基于信息量模型的地质灾害易发性评价
|
摘要
以略阳县为研究区域,在综合分析研究区地质灾害分布关系、控制因素与诱发因素的基础上,选取高程、坡度、坡向、曲率、岩性、构造、河流、道路和地震等9类评价指标,将信息量模型与GIS空间分析功能相结合,分别计算各评价指标的信息量值,构建地质灾害易发性评价体系,对该区域地质灾害易发性进行评价。结果表明,研究区内较高、高易发区面积占研究区总面积的29. 1%,灾害率为67. 1%,灾积比为3. 395。利用ROC曲线得到AUC评价指标值为0. 796,说明该方法具有较高的精度,具有良好的适用性。
Taking Lueyang County as the research area, nine types of indicators including elevation, slope, aspect, curvature,lithology, structure, river, road and earthquake are selected as evaluation indexes on the basis of comprehensive analysis of the distribution relationship, controlling factors and inducing factors of geological hazards in study area. By combining the information model with the spatial analysis function of GIS, the information value of each evaluation index is calculated separately, and the evaluation system of geological hazard risk is constructed, and the evaluation results of geological hazard risk are obtained. The results show that 29. 1% of total area belongs to high risk and medium-high risk area, 67. 1% of total area is affected by geological hazards, and the ratio of hazard accumulation is 3. 395. The area under curve( AUC) evaluation index value is 0. 796 by receiver operating characteristic( ROC) curve, which indicates that the method has higher precise and good applicability to regional geological hazard assessment.
Taking Lueyang County as the research area, nine types of indicators including elevation, slope, aspect, curvature,lithology, structure, river, road and earthquake are selected as evaluation indexes on the basis of comprehensive analysis of the distribution relationship, controlling factors and inducing factors of geological hazards in study area. By combining the information model with the spatial analysis function of GIS, the information value of each evaluation index is calculated separately, and the evaluation system of geological hazard risk is constructed, and the evaluation results of geological hazard risk are obtained. The results show that 29. 1% of total area belongs to high risk and medium-high risk area, 67. 1% of total area is affected by geological hazards, and the ratio of hazard accumulation is 3. 395. The area under curve( AUC) evaluation index value is 0. 796 by receiver operating characteristic( ROC) curve, which indicates that the method has higher precise and good applicability to regional geological hazard assessment.
引文
[1]殷坤龙,朱良峰.滑坡灾害空间区划及GIS应用研究[J].地学前缘,2001,8(2):279-284.
[2]赵洲,侯恩科,王建智,等.县域滑坡灾害风险管理信息系统研发与应用———以陕西省宁强县为例[J].工程地质学报,2012,20(2):170-182.
[3]王维早,雷霆,许强.基于层次分析法的河北省太行山区泥石流灾害危险性评估研究[J].地球与环境,2010,38(3):357-362.
[4]许冲,戴福初,姚鑫,等.基于GIS的汶川地震滑坡灾害影响因子确定性系数分析[J].岩石力学与工程学报,2010,29(S1):2972-2981.
[5]王念秦,薛瑶琼,李少兵,等.基于粗糙集理论的泥石流易发性综合评判模型[J].水土保持研究,2014,21(3):246-250.
[6]刘艺梁,殷坤龙,刘斌.逻辑回归和人工神经网络模型在滑坡灾害空间预测中的应用[J].水文地质工程地质,2010,37(5):92-96.
[7]王哲,易发成,陈廷方.基于模糊综合评判的绵阳市地质灾害易发性评价[J].科技导报,2012,30(31):53-60.
[8] ZHOU Chao, YIN Kunlong, CAO Ying, et al. Application of time se-ries analysis and PSO-SVM model in predicting the Bazimen landslidein the Three Gorges Reservoir, China[J]. Engineering Geology,2016,204(2):108-120.
[9] CHEN Wei, POURGHASEMI H R, KORNEJADY A, et al. Land-slide spatial modeling:Introducing new ensembles of ANN, Max Ent,and SVM machine learning techniques[J]. Geoderma,2017,305(6):314-327.
[10]黄发明,殷坤龙,蒋水华,等.基于聚类分析和支持向量机的滑坡易发性评价[J].岩石力学与工程学报,2018,37(1):156-167.
[11]张兴龙.基于CA-Markov的滑坡易发性动态预测模型研究[D].成都:成都理工大学,2017.
[12]刘渊博,牛瑞卿,于宪煜,等.旋转森林模型在滑坡易发性评价中的应用研究[J].武汉大学学报:信息科学版,2018,43(6):959-964.
[13]谭玉敏,郭栋,白冰心,等.基于信息量模型的涪陵区地质灾害易发性评价[J].地球信息科学学报,2015,17(12):1554-1562.
[14]安凯强,牛瑞卿.信息量支持下SVM模型滑坡灾害易发性评价[J].长江科学院院报,2016,33(8):47-51,58.
[15]殷坤龙.滑坡灾害预测预报[M].武汉:中国地质大学出版社,2004.
[16] HANLEY J A, Mc NEIL B J. The meaning and use of the area undera receiver operating characteristic(ROC)curve[J]. Radiology,1982,143(1):29-36.
[2]赵洲,侯恩科,王建智,等.县域滑坡灾害风险管理信息系统研发与应用———以陕西省宁强县为例[J].工程地质学报,2012,20(2):170-182.
[3]王维早,雷霆,许强.基于层次分析法的河北省太行山区泥石流灾害危险性评估研究[J].地球与环境,2010,38(3):357-362.
[4]许冲,戴福初,姚鑫,等.基于GIS的汶川地震滑坡灾害影响因子确定性系数分析[J].岩石力学与工程学报,2010,29(S1):2972-2981.
[5]王念秦,薛瑶琼,李少兵,等.基于粗糙集理论的泥石流易发性综合评判模型[J].水土保持研究,2014,21(3):246-250.
[6]刘艺梁,殷坤龙,刘斌.逻辑回归和人工神经网络模型在滑坡灾害空间预测中的应用[J].水文地质工程地质,2010,37(5):92-96.
[7]王哲,易发成,陈廷方.基于模糊综合评判的绵阳市地质灾害易发性评价[J].科技导报,2012,30(31):53-60.
[8] ZHOU Chao, YIN Kunlong, CAO Ying, et al. Application of time se-ries analysis and PSO-SVM model in predicting the Bazimen landslidein the Three Gorges Reservoir, China[J]. Engineering Geology,2016,204(2):108-120.
[9] CHEN Wei, POURGHASEMI H R, KORNEJADY A, et al. Land-slide spatial modeling:Introducing new ensembles of ANN, Max Ent,and SVM machine learning techniques[J]. Geoderma,2017,305(6):314-327.
[10]黄发明,殷坤龙,蒋水华,等.基于聚类分析和支持向量机的滑坡易发性评价[J].岩石力学与工程学报,2018,37(1):156-167.
[11]张兴龙.基于CA-Markov的滑坡易发性动态预测模型研究[D].成都:成都理工大学,2017.
[12]刘渊博,牛瑞卿,于宪煜,等.旋转森林模型在滑坡易发性评价中的应用研究[J].武汉大学学报:信息科学版,2018,43(6):959-964.
[13]谭玉敏,郭栋,白冰心,等.基于信息量模型的涪陵区地质灾害易发性评价[J].地球信息科学学报,2015,17(12):1554-1562.
[14]安凯强,牛瑞卿.信息量支持下SVM模型滑坡灾害易发性评价[J].长江科学院院报,2016,33(8):47-51,58.
[15]殷坤龙.滑坡灾害预测预报[M].武汉:中国地质大学出版社,2004.
[16] HANLEY J A, Mc NEIL B J. The meaning and use of the area undera receiver operating characteristic(ROC)curve[J]. Radiology,1982,143(1):29-36.