融合随机森林模型和6种水体指数的上海市水体信息提取

doi:10.13474/j.cnki.11-2246.2022.0052

测绘通报 ›› 2022, Vol. 0 ›› Issue (2): 106-109.doi: 10.13474/j.cnki.11-2246.2022.0052

融合随机森林模型和6种水体指数的上海市水体信息提取

崔青林^1,2,3, 汪鸣泉^1,3, 黄永健^1,2,3

1. 中国科学院上海高等研究院上海碳数据与碳评估中心, 上海 201210;
2. 中国科学院大学, 北京 100049;
3. 中国科学院低碳转化科学与工程重点实验室, 上海 201210

收稿日期:2021-04-22 发布日期:2022-03-11
通讯作者: 黄永健。E-mail:huangyj@sari.ac.cn
作者简介:崔青林(1996-),女,硕士生,研究方向为多源卫星遥感数据处理与应用。E-mail:cuiqinglin2019@sari.ac.cn
基金资助:
上海市科技创新行动计划社会发展科技攻关项目（20dz1204302）；国家自然科学基金（51778601）

Water information extraction in Shanghai by integrating random forest model and six water indices

CUI Qinglin^1,2,3, WANG Mingquan^1,3, HUANG Yongjian^1,2,3

1. Shanghai Carbon Data Research Center, Shanghai Advanced Research Institute, Chinese Academy of Sciences, Shanghai 201210, China;
2. University of Chinese Academy of Sciences, Beijing 100049, China;
3. Key Laboratory of Low-carbon Conversion Science and Engineering, Chinese Academy of Sciences, Shanghai 201210, China

Received:2021-04-22 Published:2022-03-11

摘要/Abstract

摘要： 为快速、准确地掌握水体分布信息，本文以上海市为研究区，基于多时相Sentinel-2卫星数据构建水体提取特征集，并采用效率高、稳健性好的随机森林模型，对研究区内的水体进行提取。水体提取特征集在现有光谱波段特征的基础上加入6种水体指数，分别为NDWI、MNDWI、AWEI_sh、WI₂₀₁₅、SWI和RWI，旨在提高水体提取精度。针对10个光谱波段特征及6种水体指数，设计了8种试验方案探究加入水体指数对于水体提取的作用。结果表明，将6种水体指数全部加入的方案精度最高，为97.910%；NDWI和RWI能提高水体提取精度、降低漏提率和误提率。

关键词: 水体信息提取, 随机森林, Sentinel-2, 水体指数, 上海市

Abstract: In order to know water distribution information quickly and accurately, this paper selects Shanghai as the study area，constructs a feature set of water extraction based on multi-temporal Sentinel-2 satellite data, uses random forest model with high efficiency and good robustness to extract water in Shanghai. To improve the accuracy of water extraction, six water indices are added into the feature set of water extraction based on the characteristics of existing spectral bands: NDWI、MNDWI、AWEI_sh、WI₂₀₁₅、SWI and RWI. According to the characteristics of 10 spectral bands and 6 water indices, eight experimental schemes are designed to explore the effect of adding water indexes on water extraction. The results show that the scheme which included all the six water indices has the highest overall accuracy, which is 97.910%. NDWI and RWI can also improve the accuracy of water extraction and reduce the rate of leakage and error.

Key words: water information extraction, RF model, Sentinel-2, water index, Shanghai city

中图分类号:

P237

崔青林, 汪鸣泉, 黄永健. 融合随机森林模型和6种水体指数的上海市水体信息提取[J]. 测绘通报, 2022, 0(2): 106-109.

CUI Qinglin, WANG Mingquan, HUANG Yongjian. Water information extraction in Shanghai by integrating random forest model and six water indices[J]. Bulletin of Surveying and Mapping, 2022, 0(2): 106-109.

参考文献

[1] 金建文,李国元,孙伟,等.卫星遥感水资源调查监测应用现状及展望[J].测绘通报, 2020(5):7-10.
[2] 田颖,陈卓奇,惠凤鸣,等.欧空局哨兵卫星Sentinel-2A/B数据特征及应用前景分析[J].北京师范大学学报(自然科学版), 2019, 55(1):57-65.
[3] 龚燃.哨兵-2A光学成像卫星发射升空[J].国际太空, 2015(8):36-40.
[4] KAPLAN G,AVDAN U.Object-based water body extraction model using Sentinel-2 satellite imagery[J].European Journal of Remote Sensing,2017,50(1):137-143.
[5] BREIMAN L.Random forests[J]. Machine Learning, 2001,45(1):5-32.
[6] 张磊,宫兆宁,王启为,等. Sentinel-2影像多特征优选的黄河三角洲湿地信息提取[J].遥感学报, 2019, 23(2):313-326.
[7] 何云,黄翀,李贺,等.基于Sentinel-2A影像特征优选的随机森林土地覆盖分类[J].资源科学, 2019,41(5):992-1001.
[8] 张卫春,刘洪斌,武伟.基于随机森林和Sentinel-2影像数据的低山丘陵区土地利用分类:以重庆市江津区李市镇为例[J].长江流域资源与环境, 2019, 28(6):1334-1343.
[9] 王德军,姜琦刚,李远华,等.基于Sentinel-2A/B时序数据与随机森林算法的农耕区土地利用分类[J].国土资源遥感, 2020, 32(4):236-243.
[10] LI Dan, WU Baosheng, CHEN Bowei, et al. Open-surface River extraction based on sentinel-2 MSI imagery and DEM data:case study of the upper Yellow River[J]. Remote Sensing, 2020, 12(17):2737.
[11] ZHANG Lin, LIU Zhe, REN Tianwei, et al. Identification of seed maize fields with high spatial resolution and multiple spectral remote sensing using random forest classifier[J]. Remote Sensing, 2020, 12(3):362.
[12] MCFEETERS S K. The use of the Normalized Difference Water Index (NDWI) in the delineation of open water features[J]. International Journal of Remote Sensing, 1996, 17(7):1425-1432.
[13] 徐涵秋.利用改进的归一化差异水体指数(MNDWI)提取水体信息的研究[J].遥感学报, 2005, 9(5):589-595.
[14] FEYISA G L, MEILBY H, FENSHOLT R, et al. Automated Water Extraction Index:a new technique for surface water mapping using Landsat imagery[J]. Remote Sensing of Environment, 2014, 140:23-35.
[15] FISHER A, FLOOD N, DANAHER T. Comparing Landsat water index methods for automated water classification in eastern Australia[J]. Remote Sensing of Environment, 2016, 175:167-182.
[16] 吴庆双,汪明秀,申茜,等.基于Sentinel-2遥感图像的细小水体提取方法研究[J].遥感学报, 2019,23(5):871-882.
[17] JIANG W, NI Y, PANG Z, et al. A new index for identifying water body from sentinel-2 satellite remote sensing imagery[J]. ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences, 2020:33-38.
[18] 成方龙,赵冠伟,杨木壮,等.集成地理探测器与随机森林模型的城市人口分布格网模拟[J].测绘通报, 2020(1):76-81.
[19] WA AŚNIEWSKI A, HO AŚCI?O A, ZAGAJEWSKI B, et al. Assessment of sentinel-2 satellite images and random forest classifier for rainforest mapping in Gabon[J]. Forests, 2020, 11(9):941.
[20] WANG Xiaoxue, GAO Xiangwei, ZHANG Yuanzhi, et al. Land-cover classification of coastal wetlands using the RF algorithm for worldview-2 and landsat 8 images[J]. Remote Sensing, 2019, 11(16):1927.
[21] 林晓萍.基于国产卫星影像的自然资源动态监测[J].测绘通报, 2020(11):28-32.

融合随机森林模型和6种水体指数的上海市水体信息提取

Water information extraction in Shanghai by integrating random forest model and six water indices

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价

[1]	孔瑞瑶, 谢涛, 马明, 孔瑞林. CatBoost模型在水深反演中的应用[J]. 测绘通报, 2022, 0(7): 33-37.
[2]	吕峥, 孙群, 温伯威, 马京振. 一种自身全局最优的道路网Stroke生成方法[J]. 测绘通报, 2022, 0(7): 93-99.
[3]	王春霞, 张俊, 李屹旭, 范成成. 一种基于Landsat 8的多波段组合水体指数模型[J]. 测绘通报, 2022, 0(5): 20-25.
[4]	郁宗桥, 王育红, 刘文宋, 左雨芳, 冯锋. 顾及GF-3影像纹理特征的洪涝范围提取方法[J]. 测绘通报, 2022, 0(5): 26-31.
[5]	窦世卿, 陈治宇, 徐勇, 郑贺刚, 苗林林, 宋莹莹. 基于多特征融合与典型降维方法的高光谱影像分类[J]. 测绘通报, 2022, 0(4): 32-36,50.
[6]	冯志立, 肖锋, 卢小平, 郝波, 王如意, 朱睿. 基于随机森林特征优选的冬小麦分类方法[J]. 测绘通报, 2022, 0(3): 70-75.
[7]	王刚, 丁华祥. Sentinel-2A数据支持下的雷州半岛植被类型识别[J]. 测绘通报, 2022, 0(3): 76-82.
[8]	王晓晓, 韩留生, 杨骥, 李勇, 张大富, 孙广伟, 范俊甫. Sentinel-2与Landsat 8数据组合下的多特征冬小麦面积提取[J]. 测绘通报, 2022, 0(3): 111-115.
[9]	高雨, 胡召玲, 樊茹. 高分辨率影像融合算法对滨海湿地土地利用分类精度的影响[J]. 测绘通报, 2022, 0(1): 116-120.
[10]	穆超, 刘振宇, 孟丹. 基于Sentinel-2卫星数据的内陆湖泊水体大气校正[J]. 测绘通报, 2021, 0(9): 9-14.
[11]	李军, 桑潇, 张成业, 赵伟, 刘新华, 王宏鹏, 王金阳, 李佳瑶, 杨颖. 资源型城市长时间序列土壤含水量变化分析——以锡林浩特市为例[J]. 测绘通报, 2021, 0(7): 17-22,38.
[12]	陶莉, 胡召玲. 利用Sentinel-2A数据提取长江中下游丘陵地带农作物种植信息[J]. 测绘通报, 2021, 0(7): 39-43.
[13]	刘茂华, 李曼雯. 融合高分影像和LiDAR数据的城市道路提取[J]. 测绘通报, 2021, 0(6): 1-5,60.
[14]	古春霞, 李大成. 时空融合技术在区域地表覆盖时序分类中的应用[J]. 测绘通报, 2021, 0(5): 20-24.
[15]	苏美臣, 魏晓燕, 周峻松, 汪祎勤. 金沙江流域滑坡易发性空间预报分析[J]. 测绘通报, 2021, 0(4): 13-16.