Taking Panzhihua City as an Example.Evaluation of Landslide Susceptibility Based on MaxEnt Model[J].Research of Soil and Water Conservation,2021,28(02):224-229.
基于MaxEnt模型的滑坡易发性评价——以攀枝花市为例
- Title:
- Evaluation of Landslide Susceptibility Based on MaxEnt Model
- 文章编号:
- 1005-3409(2021)02-0224-06
- 关键词:
- 最大熵(maxEnt)模型; ArcGIS; 滑坡; 易发性; 攀枝花市
- Keywords:
- maximum entropy(maxEnt)model; ArcGIS; landslide; susceptibility; Panzhihua City
- 分类号:
- P642.22
- 文献标志码:
- A
- 摘要:
- 为了客观评价滑坡影响因子的贡献度和构建滑坡预测模型,以滑坡灾害发生较多的攀枝花市为研究区,通过筛选后选取高程、坡度、坡向、土地利用类型、归一化植被指数(NDVI)和人口密度6项因子作为滑坡易发性的评价指标; 基于最大熵(maxEnt)模型和ArcGIS空间分析模块对研究区滑坡易发性进行了定量预测和分析研究。结果表明:maxEnt模型在研究区滑坡易发性研究方面的适用性等级为优秀(AUC=0.96),Kappa系数为0.86; 随机选取75%的数据集用于训练模型,其余25%用于验证模型,得到的AUC值最稳定且精度最高,模型预测可信度最高; 研究区高易发生和极易发生区分别占总面积的2.57%,0.80%,主要分布在人口比较密集的东部和西部地区,部分沿着金沙江、雅砻江、巴关河、安宁河和主要道路两侧发育; 植被覆盖度和坡度是决定研究区滑坡易发性空间分布格局最重要的环境影响因子。
- Abstract:
- In order to objectively evaluate the contribution of landslide impact factors and build landslide prediction model, Panzhihua City, which has more landslide disasters, was selected as the research area in this study. Six factors including elevation, slope, slope direction, land use, normalized difference vegetation index(NDVI)and population density were selected as evaluation indexes for landslide susceptibility in this paper. Based on the maximum entropy(maxEnt)model and ArcGIS spatial analysis module, the landslide susceptibility in the study area was predicted and analyzed quantitatively. The results show that the applicability of the maxEnt model based on the object unit in the study area for landslide susceptibility is rated as excellence(AUC=0.96), and the Kappa coefficient is 0.86; the AUC value is the most stable and accurate, and the model prediction has the highest credibility when 75% of the data sets are randomly selected to train the model, and the remaining 25% are used to verify the model; The high-prone and high-prone areas in the study area account for 2.57% and 0.80% of the total area, respectively, which mainly distribute in the densely populated eastern and western areas, along the main roads of Jinsha River, Yalong River, Banguan River, Anning River and Panzhihua City; among the influencing factors of landslide susceptibility, vegetation cover and slope are the most important geographical environment factors that determine the spatial distribution pattern of landslide susceptibility in this study area.
参考文献/References:
[1] 张国平,徐晶,毕宝贵.滑坡和泥石流灾害与环境因子的关系[J].应用生态学报,2009,20(3):653-658.
[2] Ilanloo M. A comparative study of fuzzy logic approach for landslide susceptibility mapping using GIS: An experience of Karaj dam basin in Iran[J]. Procedia-Social and Behavioral Sciences, 2011,19:668-676.
[3] 武雪玲,沈少青,牛瑞卿. GIS支持下应用PSO-SVM模型预测滑坡易发性[J].武汉大学学报:信息科学版,2016,41(5):665-671.
[4] 任敬,范宣梅,赵程,等.贵州省都匀市滑坡易发性评价研究[J].水文地质工程地质,2018,45(5):165-172.
[5] 吴玮莹.云南鲁甸地震滑坡易发性分析[D].北京:中国地震局地震预测研究所,2018.
[6] 许英姿,卢玉南,李东阳,等.基于GIS和信息量模型的广西花岗岩分布区滑坡易发性评价[J].工程地质学报,2016,24(4):693-703.
[7] 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.
[8] Mokarram M, Zarei A R. Landslide susceptibility mapping using fuzzy-AHP[J].Geotechnical and Geological Engineering,2018,36(6):3931-3943.
[9] Akgun A, Dag S, Bulut F. Landslide susceptibility mapping for a landslide-prone area(Findikli, NE of Turkey)by likelihood-frequency ratio and weighted linear combination models[J]. Environmental Geology, 2008,54(6):1127-1143.
[10] Akgun A, Cem K, Pradhan B. Application of remote sensing data and GIS for landslide risk assessment as an environmental threat to Izmir city(west Turkey)[J]. Environmental Monitoring & Assessment, 2012,184(9):5453-5470.
[11] Pradhan B, Lee S. Regional landslide susceptibility analysis using back-propagation neural network model at Cameron Highland, Malaysia[J]. Landslides, 2010,7(1):13-30.
[12] Pradhan B. Landslide susceptibility mapping of a catchment area using frequency ratio, fuzzy logic and multivariate logistic regression approaches[J]. Journal of the Indian Society of Remote Sensing, 2010,38(2):301-320.
[13] Lee S, Min K. Statistical analysis of landslide susceptibility at Yongin, Korea[J]. Environmental Geology, 2001,40(9):1095-1113.
[14] Pourghasemi H R, Mohammady M, Pradhan B. Landslide susceptibility mapping using index of entropy and conditional probability models in GIS: Safarood Basin, Iran[J]. Catena,2012,97(15):71-84.
[15] Merow C, Smith M J, Silander J A. A practical guide to maxEnt for modeling species' distributions: what it does, and why inputs and settings matter[J]. Ecography,2013,36(10):1058-1069.
[16] 叶永昌,周广胜,殷晓洁.1961—2010年内蒙古草原植被分布和生产力变化:基于maxEnt模型和综合模型的模拟分析[J].生态学报,2016,36(15):4718-4728.
[17] 黄旭,李跃清,王峰.攀枝花市旅游气候资源分析及开发建议[J].高原山地气象研究,2002,22(2):42-45.
[18] 李石桥,许俊豪,曹亚廷,等.四川省攀枝花市炳密滑坡特征及成因分析[J].地质灾害与环境保护,2017,28(4):1-6.
[19] 彭盛恩.攀枝花市滑坡分布及分区特征[C]∥中国地质学会工程地质专业委员会.第四届全国工程地质大会论文选集(一).工程地质学报编辑部,1992.
[20] 王喜娜,黄华兵,班亚,等.GIS辅助下滑坡灾害危险性区划图的绘制:以四川省攀枝花市为例[J].测绘通报,2015(2):46-50.
[21] 张丽,何晓旭,魏鸣.基于NDVI的淮河流域植被覆盖度动态变化[J].长江流域资源与环境,2012,21(S1):51-56.
[22] Swets J A. Measuring the accuracy of diagnostic systems [J]. Science,1988,240(4857):1285-1293.
[23] 陈新美,雷渊才,张雄清,等.样本量对maxEnt模型预测物种分布精度和稳定性的影响[J].林业科学,2012,48(1):53-59.
备注/Memo
收稿日期:2019-12-19 修回日期:2020-05-19
资助项目:国家自然科学基金(41961044); 云南省科技厅—云南大学“双一流”建设联合资助项目(2018FY001-017)
第一作者:屈新星(1997—),女,河南登封人,硕士研究生,研究方向为区域环境变化及其生态响应。E-mail:1550609927@qq.com
通信作者:何云玲(1978—),女,云南大理人,博士,副教授,主要从事区域环境变化及其生态响应研究。E-mail:hyl610@126.com