基于联系云和改进冲突证据融合算法的泥石流易发性评价

doi:10.16265/j.cnki.issn1003-3033.2024.08.1882

摘要/Abstract

摘要：

泥石流作为一种常见的地质灾害,其形成机制复杂,影响指标众多且呈现多重不确定性,为综合考虑多种影响因素协同作用,基于信息融合和不确定性分析理论,提出一种基于证据理论和云模型的泥石流易发评价方法。首先,应用联系云模型(CCM)计算泥石流易发性关键评价指标的基本概率分配函数(BPA);然后,引入兰氏距离和邓氏熵,分别修正指标BPA的可信度和不确定度,得到修正后的BPA;最后,基于D-S证据理论对修正BPA进行证据融合,实现泥石流易发性评价,并进行实例验证。结果表明:所采用的CCM能够克服正态云模型计算BPA时要求指标为正态分布的缺陷,并考虑的指标分布的随机性和不确定性;提出的方法与其他4种常用的证据融合方法评价结果基本吻合,用于泥石流易发性评价有效可行;基于兰氏距离和邓氏熵改进的冲突证据融合算法可提高证据融合的收敛速度和精度,并且结果更准确可靠。

关键词: 联系云模型(CCM), 泥石流, 易发性评价, 基本概率分配函数(BPA), 冲突证据融合, 兰氏距离, 邓氏熵, 证据理论

Abstract:

Debris flow, as a common geological disaster, has a complex formation mechanism with numerous influencing factors and multiple uncertainties. To comprehensively consider the synergistic effects of various influencing factors, based on information fusion and uncertainty analysis theory, this paper proposed a debris flow susceptibility evaluation method based on evidence theory and cloud model. Firstly, the BPA function of key evaluation indicators for debris flow susceptibility was calculated using a connection cloud model. Subsequently, the reliability and uncertainty of the indicators' BPA were modified using Lance distance and DENG entropy, respectively, resulting in a corrected BPA. Finally, evidence fusion was performed on the corrected BPA based on Dempster-Shafer (D-S) evidence theory to achieve debris flow susceptibility assessment, followed by a case validation. The results show that the connection cloud model used in this paper overcomes the limitation that the normal cloud model requires indicators to follow the normal distribution when calculating BPA, and it considers the randomness and uncertainty of indicator distribution. The proposed method's evaluation results are generally consistent with those of four other commonly used evidence fusion methods, proving it to be effective and feasible for debris flow susceptibility evaluation. The conflict evidence fusion method improved based on Lance distance and DENG entropy can enhance the convergence speed and precision of evidence fusion, making the results more accurate and reliable.

Key words: connection cloud model(CCM), debris flow, susceptibility evaluation, basic probability assignment (BPA), conflict evidence fusion, Lance distance, DENG entropy, evidence fusion

中图分类号:

陈光耀, 李司豪, 梁阳泽, 夏震昭, 徐照. 基于联系云和改进冲突证据融合算法的泥石流易发性评价[J]. 中国安全科学学报, 2024, 34(8): 222-230.

CHEN Guangyao, LI Sihao, LIANG Yangze, XIA Zhenzhao, XU Zhao. Susceptibility evaluation based on connection cloud model and improved conflict evidence fusion method for debris flow disaster[J]. China Safety Science Journal, 2024, 34(8): 222-230.

图/表 7

图1

图2

图3

表1

表2

不同证据融合规则的评价结果及对比

样本	(A_i)	1	2	3	4	5	6	7	8	9	10	11
Demptser	A₁(I级)	0.000 0	0.998 8	0.000 0	0.001 2	0.000 0	0.000 0	0.000 0	0.508 3	0.000 0	0.000 0	0.003 5
	A₂(II级)	0.003 4	0.001 2	0.000 0	0.002 7	1.000 0	0.001 0	0.000 0	0.209 6	0.000 3	1.000 0	0.002 3
	A₃(III级)	0.994 0	0.000 0	0.999 3	0.995 5	0.000 0	0.965 8	0.990 6	0.122 1	0.998 0	0.000 0	0.865 3
	A₄(IV级)	0.002 7	0.000 0	0.000 6	0.000 3	0.000 0	0.033 2	0.009 3	0.159 2	0.001 7	0.000 0	0.126 2
	A₅(Θ)	0.000 0	0.000 0	0.000 0	0.000 2	0.000 0	0.000 0	0.000 0	0.000 7	0.000 0	0.000 0	0.002 7
	评价结果	III	I	III	III	II	III	III	I	III	II	III
MURPHY^[23]	A₁(I级)	0.000 0	0.000 9	0.000 0	0.000 5	0.000 4	0.004 9	0.001 0	0.002 8	0.000 0	0.000 3	0.000 0
	A₂(II级)	0.012 5	0.000 0	0.000 0	0.000 9	0.000 0	0.000 5	0.003 2	0.000 1	0.006 4	0.000 0	0.000 0
	A₃(III级)	0.972 6	0.998 2	0.986 9	0.995 1	0.999 5	0.955 6	0.986 6	0.047 8	0.960 3	0.999 7	0.466 0
	A₄(IV级)	0.000 1	0.000 0	0.000 2	0.000 0	0.000 0	0.029 1	0.009 1	0.824 7	0.000 4	0.000 0	0.129 6
	A₅(Θ)	0.014 9	0.000 9	0.012 9	0.003 6	0.000 1	0.009 9	0.000 1	0.124 6	0.032 9	0.000 0	0.404 3
	评价结果	III	III	III	III	III	III	III	IV	III	III	III
DENG^[16]	A₁(I级)	0.000 0	0.000 0	0.000 0	0.000 0	0.000 0	0.000 2	0.000 0	0.000 0	0.000 0	0.000 0	0.000 0
	A₂(II级)	0.002 1	0.000 0	0.000 0	0.000 1	0.000 0	0.000 1	0.000 0	0.000 0	0.000 4	0.000 0	0.000 0
	A₃(III级)	0.981 6	0.999 0	0.994 3	0.998 2	0.999 9	0.989 2	0.999 3	0.001 5	0.944 1	1.000 0	0.344 7
	A₄(IV级)	0.000 0	0.000 0	0.000 1	0.000 0	0.000 0	0.006 4	0.000 7	0.883 8	0.000 8	0.000 0	0.101 6
	A₅(Θ)	0.016 2	0.001 0	0.005 5	0.001 7	0.000 1	0.004 1	0.000 0	0.114 6	0.054 7	0.000 0	0.553 7
	评价结果	III	III	III	III	III	III	III	IV	III	III	Θ
WANG^[24]	A₁(I级)	0.000 0	0.000 0	0.000 0	0.000 0	0.000 0	0.000 3	0.000 0	0.000 1	0.000 0	0.000 0	0.000 0
	A₂(II级)	0.004 2	0.000 0	0.000 0	0.000 2	0.000 0	0.000 1	0.000 1	0.000 0	0.001 4	0.000 0	0.000 0
	A₃(III级)	0.981 9	0.999 1	0.992 0	0.997 8	0.999 9	0.985 5	0.997 9	0.008 0	0.957 2	1.000 0	0.414 6
	A₄(IV级)	0.000 0	0.000 0	0.000 2	0.000 0	0.000 0	0.010 3	0.002 0	0.869 8	0.000 5	0.000 0	0.118 4
	A₅(Θ)	0.013 9	0.000 9	0.007 9	0.001 9	0.000 1	0.003 8	0.000 0	0.122 1	0.040 9	0.000 0	0.467 0
	评价结果	III	III	III	III	III	III	III	IV	III	III	Θ

表2

图4

图5

参考文献 24

[1]	崔传峰, 王俊豪, 崔志超, 等. 基于灰色可拓模型的洮河下游泥石流易发性评价[J]. 中国地质灾害与防治学报, 2019, 30(6): 40-48.
	CUI Chuanfeng, WANG Junhao, CUI Zhichao, et al. Evaluation of debris flow susceptibility in the lower reaches of Taohe River based on grey extension model[J]. The Chinese Journal of Geological Hazard and Control, 2019, 30(6): 40-48.
[2]	史明远, 丁桂伶, 陈剑平, 等. 基于博弈论和K均值的北京山区小流域综合敏感性评价[J]. 工程地质学报, 2015, 23(4): 790-794.
	SHI Mingyuan, DING Guiling, CHEN Jianping, et al. Game theory and K-means algorithm based comprehensive susceptibility analysis of catchments for debris flows in mountainous area of Beijing[J]. Journal of Engineering Geology, 2015, 23(4): 790-794.
[3]	李晓婷, 刘文龙. 模糊综合评判法在甘肃陇南武都区石门乡泥石流危险性评价中的应用[J]. 中国地质灾害与防治学报, 2020, 31(4): 71-76.
	LI Xiaoting, LIU Wenlong. Application of fuzzy comprehensive evaluation method to debris flow risk evaluation in Shimen township in Wudu district of Longnan city, Gansu province[J]. The Chinese Journal of Geological Hazard and Control, 2020, 31(4): 71-76.
[4]	曹洪洋, 王禹, 满兵. 基于改进灰色关联分析的泥石流危险性评价[J]. 南水北调与水利科技, 2015, 13(1): 91-94.
	CAO Hongyang, WANG Yu, MAN Bing. Risk evaluation of potential debris flow based on the improved grey correlation method[J]. South-to-North Water Transfers and Water Science & Technology, 2015, 13(1): 91-94.
[5]	罗真富, 蒲达成, 谢洪斌, 等. 基于GIS和信息量法的泥石流流域滑坡危险性评价[J]. 中国安全科学学报, 2011, 21(11): 144-150.
	LUO Zhenfu, PU Dacheng, XIE Hongbin, et al. Landslide hazard evaluation in debris flow catchment area based on GIS and information method[J]. China Safety Science Journal, 2011, 21(11): 144-150.
[6]	马彦彬, 李红蕊, 王林, 等. 机器学习方法在滑坡易发性评价中的应用:英文[J]. 土木与环境工程学报:中英文, 2022, 44(1): 53-67.
	MA Yanbin, LI Hongrui, WANG Lin, et al. Machine learning algorithms and techniques for landslide susceptibility investigation: a literature review[J]. Journal of Civil and Environmental Engineering, 2022, 44(1): 53-67.
[7]	刘汉龙, 马彦彬, 仉文岗. 大数据技术在地质灾害防治中的应用综述[J]. 防灾减灾工程学报, 2021, 41(4): 710-722.
	LIU Hanlong, MA Yanbin, ZHANG Wengang. Application of big data techniques in geological disaster analysis and prevention: a systematic review[J]. Journal of Disaster Prevention and Mitigation Engineering, 2021, 41(4): 710-722.
[8]	仉文岗, 何昱苇, 王鲁琦, 等. 基于水系分区的滑坡易发性机器学习分析方法:以重庆市奉节县为例[J]. 地球科学, 2023, 48(5): 2 024-2 038.
	ZHANG Wengang, HE Yuwei, WANG Luqi, et al. Machine learning solution for landslide susceptibility based on hydrographic division: case study of Fengjie county in Chongqing[J]. Earth Science, 2023, 48(5): 2 024-2 038.
[9]	LIU Songlin, WANG Luqi, ZHANG Wengang, et al. A physics-informed data-driven model for landslide susceptibility assessment in the three gorges reservoir area[J]. Geoscience Frontiers, 2023, 14(5): DOI:10.1016/J.GSF.2023.101621.
[10]	宋英华, 吴昊, 刘丹, 等. 基于D-S证据理论的地震应急救援群决策[J]. 中国安全科学学报, 2020, 30(5): 163-168. doi: 10.16265/j.cnki.issn1003-3033.2020.05.025
	SONG Yinghua, WU Hao, LIU Dan, et al. Group decision-making for earthquake emergency rescue plan based on D-S evidence theory[J]. China Safety Science Journal, 2020, 30(5): 163-168. doi: 10.16265/j.cnki.issn1003-3033.2020.05.025
[11]	曹文贵, 杨伟康, 翟友成. 基于D-S证据理论的岩体质量分级组合评价方法[J]. 湖南大学学报:自然科学版, 2015, 42(5): 86-91.
	CAO Wengui, YANG Weikang, ZHAI Youcheng. Combination evaluation method for the classification of rock mass quality based on D-S theory of evidence[J]. Journal of Hunan University: Natural Science, 2015, 42(5): 86-91.
[12]	张彪, 戴兴国. 基于指标距离与不确定度量的岩爆云模型预测研究[J]. 岩土力学, 2017, 38(增2): 257-265.
	ZHANG Biao, DAI Xingguo. A cloud model for predicting rockburst intensity grade based on index distance and uncertainty measure[J]. Rock and Soil Mechanics, 2017, 38(S2): 257-265.
[13]	苏永华. 岩土参数模糊隶属函数的构造方法及应用[J]. 岩土工程学报, 2007, 29(12): 1 772-1 779.
	SU Yonghua. Constructing method of fuzzy membership function of geotechnical parameters and its application[J]. Chinese Journal of Geotechnical Engineering, 2007, 29(12): 1 772-1 779.
[14]	张友鹏, 李远远. 基于云模型和证据理论的铁路信号系统风险评估[J]. 铁道学报, 2016, 38(1): 75-80.
	ZHANG Youpeng, LI Yuanyuan. Risk assessment of railway signal system based on cloud model and evidence theory[J]. Journal of the China Railway Society, 2016, 38(1): 75-80.
[15]	FANG Ye, CHEN Jie, LI Yibing. Improvement of D-S evidence theory for multi-sensor conflicting information[J]. Symmetry, 2017, 9(5): 1-15.
[16]	邓勇, 施文康, 朱振福. 一种有效处理冲突证据的组合方法[J]. 红外与毫米波学报, 2004, 23(1): 27-32.
	DENG Yong, SHI Wenkang, ZHU Zhenfu. Efficient combination approach of conflict evidence[J]. Journal of Infrared and Millimeter Waves, 2004, 23(1): 27-32.
[17]	李德毅, 孟海军, 史雪梅. 隶属云和隶属云发生器[J]. 计算机研究与发展, 1995, 32(6): 15-20.
	LI Deyi, MENG Haijun, SHI Xuemei. Membership cloud and membership generators[J]. Journal of Computer Research and Development, 1995, 32(6): 15-20.
[18]	汪明武, 金菊良. 联系数理论与应用[M]. 北京: 科学出版社, 2017. 55-75.
	WANG Mingwu, JIN Juliang. The theory and applications of connection numbers[M]. Beijing: Science Press, 2017: 55-75.
[19]	毛艺帆, 张多林, 王路. 基于重合度的证据冲突度量方法[J]. 控制与决策, 2017, 32(2): 293-298.
	MAO Yifan, ZHANG Duolin, WANG Lu. Measurement of evidence conflict based on overlapping degree[J]. Control and Decision, 2017, 32(2): 293-298.
[20]	DENG Yong. Deng entropy[J]. Chaos, Solitons and Fractals: the Interdisciplinary Journal of Nonlinear Science, and Nonequilibrium and Complex Phenomena, 2016, 91:549-553.
[21]	薛喜成. 西秦岭矿山泥石流发育规律与环境效应[M]. 西安: 陕西科学技术出版社, 2008: 77-155.
[22]	孙祥, 汪明武, 李杰, 等. 基于博弈论的泥石流灾害易发性联系云评价模型[J]. 合肥工业大学学报:自然科学版, 2020, 43(10): 1 357-1 361.
	SUN Xiang, WANG Mingwu, LI Jie, et al. Vulnerability evaluation of debris flow disaster based on game theory and connection cloud model[J]. Journal of Hefei University of Technology:Natural Science, 2020, 43(10): 1 357-1 361.
[23]	MURPHY C K. Combining belief functions when evidence conflicts[J]. Decision Support Systems, 2000, 29(1): 1-9.
[24]	汪明武, 董昊, 叶晖, 等. 基于联系云-证据理论的岩爆烈度预测模型[J]. 应用数学和力学, 2018, 39(9): 1 021-1 029.
	WANG Mingwu, DONG Hao, YE Hui, et al. A connection cloud-evidence theory coupling model for prediction of rockburst intensity[J]. Applied Mathematics and Mechanics, 2018, 39(9): 1 021-1 029.