible units(HSU) along a national highway corridor in the northern Himalayas，India[J]. Landslides，2011，8(3)：293–308.
[21] SEGONI S，LAGOMARSINO D，FANTI R，et al. Integration of rainfall thresholds and susceptibility maps in the Emilia Romagna(Italy) regional-scale landslide warning system[J]. Landslides，2014，12(4)：773–785.
[22] GUZZETTI F，REICHENBACH P，CARDINALI M，et al. Probabilistic landslide hazard assessment at the basin scale[J]. Geomorphology，2005，72(1-4)：272–299.
[23] REICHENBACH P，ROSSI M，MALAMUD B D，et al. A review of statistically-based landslide susceptibility models[J]. Earth-Science Reviews，2018，180(1)：60–91.
[24] FELL R，COROMINAS J，BONNARD C，et al. Guidelines for landslide susceptibility，hazard and risk zoning for land use planning[J]. Engineering Geology，2008，102(3/4)：85–98.
[25] 王佳佳，殷坤龙，肖莉丽. 基于GIS和信息量的滑坡灾害易发性评价——以三峡库区万州区为例[J]. 岩石力学与工程学报，2014，33(4)：797–808.(WANG Jiajia，YIN Kunlong，XIAO Lili. Landslide susceptibility assessment based on GIS and weighted information value：a case study of WanZhou district，three gorges reservoir[J]. Chinese Journal of Rock Mechanics and Engineering，2014，33(4)：797–808.(in Chinese))
[26] CANNON S H，GARTNER J E，WILSON R C，et al. Storm rainfall conditions for floods and debris flows from recently burned areas in southwestern Colorado and southern California[J]. Geomorphology，2008，96(3/4)：250–269.
[27] BERTI M，MARTINA M，FRANCESCHINI S，et al. Probabilistic rainfall thresholds for landslide occurrence using a Bayesian approach[J]. Journal of Geophysical Research：Earth Surface，2012，117(F4)：1–20.
[28] VESSIA G，PARISE M，BRUNETTI M T，et al. Automated reconstruction of rainfall events responsible for shallow landslides[J]. Natural Hazards and Earth System Sciences，2014，14(9)：2 399–2 408.
[29] IADANZA C，TRIGILA A，NAPOLITANO F. Identification and characterization of rainfall events responsible for triggering of debris flows and shallow landslides[J]. Journal of Hydrology，2016，541(1)：230–245.
[30] 李铁锋，丛威青. 基于Logistic回归及前期有效雨量的降雨诱发型滑坡预测方法[J]. 中国地质灾害与防治学报，2006，17(1)：33–35.(LI Tiefeng，CONG Weiqing. A method for rainfall-induced landslides prediction based on Logistic regression and effective antecedent rainfall[J]. The Chinese Journal of Geological Hazard and Control，2006，17(1)：33–35.( in Chinese))
[31] FENWICK D，SCHEIDT C，CAERS J. Quantifying asymmetric parameter interactions in sensitivity analysis：application to reservoir modeling[J]. Mathematical Geosciences，2014，46(4)：493–511.
[32] 黄发明，陈佳武，范宣梅，等. 降雨型滑坡时间概率的逻辑回归拟合及连续概率滑坡危险性建模[J]. 地球科学，2021，doi：10.3799/ dqkx.2021.164(HUANG Faming，CHEN Jiawu，FAN Xuanmei，et al. Logistic regression fitting of rainfall-induced landslide occurrence probability and continuous landslide hazard prediction modelling[J]. Earth Science，2021，doi：10.3799/dqkx.2021. 164.(in Chinese))
[33] BORDONI M，VIVALDI V，LUCCHELLI L，et al. Development of a data-driven model for spatial and temporal shallow landslide probability of occurrence at catchment scale[J]. Landslides，2020，18(1)，1 209–1 229.
[34] LEE J H，KIM H，PARK H J，et al. Temporal prediction modeling for rainfall-induced shallow landslide hazards using extreme value distribution[J]. Landslides，2020，18(1)：321–338.
[35] NEDUMPALLILE VASU N，LEE S-R，PRADHAN A M S，et al. A new approach to temporal modelling for landslide hazard assessment using an extreme rainfall induced-landslide index[J]. Engineering Geology，2016，215(1)：36–49.
[36] PICIULLO L，DAHL M P，DEVOLI G，et al. Adapting the EDuMaP method to test the performance of the Norwegian early warning system for weather-induced landslides[J]. Natural Hazards and Earth System Sciences，2017，17(6)：817–831.
[37] 杜继稳. 降雨型地质灾害预警预报——以黄土高原和秦巴山区为例[M]. 北京：科学出版社，2010：70–89.(DU Jiwen. Early warning and forecast of rainfall-induced landslide geological hazards—taking the Loess Plateau and Qinba Mountains as examples[M]. Beijing：Science Press，2010：70–89.(in Chinese))
[38] GARIANO S L，MELILLO M，PERUCCACCI S，et al. How much does the rainfall temporal resolution affect rainfall thresholds for landslide triggering?[J]. Natural Hazards，2020，100(2)：655–670.
[39] BRUNETTI M，PERUCCACCI S，ROSSI M，et al. Rainfall thresholds for the possible occurrence of landslides in Italy[J]. Natural Hazards and Earth System Sciences，2010，10(3)：447–458.
[40] GIANNECCHINI R，GALANTI Y，D?AMATO AVANZI G，et al. Probabilistic rainfall thresholds for triggering debris flows in a human-modified landscape[J]. Geomorphology，2016，257(1)：94–107.
