数据驱动自适应更新的斜坡地质灾害易发性评价系统

doi:10.13722/j.cnki.jrme.2015.0070

摘要
图/表
参考文献(25)
相关文章 (15)

全文: PDF (1486 KB) HTML (1 KB)
输出: BibTeX | EndNote (RIS)

摘要为了实现斜坡地质灾害易发性评价能够随着影响因子动态变化和灾害点数目不断增加的自适应更新，使得评价精度能够随着影响因子认识的深入和样本点的丰富不断升高，提出一种数据驱动的斜坡地质灾害易发性评价系统自适应更新机制，以影响因子处理与筛选、支持向量机以及正确率、Kappa系数和AUC三个评价指标为理论支撑，设计并实现斜坡地质灾害易发性评价系统。该系统由数据预处理、易发性评价模型构建、评价模型评估、地质灾害易发性评价等4个模块构成，以数据变化触发系统自适应更新，可以支持影响因子的动态更新、地质灾害样本点的实时更新以及评价模型的迭代更新，使得评价模型能动态升级以适应最新的区域环境特征和地质灾害特征，保证评价模型的准确性。在浙江省文成县的实验结果表明，数据驱动自适应更新的斜坡地质灾害易发性评价系统能对地质灾害进行有效评价，并随着数据的丰富，将有效提高评价精度。

	服务

	把本文推荐给朋友
	加入我的书架
	加入引用管理器
	E-mail Alert
	RSS
	作者相关文章
	王丽丽1
	苏程1
	冯存均2
	左石磊2
	黄智才1
	章孝灿1

关键词 ：边坡工程, 斜坡地质灾害, 易发性评价, 数据驱动, 自适应更新, 支持向量机

Abstract：To maintain the susceptibility assessment model up-to-date and to improve the accuracy of assessment result，a data driven self-adaptive update mechanism in landslide susceptibility assessment system is proposed to accommodate changes of conditioning factors and increasing number of landslide inventories. Based on the theory of conditioning factor processing and selecting method，support vector machine and three evaluation indices (accuracy，kappa coefficient and AUC)，a landslide susceptibility assessment system has been designed and implemented. The system includes 4 modules：data preprocessing，landslide assessment model construction，model performance evaluation and landslides prediction. The self-adaptive update mechanism will be triggered by data changes. To fit the landslide assessment model for the latest regional environment and characteristics of landslides，the system will rebuild the training set and reconstruct the landslide assessment model once the conditioning factors and landslide inventories change or the assessment result cannot satisfy requirements. The experimental results in Wencheng County，Zhejiang Province，China show that the system can be updated automatically with changes of data to accommodate the latest environment and can improve the landslide susceptibility assessment result effectively as the abundance of conditioning factors and landslide inventories.

Key words： slope engineering landslides susceptibility assessment data driven self-adaptive update support vector machine

引用本文:

王丽丽1，苏程1，冯存均2，左石磊2，黄智才1，章孝灿1. 数据驱动自适应更新的斜坡地质灾害易发性评价系统[J]. 岩石力学与工程学报, 2016, 35(S1): 3076-3083.
WANG Lili1，SU Cheng1，FENG Cunjun2，ZUO Shilei2，HUANG Zhicai1，ZHANG Xiaocan1. A data driven self-adaptive update landslide susceptibility assessment system. , 2016, 35(S1): 3076-3083.

链接本文:

https://rockmech.whrsm.ac.cn/CN/10.13722/j.cnki.jrme.2015.0070 或 https://rockmech.whrsm.ac.cn/CN/Y2016/V35/IS1/3076

[1]	VAN WESTEN C J，VAN ASCH T W J，SOETERS R. Landslide hazard and risk zonation—why is it still so difficult?[J]. Bulletin of Engineering Geology and the Environment，2006，65(2)：167-184.
[2]	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.
[3]	CAPPARELLI G，VERSACE P. FLaIR and SUSHI： two mathematical models for early warning of landslides induced by rainfall[J]. Landslides，2011，8(1)：67-79.
[4]	GRECO R，GIORGIO M，CAPPARELLI G，et al. Early warning of rainfall-induced landslides based on empirical mobility function predictor[J]. Engineering Geology，2013，153：68-79.
[5]	JAKOB M，OWEN T，SIMPSON T. A regional real-time debris-flow warning system for the District of North Vancouver，Canada[J]. Landslides，2012，9(2)：165-178.
[6]	丁伟翠，杨强，王爱军，等. 应用GIS技术对甘肃省灵台县地质灾害气象预警的研究[J]. 中国地质，2010，37(4)：1199-1207. (DING Weicui，YANG Qiang，WANG Aijun，et al. A study of geological hazards meteorological early-warning in Lingtai County of Gansu Province based on GIS[J]. Geology in China，2010，37(4)：1199-1207. (in Chinese))
[7]	周申立，廖露，侯万儒. 基于三元结构的地质灾害预警系统研究[J].四川大学学报：工程科学版，2007，39(5)：31-37.(ZHOU Shenli，LIAO Lu，HOU Wanru. Research on early warning system in geological disaster based on framework of three factors[J]. Journal of Sichuan University：Engineering Science，2007，39(5)：31-37.(in Chinese))
[8]	张桂荣，殷坤龙，刘礼领，等. 基于WEBGIS和实时降雨信息的区域地质灾害预警预报系统[J].岩土力学，2005，26(8)：1312-1317.(ZHANG Guirong，YIN Kunlong，LIU Liling，et al. A real-time regional geological hazard warning system in terms of WEBGIS and rainfall[J]. Rock and Soil Mechanics，2005，26(8)：1312-1317.(in Chinese))
[9]	YU F，CHEN C，LIN S，et al. A web-based decision support system for slopeland hazard warning[J]. Environmental Monitoring and Assessment，2007，127(1/3)：419-428.
[10]	傅朝义，张鑫林，李再凯，等. 广东省地质灾害预警信息系统流程设计[J]. 中国地质灾害与防治学报，2006，17(1)：51-55.(FU Chaoyi，ZHANG Xinlin，LI Zaikai，et al. The design of framework of geo-hazardearly-warning in Guangdong Province[J]. The Chinese Journal of Geological Hazard and Control，2006，17(1)：51-55.(in Chinese))
[11]	李伟，王卫红. 基于WebGIS的突发性地质灾害预警预报系统设计与实现[J]. 浙江工业大学学报，2009，37(6)：602-606.(LI Wei，WANG Weihong. Design and implementation of the early warning and forecast system of abrupt geological hazard based on WebGIS[J]. Journal of Zhejiang University of Technology，2009，37(6)：602-606.(in Chinese))
[12]	王佳佳，殷坤龙. 基于WEBGIS和四库一体技术的三峡库区滑坡灾害预测预报系统研究[J]. 岩石力学与工程学报，2014，33(5)：1004-1013.(WANG Jiajia，YIN Kunlong. Landslide hazard predicting system based on WEBGIS and integrated databases in Three Gorges Reservoir Area[J]. Chinese Journal of Rock Mechanics and Engineering，2014，33(5)：1004-1013.(in Chinese))
[13]	GLADE T，CROZIER M，SMITH P. Applying probability determination to refine landslide-triggering rainfall thresholds using an empirical “Antecedent Daily Rainfall Model”[J]. Pure and Applied Geophysics，2000，157(6/8)：1059-1079.
[14]	贾俊平. 统计学[M]. 北京：清华大学出版社，2004：287-289.(JIA Junping. Statistics[M]. Beijing：Tsinghua University Press，2004：287-289.(in Chinese))
[15]	侯居茌，梁莹，任长志. 多变量连续属性离散化方法[J]. 模式识别与人工智能，2011，24(6)：792-797.(HOU Juchi，LIANG Ying，REN Changzhi. A multivariate discretization method for continuous attributes[J].Pattern Recognition and Artificial Intelligence，2011，24(6)：792-797.(in Chinese))
[16]	CHENGS，WANG L，WANG X，et al. Mapping of rainfall-induced landslide susceptibility in Wencheng，China，using support vector machine[J]. Natural Hazards，2015，76(3)：1759-1779.
[17]	BALLABIO C，STERLACCHINI S. Support vector machines for landslide susceptibility mapping：the Staffora River Basin case study，Italy[J]. Mathematical Geosciences，2012，44(1)：47-70.
[18]	WU Y，CHEN L，CHENG C，et al. GIS-based landslide hazard predicting system and its real-time test during a typhoon，Zhejiang Province，Southeast China[J]. Engineering Geology，2014，175：9-21.
[19]	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]. 岩土力学与工程学报，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))
[20]	马志江，陈汉林，杨树锋. 基于支持向量机理论的滑坡灾害预测——以浙江庆元地区为例[J]. 浙江大学学报：理学版，2003，30(5)：592-596.(MA Zhijiang，CHEN Hanlin，YANG Shufeng. Prediction of landslide hazard based on support vector machine theory[J]. Journal of Zhejiang University：Science Edition，2003，30(5)：592-596.(in Chinese))
[21]	POURGHASEMI H R，JIRANDEH A G，PRADHAN B，et al. Landslide susceptibility mapping using support vector machine and GIS at the Golestan Province，Iran[J]. Journal of Earth System Science，2013，122(2)：349-369.
[22]	PLATT J C. Probabilistic outputs for support vector machines and comparisons to regularized likelihood methods[C]// SMOLA A，BARTLETT P，SCHOLKOPF B，et al. Advances in Large Margin Classi?ers. Cambridge：MIT Press，1999：61-74.
[23]	DI EUGENIO B，GLASS M. Squibs and discussions-The kappa statistic：a second look[J]. Computational Linguistics，2004，1(30)：95-101.
[24]	FAWCETT T. An introduction to ROC analysis[J]. Pattern RecognitionLetters，2006，27(8)：861-874.
[25]	CHANG C，LIN C. LIBSVM：a library for support vector machines[J]. ACM Transactions on Intelligent Systems and Technology，2011，2(3)：1-27.