旋转森林模型在滑坡易发性评价中的应用研究
|
摘要
以三峡库区万州段为研究区,从多源空间数据中提取29个致灾因子作为区域滑坡易发性分析的评价指标,在数字高程模型基础上采用集水区重叠法划分斜坡单元,构建旋转森林集成学习模型,定量预测滑坡空间易发性,并生成滑坡易发性分区图。在易发性分区图中,高易发区占11.6%,主要分布在万州主城区和长江及支流两岸;不易发区占45.6%,主要分布在人类工程活动低、植被覆盖度高的区域。采用受访者工作特征曲线和曲线下面积对旋转森林模型的滑坡易发性进行评价,结果显示该模型的预测精度为90.7%,其预测能力优于C4.5决策树。研究表明,应用旋转森林进行滑坡易发性评价具有预测能力强、精度高等优点。
Focusing on Wanzhou region of the Three Gorges Reservoir,29 hazard factors were extracted from the multi-source spatial data used in evaluation factors in landslide susceptibility analysis.The study area was partitioned into slope units from digital elevation model to resample the conditioning factors.A rotation forest model was trained and used to map landslide susceptibility with the best accuracy being 90.7%,according to the receiver operator characteristic(ROC)curve and area under the curve(AUC).The higher susceptibility zones were about 11.6% of the total area,and primarily distributed in the main Wanzhou city zone,and along both sides of the Yangtze River and its tributaries.The stability zones are accounted for about 45.6%,mainly distributed in the areas of low human engineering activities and high surface cover degree.The results show that application of rotation forest in the landslide susceptibility assessment exhibits both excellent prediction ability and high accuracy.
Focusing on Wanzhou region of the Three Gorges Reservoir,29 hazard factors were extracted from the multi-source spatial data used in evaluation factors in landslide susceptibility analysis.The study area was partitioned into slope units from digital elevation model to resample the conditioning factors.A rotation forest model was trained and used to map landslide susceptibility with the best accuracy being 90.7%,according to the receiver operator characteristic(ROC)curve and area under the curve(AUC).The higher susceptibility zones were about 11.6% of the total area,and primarily distributed in the main Wanzhou city zone,and along both sides of the Yangtze River and its tributaries.The stability zones are accounted for about 45.6%,mainly distributed in the areas of low human engineering activities and high surface cover degree.The results show that application of rotation forest in the landslide susceptibility assessment exhibits both excellent prediction ability and high accuracy.
引文
[1]Huang Runqiu,Xu Qiang.China Typical Catastrophic Landslide[M].Beijing:Science Press,2008(黄润秋,许强.中国典型灾难性滑坡[M].北京:科学出版社,2008)
[2]Yin Kunlong,Zhang Guirong,Chen Lixia,et al.Landslide Risk Assessment[M].Beijing:Science Press,2010(殷坤龙,张桂荣,陈丽霞,等.滑坡灾害风险分析[M].北京:科学出版社,2010)
[3]Dou J,Yamagishi H,Pourghasemi H,et al.An Integrated Artificial Neural Network Model for the Landslide Susceptibility Assessment of Osado Island,Japan[J].Natural Hazards,2015,78(3):1 749-1 776
[4]Tan Long,Chen Guan,Zeng Runqiang,et al.Application of Artificial Neural Network in Landslide Susceptibility Assessment[J].Journal of Lanzhou University(Natural Sciences),2014,50(1):15-20(谭龙,陈冠,曾润强,等.人工神经网络在滑坡敏感性评价中的应用[J].兰州大学学报(自然科学版),2014,50(1):15-20)
[5]Tehrany M,Pradhan B,Mansor S,et al.Flood Susceptibility Assessment Using GIS-based Support Vector Machine Model with Different Kernel Types[J].Catena,2015,125(125):91-101
[6]Niu Ruiqing,Peng Ling,Ye Runqing,et al.Landslide Susceptibility Assessment Based on Rough Sets and Support Vector Machine[J].Journal of Jilin University(Earth Science Edition),2012,42(2):430-439(牛瑞卿,彭令,叶润青,等.基于粗糙集的支持向量机滑坡易发性评价[J].吉林大学学报(地球科学版),2012,42(2):430-439)
[7]Tsangaratos P,Ilia I.Landslide Susceptibility Mapping Using a Modified Decision Tree Classifier in the Xanthi Perfection,Greece[J].Landslides,2016,13(2):305-320
[8]Hong H,Pradhan B,Xu C,et al.Spatial Prediction of Landslide Hazard at the Yihuang Area(China)Using Two-class Kernel Logistic Regression,Alternating Decision Tree and Support Vector Machines[J].Catena,2015,133(133):266-281
[9]Li Ting,Tian Yuan,Wu Lun,et al.Landslide Susceptibility Mapping Using Random Forest[J].Geography and Geo-Information Science,2014,30(6):25-30(李亭,田原,邬伦,等.基于随机森林方法的滑坡灾害危险性区划[J].地理与地理信息科学,2014,30(6):25-30)
[10]Liu Ben.The Research on Ensembles Method and Its Application on Remote Sensing Image Classification[D].Dalian:Dalian University of Technology,2014(刘贲.集成方法研究及其在遥感分类中的应用[D].大连:大连理工大学,2014)
[11]Ozcift A,Gulten A.Classifier Ensemble Construction with Rotation Forest to Improve Medical Diagnosis Performance of Machine Learning Algorithms[J].Computer Methods and Programs in Biomedicine,2011,104(3):443-451
[12]Liu Yaqing,Lu Huijuan,Du Bangjun,et al.Study on Classifier Algorithm of Genetic Data Based on Rotation Forest[J].Journal of China University of Metrology,2015,26(2):227-231(刘亚卿,陆慧娟,杜帮俊,等.面向基因数据分类的旋转森林算法研究[J].中国计量学院学报,2015,26(2):227-231)
[13]Ao Pei,Li He,Zhao Sifang,et al.Analog Circuit Fault Diagnosis Based on Improved Integrated ELM[J].Electronics World,2014,20(20):89-90(敖培,李贺,赵四方,等.基于集成改进ELM的模拟电路故障诊断[J].电子世界,2014,20(20):89-90)
[14]Shao Liangshan,Ma Han.Study on Classifier Ensemble Algorithm Based on Rotation Forest[J].Computer Engineering and Applications,2015,51(23):149-154(邵良杉,马寒.基于旋转森林的分类器集成算法研究[J].计算机工程与应用,2015,51(23):149-154)
[15]Rodríguez J,Kuncheva L,Alonso C J.Rotation Forest:A New Classifier Ensemble Method[J].IEEE Transactions on Pattern Analysis&Machine Intelligence,2006,28(10):1 619-1 630
[16]Hu Qiufen,Wang Gang,Wang Shimei,et al.Evaluation and Regionalization of Landslide Geological Disaster in Wanzhou City,Three Goreges Reservoir Area[J].Journal of China Three Gorges Univ(Natural Sciences),2006,38(1):20-25(胡秋芬,王刚,王世梅,等.三峡库区万州滑坡地质灾害危险性评价与区划[J].三峡大学学报(自然科学版),2016,38(1):20-25)
[17]Zhang Jun,Yin Kunlong,Wang Jiajia,et,al.Evaluation of Landslide Susceptibility for Wanzhou District of Three Gorges Reservoir[J].Chinese Journal of Rock Mechanics and Engineering,2016,35(2):284-296(张俊,殷坤龙,王佳佳,等.三峡库区万州区滑坡灾害易发性评价研究[J].岩石力学与工程学报,2016,35(2):284-296)
[18]Zeng Zhongping,Fu Xiaolin,Liu Xuemei,et al.Mapping and Quantitative Analysis on the Correlation Between Landslide and Geometric Alignment of Strikes of Slope and Stratum Based on GIS[J].Geography and Geo-Information Science,2006,22(1):22-25(曾忠平,付小林,刘雪梅,等.GIS支持下滑坡斜坡类型定量化及制图研究[J].地理与地理信息科学,2006,22(1):22-25)
[19]Huang Dengqi.Regional Landslide Stability Evaluation Based on FUZZY of GIS[J].Prospect of Science and Technology,2016,6(6):128-129(黄登琪.基于GIS的FUZZY在区域滑坡稳定性评价中的应用[J].科技展望,2016,6(6):128-129)
[20]Wu Xueling,Ren Fu,Niu Ruiqing,et al.Landslide Spatial Prediction Based on Slope Units and Support Vector Machines[J].Geomatics and Information Science of Wuhan University,2013,38(12):1 499-1 503(武雪玲,任福,牛瑞卿,等.斜坡单元支持下的滑坡易发性评价支持向量机模型[J].武汉大学学报·信息科学版,2013,38(12):1499-1503)
[21]Kuncheva L,Rodríguez J.An Experimental Study on Rotation Forest Ensembles[M].Heidelberg,Berlin:Springer,2007
[22]Yu X,Wang Y,Niu R,et al.A Combination of Geographically Weighted Regression,Particle Swarm Optimization and Support Vector Machine for Landslide Susceptibility Mapping:A Case Study at Wanzhou in the Three Gorges Area,China[J].International Journal of Environmental Research and Public Health,2016,13(5):487-521
[23]Hanley J,Mcneil B.The Meaning and Use of the Area Under a Receiver Operating Characteristic(ROC)Curve[J].Radiology,1982,143(1):29-36
[2]Yin Kunlong,Zhang Guirong,Chen Lixia,et al.Landslide Risk Assessment[M].Beijing:Science Press,2010(殷坤龙,张桂荣,陈丽霞,等.滑坡灾害风险分析[M].北京:科学出版社,2010)
[3]Dou J,Yamagishi H,Pourghasemi H,et al.An Integrated Artificial Neural Network Model for the Landslide Susceptibility Assessment of Osado Island,Japan[J].Natural Hazards,2015,78(3):1 749-1 776
[4]Tan Long,Chen Guan,Zeng Runqiang,et al.Application of Artificial Neural Network in Landslide Susceptibility Assessment[J].Journal of Lanzhou University(Natural Sciences),2014,50(1):15-20(谭龙,陈冠,曾润强,等.人工神经网络在滑坡敏感性评价中的应用[J].兰州大学学报(自然科学版),2014,50(1):15-20)
[5]Tehrany M,Pradhan B,Mansor S,et al.Flood Susceptibility Assessment Using GIS-based Support Vector Machine Model with Different Kernel Types[J].Catena,2015,125(125):91-101
[6]Niu Ruiqing,Peng Ling,Ye Runqing,et al.Landslide Susceptibility Assessment Based on Rough Sets and Support Vector Machine[J].Journal of Jilin University(Earth Science Edition),2012,42(2):430-439(牛瑞卿,彭令,叶润青,等.基于粗糙集的支持向量机滑坡易发性评价[J].吉林大学学报(地球科学版),2012,42(2):430-439)
[7]Tsangaratos P,Ilia I.Landslide Susceptibility Mapping Using a Modified Decision Tree Classifier in the Xanthi Perfection,Greece[J].Landslides,2016,13(2):305-320
[8]Hong H,Pradhan B,Xu C,et al.Spatial Prediction of Landslide Hazard at the Yihuang Area(China)Using Two-class Kernel Logistic Regression,Alternating Decision Tree and Support Vector Machines[J].Catena,2015,133(133):266-281
[9]Li Ting,Tian Yuan,Wu Lun,et al.Landslide Susceptibility Mapping Using Random Forest[J].Geography and Geo-Information Science,2014,30(6):25-30(李亭,田原,邬伦,等.基于随机森林方法的滑坡灾害危险性区划[J].地理与地理信息科学,2014,30(6):25-30)
[10]Liu Ben.The Research on Ensembles Method and Its Application on Remote Sensing Image Classification[D].Dalian:Dalian University of Technology,2014(刘贲.集成方法研究及其在遥感分类中的应用[D].大连:大连理工大学,2014)
[11]Ozcift A,Gulten A.Classifier Ensemble Construction with Rotation Forest to Improve Medical Diagnosis Performance of Machine Learning Algorithms[J].Computer Methods and Programs in Biomedicine,2011,104(3):443-451
[12]Liu Yaqing,Lu Huijuan,Du Bangjun,et al.Study on Classifier Algorithm of Genetic Data Based on Rotation Forest[J].Journal of China University of Metrology,2015,26(2):227-231(刘亚卿,陆慧娟,杜帮俊,等.面向基因数据分类的旋转森林算法研究[J].中国计量学院学报,2015,26(2):227-231)
[13]Ao Pei,Li He,Zhao Sifang,et al.Analog Circuit Fault Diagnosis Based on Improved Integrated ELM[J].Electronics World,2014,20(20):89-90(敖培,李贺,赵四方,等.基于集成改进ELM的模拟电路故障诊断[J].电子世界,2014,20(20):89-90)
[14]Shao Liangshan,Ma Han.Study on Classifier Ensemble Algorithm Based on Rotation Forest[J].Computer Engineering and Applications,2015,51(23):149-154(邵良杉,马寒.基于旋转森林的分类器集成算法研究[J].计算机工程与应用,2015,51(23):149-154)
[15]Rodríguez J,Kuncheva L,Alonso C J.Rotation Forest:A New Classifier Ensemble Method[J].IEEE Transactions on Pattern Analysis&Machine Intelligence,2006,28(10):1 619-1 630
[16]Hu Qiufen,Wang Gang,Wang Shimei,et al.Evaluation and Regionalization of Landslide Geological Disaster in Wanzhou City,Three Goreges Reservoir Area[J].Journal of China Three Gorges Univ(Natural Sciences),2006,38(1):20-25(胡秋芬,王刚,王世梅,等.三峡库区万州滑坡地质灾害危险性评价与区划[J].三峡大学学报(自然科学版),2016,38(1):20-25)
[17]Zhang Jun,Yin Kunlong,Wang Jiajia,et,al.Evaluation of Landslide Susceptibility for Wanzhou District of Three Gorges Reservoir[J].Chinese Journal of Rock Mechanics and Engineering,2016,35(2):284-296(张俊,殷坤龙,王佳佳,等.三峡库区万州区滑坡灾害易发性评价研究[J].岩石力学与工程学报,2016,35(2):284-296)
[18]Zeng Zhongping,Fu Xiaolin,Liu Xuemei,et al.Mapping and Quantitative Analysis on the Correlation Between Landslide and Geometric Alignment of Strikes of Slope and Stratum Based on GIS[J].Geography and Geo-Information Science,2006,22(1):22-25(曾忠平,付小林,刘雪梅,等.GIS支持下滑坡斜坡类型定量化及制图研究[J].地理与地理信息科学,2006,22(1):22-25)
[19]Huang Dengqi.Regional Landslide Stability Evaluation Based on FUZZY of GIS[J].Prospect of Science and Technology,2016,6(6):128-129(黄登琪.基于GIS的FUZZY在区域滑坡稳定性评价中的应用[J].科技展望,2016,6(6):128-129)
[20]Wu Xueling,Ren Fu,Niu Ruiqing,et al.Landslide Spatial Prediction Based on Slope Units and Support Vector Machines[J].Geomatics and Information Science of Wuhan University,2013,38(12):1 499-1 503(武雪玲,任福,牛瑞卿,等.斜坡单元支持下的滑坡易发性评价支持向量机模型[J].武汉大学学报·信息科学版,2013,38(12):1499-1503)
[21]Kuncheva L,Rodríguez J.An Experimental Study on Rotation Forest Ensembles[M].Heidelberg,Berlin:Springer,2007
[22]Yu X,Wang Y,Niu R,et al.A Combination of Geographically Weighted Regression,Particle Swarm Optimization and Support Vector Machine for Landslide Susceptibility Mapping:A Case Study at Wanzhou in the Three Gorges Area,China[J].International Journal of Environmental Research and Public Health,2016,13(5):487-521
[23]Hanley J,Mcneil B.The Meaning and Use of the Area Under a Receiver Operating Characteristic(ROC)Curve[J].Radiology,1982,143(1):29-36