FAN Tiancheng,JIA Yunfei,LI Yunfei,et al.Prediction of Gully Distribution Probability in Yanhe Basin Based on Remote Sensing Image and Logistic Regression Model[J].Research of Soil and Water Conservation,2022,29(04):316-321.
基于遥感影像与逻辑回归模型的延河流域沟壑分布概率预测
- Title:
- Prediction of Gully Distribution Probability in Yanhe Basin Based on Remote Sensing Image and Logistic Regression Model
- 文章编号:
- 1005-3409(2022)04-0316-06
- Keywords:
- remote sensing image; gully distribution; logistic regression model; multiple-factor; Yanhe Basin; Loess Plateau
- 分类号:
- P208
- 文献标志码:
- A
- 摘要:
- 为研究黄土高原沟壑地貌空间分布特征,开展了基于遥感影像和机器学习的沟壑地貌提取,研究了延河流域沟壑地貌空间分布及其环境控制因子。以Google Earth Pro平台为支撑,在人工提取大量沟壑地貌样本的基础上,基于Landsat8 OLI影像波段信息,采用主成分分析前3个变量、缨帽变换前3个变量、NDVI、高程、坡度和坡向10个因子,使用逻辑回归模型预测整个延河流域的沟壑概率分布。结果表明:(1)在10个变量因子中,因子Brightness的R2McF为0.158,重要性最大,因子elevation的R2McF为3.6×10-5,重要性最小;(2)最优逻辑回归模型由组合因子Brightness,PCA1,Greenness,Wetness,PCA3和slope确定,其重要性R2McF为0.206;(3)最优逻辑回归模型的沟壑概率预测精度为73.72%,ROC曲线下面积即AUC值为0.80;(4)延河流域沟壑地貌约占整个延河流域面积的52.05%。研究表明,延河流域沟壑分布呈现从西北方向到东南方向逐渐集中的特点。
- Abstract:
- In order to study the spatial distribution characteristics of gully landform on the Loess Plateau, remote sensing images and machine learning were used to extract gully landform, and the spatial distribution and environmental control factors of gully landform in the Yanhe Basin were studied. We estimated the probability of gully distribution based on a large number of gully samples extracted manually from Google Earth Pro platform and the logical regression model. Based on the Landsat8-OLI image, we established 10 environmental and spectrum factors, including the first three variables of principal component analysis, the first three variables of Landsat8-OLI transform, NDVI, elevation, slope as well as aspect, to calibrate the logistic regression method. Then, the model was used to predict the probability distribution of gullies in the entire Yanhe Basin. The results show that:(1)among the 10 variables, the most important factor is brightness with the R2McF of 0.158, while elevation has the lowest contribution with the R2McF of 3.6×10-5;(2)the optimal logistic regression model is determined by the combined factors of Brightness, PCA1, Greenness, Wetness, PCA3 and slope, and its overall R2McF is 0.206;(3)the accuracy of the optimal logistic regression model is 73.72% and the AUC value of the ROC curve is 0.80, which indicates that the model has relatively higher accuracy to estimate the distribution of gully on the Loess Plateau;(4)the gully landform accounts for 52.05% of the total areas of Yanhe Basin. The study shows that the distribution of gullies in Yanhe Basin gradually concentrates from northwest to southeast.
参考文献/References:
[1] 姚文艺,肖培青.黄土高原土壤侵蚀规律研究方向与途径[J].水利水电科技进展,2012,32(2):73-78.
[2] 高海东,李占斌,李鹏,等.基于土壤侵蚀控制度的黄土高原水土流失治理潜力研究[J].地理学报,2015,70(9):1503-1515.
[3] Zhao J, Vanmaercke M, Chen L, et al. Vegetation cover and topography rather than human disturbance control gully density and sediment production on the Chinese Loess Plateau[J]. Geomorphology,2016,274:92-105.
[4] 王庆,李智广,高云飞,等.基于DEM及高分辨率遥感影像的西北黄土高原区侵蚀沟道普查[J].中国水土保持,2013(10):61-64.
[5] Broeckx J, Vanmaercke M, Duchateau R, et al. A data-based landslide susceptibility map of Africa [J]. Earth-Science Reviews, 2018,185:102-121.
[6] Vanmaercke M, Chen Y, Haregeweyn N, et al. Predicting gully densities at sub-continental scales: A case study for the Horn of Africa[J]. Earth Surface Processes and Landforms, 2020,45(15):3763-3779.
[7] 胡涛,樊鑫,王硕,等.基于逻辑回归模型和3S技术的思南县滑坡易发性评价[J].地质科技通报,2020,39(2):113-121.
[8] 陈黔,李晓松,修晓敏,等.基于Google Earth Engine与机器学习的大尺度30 m分辨率沙地灌木覆盖度估算[J].生态学报,2019,39(11):4056-4069.
[9] 修晓敏,周淑芳,陈黔,等.基于Google Earth Engine与机器学习的省级尺度零散分布草地生物量估算[J].测绘通报,2019(3):46-52.
[10] 杨敏,林杰,顾哲衍,等.基于Landsat 8 OLI多光谱影像数据和BP神经网络的叶面积指数反演[J].中国水土保持科学,2015,13(4):86-93.
[11] 刘婷,周自翔,朱青,等.延河流域生态系统土壤保持服务时空变化[J].水土保持研究,2021,28(1):93-100.
[12] 朱青,周自翔,刘婷,等.黄土高原植被恢复与生态系统土壤保持服务价值增益研究:以延河流域为例[J].生态学报,2021,41(7):2557-2570.
[13] 夏岩,张姝琪,高文冰,等.黄土高原变绿对黄河中游延河流域径流演变的影响估算[J].地球科学与环境学报,2020,42(6):849-860.
[14] 苗连朋,温仲明,张莉.植被变化与水沙响应关系研究:以延河流域为例[J].干旱区资源与环境,2015,29(5):75-81.
[15] 邱新彩,郑冬梅,王海宾,等.结合地统计学与Landsat 8影像的乔木林地上碳储量估算[J].中南林业科技大学学报,2020,40(11):138-146.
[16] 岳程鹏,李兴,包龙山,等.基于Landsat 8 OLI遥感数据反演乌梁素海浮游植物生物量[J].灌溉排水学报,2020,39(8):122-128.
[17] 傅姣琪,陈超,郭碧云.缨帽变换的遥感图像水边线信息提取方法[J].测绘科学,2019,44(5):177-183.
[18] 陈晔,何政伟,邓辉,等.利用ASTER影像识别和提取矿化蚀变信息[J].桂林理工大学学报,2014,34(1):51-57.
[19] Pontius R G, Schneider L C. Land-cover change model validation by an ROC method for the Ipswich watershed, Massachusetts, USA [J]. Agriculture, Ecosystems and Environment, 2001,85:239-248.
[20] 丁琳,刘辉.延河流域沟壑密度统计学特征及影响因素分析[J].安徽农学通报,2016,22(14):108-110,116.
相似文献/References:
[1]段峥,宋现锋,石敏俊.密云县土地利用景观格局时空变化及驱动力分析[J].水土保持研究,2009,16(05):55.
DUAN Zheng,SONG Xian-feng,SHI Min-jun.Changes of Spatial Landscape Pattern and Driving Forces in Miyun County During 1992-2006[J].Research of Soil and Water Conservation,2009,16(04):55.
[2]郭晓清,郑粉莉,万培余.基于多期遥感影像的森林资源动态监测研究——以延安市桥北林业局直罗林场为例[J].水土保持研究,2011,18(06):46.
GUO Xiao-qing,ZHENG Fen-li,WAN Pei-yu.Dynamic Monitoring on Forest Resources Based on Multi-period Remote Sensing Image -Taking Zhiluo Forest Farm in Yan’an City as an Example[J].Research of Soil and Water Conservation,2011,18(04):46.
[3]程承旗,常鹏飞,郭仕德,等.空气总悬浮颗粒物浓度的遥感信息模型研究[J].水土保持研究,2006,13(06):243.
CHENG Cheng-qi,CHANG Peng-fei,GUO Shi-de,et al.Research on Remote Sensing Information Model for Total Suspended Particles and Case Study[J].Research of Soil and Water Conservation,2006,13(04):243.
[4]张雨果,王飞,孙文义,等.基于面向对象的SPOT卫星影像梯田信息提取研究[J].水土保持研究,2016,23(06):345.
ZHANG Yuguo,WANG Fei,SUN Wenyi,et al.Terrace Information Extraction From SPOT Remote Sensing Image Based on Object-oriented Classification Method[J].Research of Soil and Water Conservation,2016,23(04):345.
[5]王文杰,张永福,王慧杰.基于GIS干旱区绿洲县域土地利用变化生态风险分析——以新疆泽普县为例[J].水土保持研究,2016,23(06):216.
WANG Wenjie,ZHANG Yongfu,WANG Huijie.Analysis on Ecological Risk of Land Use at County Level in the Arid Oasis Base on GIS—A Case Study in Zepu of Xinjiang[J].Research of Soil and Water Conservation,2016,23(04):216.
[6]李玉珍,张永福,安放舟.基于GIS的新和县土地利用生态风险分析[J].水土保持研究,2015,22(01):172.
LI Yuzhen,ZHANG Yongfu,AN Fangzhou.Analysis on Ecological Risk of Land Use in Xinhe County Based on GIS[J].Research of Soil and Water Conservation,2015,22(04):172.
[7]李小曼,王刚.DEM支持的黄土丘陵沟壑区地被遥感分类方法[J].水土保持研究,2013,20(03):110.
LI Xiao-man,WANG Gang.Research on DEM Based on Remote Sensing Classification Method in Loess Hilly Ravine Area[J].Research of Soil and Water Conservation,2013,20(04):110.
[8]吴楠,张永福,李瑞.基于景观指数的干旱区河谷县域土地利用生态风险分析及预测[J].水土保持研究,2018,25(02):207.
WU Nan,ZHANG Yongfu,LI Rui.Ecological Risk Analysis and Prediction of Land Use in Arid Valley Based on Landscape Index[J].Research of Soil and Water Conservation,2018,25(04):207.
[9]张佳瑜,白林波,杨美玲.银川市近30年城市扩展时空演变[J].水土保持研究,2019,26(05):359.
ZHANG Jiayu,BAI Linbo,YANG Meiling.Spatial and Temporal Evolution of Yinchuan Urban Expansion in the Last 30 Years[J].Research of Soil and Water Conservation,2019,26(04):359.
备注/Memo
收稿日期:2021-08-16 修回日期:2021-09-17
资助项目:国家自然科学基金(41907048); 中央高校基本科研费专项资金(300102260206)
第一作者:范天程(1997—),男,山西临汾人,硕士研究生,研究方向为生态遥感应用。E-mail:2020226008@chd.edu.cn
通信作者:赵建林(1988—),男,陕西镇巴人,讲师,主要从事土壤侵蚀与区域生态评价研究。E-mail:jianlin.zhao@chd.edu.cn