[1]管家琳a,黄炎和a,林金石a,等.基于信息量模型与随机森林模型的崩岗风险对比评估[J].山地学报,2021,(4):539-551.[doi:10.16089/j.cnki.1008-2786.000618]
　GUAN Jialina,HUANG Yanhea,LIN Jinshia,et al.Comparisons Between Benggang Risk Assessments Based on Information Model and Random Forest Model[J].Mountain Research,2021,(4):539-551.[doi:10.16089/j.cnki.1008-2786.000618]
点击复制

基于信息量模型与随机森林模型的崩岗风险对比评估()
分享到：

《山地学报》[ISSN:1008-2186/CN:51-1516]

卷:
期数:
2021年第4期
页码:
539-551
栏目:
山地灾害
出版日期:
2021-07-25

文章信息/Info

Title:
Comparisons Between Benggang Risk Assessments Based on Information Model and Random Forest Model
文章编号:
1008-2786-(2021)4-539-13
作者:
管家琳a; 黄炎和a; 林金石a; 蒋芳市a; 姚莹莹b; 季 翔b*
福建农林大学 a.资源与环境学院; b.公共管理学院,福州 350002
Author(s):
GUAN Jialina;  HUANG Yanhea;  LIN Jinshia;  JIANG Fangshia;  YAO Yingyingb;  JI Xiangb*
a.College of Resources and Environment; b.College of Public Management, Fujian Agriculture and Forestry University, Fuzhou 350002, China
关键词:
崩岗;  信息量模型;  随机森林模型;  龙门镇;  模型对比
Keywords:
Benggang;  Information model;  Random Forest model;  Longmen Town;  model comparisons
分类号:
S157
DOI:
10.16089/j.cnki.1008-2786.000618
文献标志码:
A
摘要:
崩岗是发生在我国南部地区一种典型的水土流失现象,对其进行风险评估有利于崩岗防控。建立崩岗风险评估体系和崩岗评估模型是崩岗风险评估的基础,而不同的评估模型对崩岗风险的评估结果存在差异。探究不同模型在崩岗风险评估中的应用差异,提高预测精度是目前亟需解决的问题。本研究以福建省安溪县龙门镇小流域为例,根据风险因子与崩岗发生之间的关系选择出主要因子,分别运用信息量模型与随机森林模型对崩岗进行风险评估,对比两种方法的优缺点,进一步探究较优的崩岗风险评估方法。结果表明:(1)信息量模型与随机森林模型均适用于研究区的崩岗发生风险评估,基于随机森林模型对崩岗发生风险的预测精度高于信息量模型(AUC值分别为0.89和0.81),混淆矩阵准确率达到84.09%,且泛化能力较好;(2)高程、地形起伏度、坡度和河网缓冲距离因子是崩岗发生的重要风险因子;(3)2个模型预测的崩岗风险空间分布大致相同,约83%的风险区等级面积趋于一致,且以中、高风险为主。研究结果表明随机森林模型的预测性能总体较信息量模型优,可用于未来崩岗发生的风险评估,为崩岗的防治工作提供参考。
Abstract:
Benggang represents a typical soil erosion phenomenon in the granite region of Southern China, characterized by considerable erosion and extreme landform changes. Different assessment models for Benggang risk exhibited different results, which requires a thorough comparison on their accuracy for the purpose of Benggang control. The establishment of a risk assessment system with a proper model is a prerequisite for Benggang risk assessment. And the differences in the applications of these models should be further determined for promotion of prediction accuracy. In this study, a small watershed in Longmen Town, Anxi county, Fujian province was targeted as case study for Benggang risk assessment. Main factors were selected in the case based on the relationship between risk factors and Benggang events. It compared the advantages and disadvantages between an Information model and a Random Forest model in the process of Bengang risk evaluation, to find out which model had a better performance. The results show that:(1)Both the Information model and the Random Forest model were applicable to the risk assessment of Benggang in the study area; however, the prediction accuracy of the Random Forest model for the risk of Benggang was higher than that of the Information model(AUC values were 0.89 and 0.81, respectively). The accuracy of the confusion matrix for the Random Forest model reached 84.09% with a better generalization ability.(2)Elevation, topographic relief, slope and river buffer distance mattered for the occurrence of Benggang.(3)The distribution of risk space of Benggang predicted by the two models was equivalent; approximately 83% of the risk areas were of the same level, dominated by medium-risk and high-risk. These study found that the prediction performance of the Random Forest model was generally better than that of the Information model. Random forest model is recommended to be used for Benggang assessment and control in the future.

参考文献/References:

[1] 廖义善,唐常源,袁再健,等. 南方红壤区崩岗侵蚀及其防治研究进展[J]. 土壤学报,2018,55(6):1297-1312. [LIAO Yishan, TANG Changyuan, YUAN Zaijian, et al. Research progress on Benggang erosion and its prevention measure in red soil region of Southern China [J]. Acta Pedologica Sinica, 2018, 55(6): 1297-1312] DOI: 10.11766/trxb201807030219
[2] 冯明汉,廖纯艳,李双喜,等. 我国南方崩岗侵蚀现状调查[J]. 人民长江,2009,40(8):66-68+75. [FENG Minghan, LIAO Chunyan, LI Shuangxi, et al. Investigation on status of hill collapsing and soil erosion in southern China [J]. Yangtze River, 2009, 40(8):66-68+75] DOI: 10.16232/j.cnki.1001-4179.2009.08.025
[3] 陈嘉林. 福建省典型崩岗区潜在性崩岗风险评估与预测[D]. 福州: 福建农林大学,2015:42-54. [CHEN Jialin. Risk evaluation and simulation of the potential collapsing hills in Fujian typical collapsed area [D]. Fuzhou: FuJian Agriculture and Forestry University, 2015:42-54]
[4] 程冬兵,赵元凌,张平仓,等. 基于Logistic模型的江西省崩岗侵蚀风险评估[J]. 中国水土保持科学,2017,15(6):106-116. [CHENG Dongbing, ZHAO Yuanling, ZHANG Pingcang, et al. On the risk assessment of collapse gully erosion in Jiangxi province based on Logistic model [J]. Science of Soil and Water Conservation, 2017, 15(6):106-116] DOI:10.16843/j.sswc.2017.06.013
[5] 程冬兵,赵元凌,张平仓,等. 基于双变量熵信息法的江西省崩岗侵蚀风险评估[J]. 长江科学院院报,2019,36(2):27-32+38. [CHENG Dongbing, ZHAO Yuanling, ZHANG Pingcang, et al. Risk assessment of collapse gully erosion in Jiangxi province based on bivariate statistical analysis of entropy information [J]. Journal of Yangtze River Scientific Research Institute, 2019, 36(2):27-32+38] DOI: 10.11988/ckyyb.20170984
[6] 季翔,黄炎和,林金石,等. 崩岗侵蚀沟的时空侵蚀特征及预测[J]. 山地学报,2019,37(1):86-97. [JI Xiang, HUANG Yanhe, LIN Jinshi, et al. Spatio-temporal erosion features and prediction for the erosion gullies on collapsing hills [J]. Mountain Research, 2019, 37(1):86-97] DOI: 10.16089 /j.cnki.1008-2786.000402
[7] 季翔,黄炎和,林金石,等.基于生态位适宜度的南方花岗岩区崩岗发生敏感性评价方法[J]. 中国农业大学学报,2017,22(10):159-168. [JI Xiang, HUANG Yanhe, LIN Jinshi, et al. Sensitivity assessment method of collapsed gully occurrence in granite region of South China based on niche-fitness [J]. Journal of China Agricultural University, 2017, 22(10):159-168] DOI: 10.11841/j.issn.1007-4333.2017.10.19
[8] 杜晓晨,陈莉,陈廷芳. 基于GIS的凉山州德昌县滑坡危险性评价[J]. 长江流域资源与环境,2020,29(5):1206-1215. [DU Xiaochen, CHEN Li, CHEN Tingfang. Hazard assessment of landslide in Dechang county of Liangshan state based on GIS [J]. Resources and Environment in the Yangtze Basin, 2020, 29(5):1206-1215] DOI: 10.11870 /cjlyzyyhj202005016
[9] 陈立华,李立丰,吴福,等. 基于GIS与信息量法的北流市地质灾害易发性评价[J]. 地球与环境,2020,48(4):471-479. [CHEN Lihua, LI Lifeng, WU Fu, et al. Evaluation of the geological hazard vulnerability in the Beiliu city based on GIS and information value mode [J]. Earth and Environment, 2020, 48(4):471-479] DOI: 10.14050/j.cnki.1672-9250.2020.48.060
[10] WANG Jing, SHI Leiyu. Prediction of medical expenditures of diagnosed diabetics and the assessment of its related factors using a random forest model, MEPS 2000-2015 [J]. International Journal for Quality in Health Care, 2020, 32(2):99-112. DOI: 10.1093/intqhc/ mzz135
[11] 李曼,李园园,刘焕才. 阿克苏河流域中下游生态系统服务价值对土地利用变化的响应[J]. 内蒙古农业大学学报(自然科学版),2020,41(3):33-37. [LI Man, LI Yuanyuan, LIU Huancai. The response of ecosystem services value to land use change in the middle and lower reaches of AKSU river basin [J]. Journal of Inner Mongolia Agricultural University(Natural Science Edition), 2020, 41(3):33-37] DOI: 10.16853 /j.cnki.1009-3575.2020.03.007
[12] 王李娟,孔钰如,杨小冬,等. 基于特征优选随机森林算法的农耕区土地利用分类[J]. 农业工程学报,2020,36(4):244-250. [WANG Lijuan, KONG Yuru, YANG Xiaodong, et al, Classification of land use in farming areas based on feature optimization random forest algorithm [J]. Transactions of the Chinese Society of Agricultural Engineering, 2020, 36(4):244-250] DOI: 10.11975/j.issn. 1002-6819.2020.04.029
[13] 余坤勇,姚雄,邱祈荣,等. 基于随机森林模型的山体滑坡空间预测研究[J]. 农业机械学报,2016,47(10):338-345. [YU Kunyong, YAO Xiong, QIU Qirong, et al. Landslide spatial prediction based on random forest model [J]. Transactions of the Chinese Society of Agricultural Machinery, 2016, 47(10):338-345] DOI: 10.6041 /j.issn.1000-1298.2016.10.043
[14] SUN Deliang, WEN Haijia, WANG Danzhou, et al. A random forest model of landslide susceptibility mapping based on hyperparameter optimization using Bayes algorithm [J]. Geomorphology, 2020, 362:107201. DOI: 10.1016/j.geomorph.2020.107201
[15] DOU Jie, YUNUS A P, BUI D T, et al. Assessment of advanced random forest and decision tree algorithms for modeling rainfall-induced landslide susceptibility in the Izu-Oshima Volcanic Island, Japan [J]. Science of the Total Environment, 2019, 662:332-346. DOI: 10.1016/j.scitotenv.2019.01.221
[16] 贾南,陈悦,康可霖,等. 基于RF的森林火灾风险评价模型及其应用研究[J]. 安全与环境学报,2020,20(4):1236-1240. [JIA Nan, CHEN Yue, KANG Kelin, et al. Improved forest fire risk assessment model and its application based on the RF algorithm [J]. Journal of Safety and Environment, 2020, 20(4):1236-1240] DOI: 10.13637 /j.issn.1009-6094.2019.0899
[17] 曹正风. 随机森林算法优化研究[D]. 北京:首都经济贸易大学,2014:12-27. [CAO Zhengfeng. Study on optimization of random forests algorithm [D]. Beijing: Capital University of Economics and Business, 2014:12-27]
[18] 陈晓安,杨洁,肖胜生,等. 崩岗侵蚀分布特征及其成因[J]. 山地学报,2013,31(6):716-722. [CHEN Xiaoan, YANG Jie, XIAO Shengsheng, et al. Distribution characteristics and causes of collapse erosion [J]. Mountain Research, 2013, 31(6):716-722] DOI: 10.16089/j.cnki.1008-2786.2013.06.016
[19] 李万能,金平伟,李岚斌,等. 南方红壤丘陵区崩岗成因机理的研究进展[J]. 亚热带水土保持,2014,26(3):30-33+43. [LI Wanneng, JIN Pingwei, LI Lanbin, et al. Research progress on the genetic mechanism of collapsing gullies in red soil hilly region of South China [J]. Subtropical Soil and Water Conservation, 2014, 26(3):30-33+43]
[20] 林敬兰,黄炎和,林金石,等. 福建省崩岗侵蚀的地质地貌背景分析[J]. 亚热带水土保持,2014,26(4):1-5. [LIN Jinglan, HUANG Yanhe, LIN Jinshi, et al. Background analysis on the geology and land form of collapse erosion in Fujian province [J]. Subtropical Soil and Water Conservation, 2014, 26(4):1-5]
[21] DENG Yusong, DUAN Xiaoqian, DING Shuwen, et al. Effect of joint structure and slope direction on the development of collapsing gully in tuffaceous sandstone area in South China [J]. International Soil and Water Conservation Research, 2020, 8(2):131-140. DOI: 10.1016/j.iswcr.2020.04.003
[22] 熊传祥,王涛,鲁晓兵.降雨作用下崩岗形成细观机理模拟[J]. 山地学报,2013,31(6):710-715. [XIONG Chuanxiang, WANG Tao, LU Xiaobing. Meso-mechanical simulation of slope disintegration erosion under rainfall [J]. Mountain Research, 2013, 31(6):710-715] DOI: 10.16089/j.cnki.1008-278 6.2013.06.015
[23] 章智,陈洁,林金石,等. 含水率对安溪县花岗岩崩岗土体胀缩特性的影响[J]. 土壤学报,2020,57(3):600-609. [ZHANG Zhi, CHEN Jie, LIN Jinshi, et al. Effect of water content on swell-shrink characteristics of collapsed granite soil in Anxi county [J]. Acta Pedologica Sinica, 2020, 57(3):600-609] DOI: 10.11766/trxb201903230072
[24] 管家琳,贾秀菊,季翔. 基于信息量模型的西溪流域崩岗风险评估[J]. 森林与环境学报,2020,40(3):321-328. [GUAN Jialin, JIA Xiuju, JI Xiang. Risk assessment of collapsing gullies in the Xixi watershed based on information model [J]. Journal of Forest and Environment, 2020, 40(3):321-328] DOI: 10.13324 /j.cnki.jfcf.2020.03.013
[25] BREIMAN L. Random forests [J]. Machine Learning, 2001, 45(1):5-32. DOI: 10.1023/A:1010933404324
[26] 方匡南,吴见彬,朱建平,等. 随机森林方法研究综述[J]. 统计与信息论坛,2011,26(3):32-38. [FANG Kuangnan, WU Jianbin, ZHU Jianping, et al. A review of technologies on random forests [J]. Statistics and Information Forum, 2011, 26(3):32-38]
[27] 吴孝情,赖成光,陈晓宏,等. 基于随机森林权重的滑坡危险性评价:以东江流域为例[J]. 自然灾害学报,2017,26(5):119-129. [WU Xiaoqing, LAI Chengguang, CHEN Xiaohong, et al. A landslide hazard assessment based on random forest weight: A case study in the Dongjiang River Basin [J]. Journal of Natural Disasters, 2017, 26(5):119-129] DOI: 10.13577/j.jnd.2017.0514
[28] 李文彦,王喜乐. 频率比与信息量模型在黄土沟壑区滑坡易发性评价中的应用与比较[J]. 自然灾害学报,2020,29(4):213-220. [LI Wenyan, WANG Xile. Application and comparison of frequency ratio and information value model for evaluating landslide susceptibility of loess gully region [J]. Journal of Natural Disasters, 2020, 29(4):213-220] DOI: 10.13577/j.jnd.2020.0422
[29] 张晓东,刘湘南,赵志鹏,等. 信息量模型、确定性系数模型与逻辑回归模型组合评价地质灾害敏感性的对比研究[J]. 现代地质,2018,32(3):602-610. [ZHANG Xiaodong, LIU Xiangnan, ZHAO Zhipeng, et al. Comparative study of geological hazards susceptibility assessment: Constraints from the information value + logistic regression model and the CF + logistic regression model [J]. Geoscience, 2018, 32(3):602-610] DOI: 10.19657/j.geoscience.1000-8527.2018.03.18
[30] 彭珂,彭红霞,梁峰,等. 基于信息量模型的赣州市地质灾害易发性分区[J]. 安全与环境工程,2018,25(5):22-28. [PENG Ke, PENG Hongxia, LIANG Feng, et al. Susceptibility zoning of geo-hazards in Ganzhou city based on the information model [J]. Safety and Environmental Engineering, 2018, 25(5):22-28] DOI: 10.13578/j.cnki.issn.1671-1556.2018.05.004
[31] 袁培森,曹益飞,马千里,等. 基于Random Forest的水稻细菌性条斑病识别方法研究[J]. 农业机械学报,2021,52(1):139-145+208. [YUAN Peisen, CAO Yifei, MA Qianli, et al. Identification method of rice bacterial leaf streak based on random forest [J]. Transactions of the Chinese Society for Agricultural Machinery, 2021, 52(1):139-145+208] DOI: 10.6041/j.issn.1000-1298.2021.01.015
[32] 刘坚,李树林,陈涛. 基于优化随机森林模型的滑坡易发性评价[J]. 武汉大学学报(信息科学版),2018,43(7):1085-1091. [LIU Jian, LI Shulin, CHEN Tao. Landslide susceptibility assessment based on optimized random forest model [J]. Geomatics and Information Science of Wuhan University, 2018, 43(7):1085-1091] DOI: 10.13203/j.whugis20160515
[33] ARABAMERI A, PRADHAN B, REZAEI K. Gully erosion zonation mapping using integrated geographically weighted regression with certainty factor and random forest models in GIS [J]. Journal of Environmental Management, 2019, 232:928-942. DOI: 10.1016/j.jenvman.2018.11.110

相似文献/References:

[1]熊传祥,王涛,鲁晓兵,等.降雨作用下崩岗形成细观机理模拟[J].山地学报,2013,(06):710.
　XIONG Chuanxiang,WANG Tao,LU Xiaobing.Mesomechanical Simulation of Slope Disintegration Erosion Under Rainfall[J].Mountain Research,2013,(4):710.
[2]王彦华,谢先德,王春云.风化花岗岩崩岗灾害的成因机理[J].山地学报,2000,(06):496.
[3]阮伏水.福建省崩岗侵蚀与治理模式探讨[J].山地学报,2003,(06):675.
[4]谢小康,范国雄.广东五华乌陂河流域崩岗发育规律及其治理——以迎龙山为例[J].山地学报,2010,(03):294.
[5]邹 强,唐建喜,李淑松,等.基于水文响应单元的泥石流灾害易发性分区方法[J].山地学报,2017,(04):496.[doi:10.16089/j.cnki.1008-2786.000247]
　ZOU Qiang,*,TANG jianxi,et al.Susceptibility Assessment Method of Debris Flows Based on Hydrological Response Unit[J].Mountain Research,2017,(4):496.[doi:10.16089/j.cnki.1008-2786.000247]
[6]季翔,黄炎和*,林金石,等.崩岗侵蚀沟的时空侵蚀特征及预测[J].山地学报,2019,(01):86.[doi:10.16089/j.cnki.1008-2786.000402]
　JI Xiang,HUANG Yanhe*,LIN Jinshi,et al.Spatio-temporal Erosion Features and Prediction for the Erosion Gullies on Collapsing Hills[J].Mountain Research,2019,(4):86.[doi:10.16089/j.cnki.1008-2786.000402]
[7]林小慧,何 玥,黄炎和,等.“三生空间”视角下基于云模型的崩岗侵蚀危害评价[J].山地学报,2024,(3):411.[doi:10-16089/j.cnki.1008-2786.000833]
　LIN Xiaohui,HE Yue,HUANG Yanhe,et al.Cloud Model-Based Assessment of Benggang Erosion Hazard in the Red Soil Area of South China from a Production-Living-Ecology Space Perspective[J].Mountain Research,2024,(4):411.[doi:10-16089/j.cnki.1008-2786.000833]

备注/Memo

备注/Memo:
收稿日期(Received date):2020-11-02; 改回日期(Accepted data):2021-07-20
基金项目(Foundation item):国家自然科学基金(41601557; 41571272); 福建农林大学杰出青年科研人才计划项目(XJQ201933)。[National Natural Science Foundation of China(41601557; 41571272); Funds for Distinguished Young Scholar of Fujian Agriculture and Forestry University( XJQ201933)]
作者简介(Biography):管家琳(1996-),女,江苏盐城人,硕士研究生,主要研究方向:水土保持与风险评估。[GUAN Jialin(1996-),female,born in Yancheng,Jiangsu province, M. Sc. candidate, research on water and soil conservation and risk assessment] E-mail: 1430716868@qq.com
*通讯作者(Corresponding author):季翔(1984-),女,博士,讲师,主要研究方向:土地可持续利用、土壤侵蚀与评价。[JI Xiang(1984-),female,Ph. D.,lecturer,research on landscape ecology and collapsing gully erosion] E-mail:jixiangss@126.com
更新日期/Last Update: 2021-07-30