基于决策树的高山区堰塞湖水体提取方法: 以中巴公路Attabad堰塞湖为例

李有三; 曹广超; 赵美亮; 冶文倩; 祁万强; 杨鸿魁; 毋远召; 谷强; 陆裕国; 王仕林

doi:10.19509/j.cnki.dzkq.tb20240125

基于决策树的高山区堰塞湖水体提取方法: 以中巴公路Attabad堰塞湖为例

doi: 10.19509/j.cnki.dzkq.tb20240125

李有三^{1, 2,},
曹广超^1, ,,
赵美亮¹,
冶文倩¹,
祁万强²,
杨鸿魁^{1, 2},
毋远召²,
谷强²,
陆裕国²,
王仕林³

1.
青海师范大学地理科学学院青海省自然地理与环境过程重点实验室, 西宁 810008
2.
中国地质调查局西宁自然资源综合调查中心, 西宁 810000
3.
中国石化西北油田分公司勘探开发研究院, 乌鲁木齐 830000

基金项目:

青海省创新平台建设专项 2020-ZJ-Y06

中国地质调查局地质调查项目 DD20242544

详细信息

作者简介:
李有三, E-mail: liyousan@mail.cgs.gov.cn

通讯作者:
曹广超, E-mail: caoguangchao@qhnu.edu.cn

中图分类号: P237;P343.3
计量
- 文章访问数: 45
- PDF下载量: 13
- 被引次数: 0
出版历程
- 收稿日期: 2024-03-28
- 录用日期: 2024-07-01
- 修回日期: 2024-05-30

A method for extracting water from barrier lake in high mountain areas based on decision tree classification: A case study of Attabad barrier lake on the Karakoram Highway

1.
Qinghai Province Key Laboratory of Physical Geography and Environmental Process, College of Geographical Science, Qinghai Normal University, Xining 810008, China
2.
Xining Natural Resources Comprehensive Survey Center, China Geological Survey, Xining 810000, China
3.
Exploitation and Production Research Institute of Northwest Branch of SINOPEC Corporation, Urumqi 830000, China

More Information

Author Bio:
LI Yousan, E-mail: liyousan@mail.cgs.gov.cn

Corresponding author: CAO Guangchao, E-mail: caoguangchao@qhnu.edu.cn

摘要

摘要:
堰塞湖水体动态监测对于堰塞湖的险情评估、灾害推演、安全管理以及降险处置决策等均具有重要意义。为了高效提取高山区堰塞湖真实水体范围, 以中巴公路Attabad堰塞湖为研究区, 利用决策树分类结合归一化差值水体指数(normalized difference water index, 简称NDWI)、综合水体指数(comprehensive water index, 简称CWI)等6种常规水体提取方法来提取堰塞湖水体范围, 并对比了6种方法用于堰塞湖水体提取的效果, 筛选出适用于高山区堰塞湖的最佳水体提取方法, 最后使用混淆矩阵法进行了精度评价, 并做了分类后处理, 准确提取了堰塞湖水体边界。研究结果表明: (1) 6种水体提取模型中CWI模型水体提取效果最好; (2)基于坡度的决策树分类方法总分类精度为89.31%, Kappa系数为0.84, 较为完整地提取了高海拔堰塞湖真实水体范围, 有效剔除了湖岸斜坡山体阴影, 湖泊边界较为清晰完整。基于决策树的高山区堰塞湖水体提取方法在高海拔山区能较为有效地提取真实水体范围, 尤其是针对地形切割强烈、山体阴影较多的堰塞湖区域, 能快速准确识别水体。该方法的优点是: 水体提取过程较为简单, 容易实现, 提取效率较高, 便于推广。
- 决策树分类模型 /
- Attabad堰塞湖 /
- 水体指数 /
- 中巴公路 /
- 水体提取方法
Abstract: <p>The water dynamics of barrier lakes in high mountain areas are crucial for risk assessment, disaster prediction, safety management, and decision-making. </p></sec><sec><title>Objective and Methods
To accurately and efficiently extract the water boundaries of mountainous barrier lakes, this paper focuses on the Attabad barrier lake along the Karakoram Highway, proposing a water extraction method based on decision tree classification. This method incorporates slope information into six conventional water extraction methods for decision tree classification. The effectiveness of these six methods was compared for extracting water from barrier lakes in the experimental area. The best-performing methods suitable for barrier lakes in high-altitude areas were applied to extract the water body range of the Attabad barrier lake.Accuracy was assessed using a confusion matrix, and classification post-processing was performed to refine the water boundary extraction.
Results
The research results indicate that (1) among the six models, the CWI model demonstrates the best performance, effectively distinguishing between slope, water, and shadow water, leading to a highly accurate outline of the barrier lake. However, a limitation of this model is the presence of a few mountain shadows in the middle of the slope. (2) The decision tree classification method based on slope achieved an overall accuracy of 89.31% and a kappa coefficient of 0.84. It effectively extracts the actual water range, excluding slope shoreline and mountain shadows, and provides a clearer lake boundary. Nevertheless, black fragments observed in the lower area of the barrier lake, likely due to landslides and mountain shadows, remained challenging to classify. Overall, the decision tree classification-based method proved effective in identifying water bodies, particularly in areas with rugged terrain and numerous shadows.
Conclusion
This paper proposes a method for extracting water bodies from barrier lakes in high mountain areas using decision tree classification. By incorporating slope information into conventional water body extraction methods, this approach accurately extracts the water boundary, effectively eliminates shadows from steep slopes, retain shadowed water on gentler slopes, and improves extraction efficiently. The simplicity and high extraction efficiency of this method make it a practical solution for widespread application.
- decision tree classification model /
- Attabad barrier lake /
- water body index /
- Karakoram Highway /
- water extraction mothod
注释:

所有作者声明不存在利益冲突。

HTML全文

图 1 Attabad堰塞湖位置图

Figure 1. Location map of Attabad barrier lake

下载: 全尺寸图片幻灯片

图 2 研究流程图

B₄、NDWI、ENDWI、CWI、C₃/NIR、SI均表示水体提取方法，其中B₄表示单波段B₄阈值法，NDWI表示归一化差值水体指数法，CWI表示综合水体指数法，ENDWI表示改进的归一化水体指数法，C₃/NIR表示彩色不变特征空间法，SI表示阴影指数法，下同

Figure 2. Research flow chart

下载: 全尺寸图片幻灯片

图 3 波谱特征曲线图(DN为地物的灰度值)

Figure 3. Spectrum characteristic curve

下载: 全尺寸图片幻灯片

图 4 决策树模型

Figure 4. Decision tree model

下载: 全尺寸图片幻灯片

图 5 各水体提取模型值域箱线图(其中SL表示斜坡；W表示水体；WS表示阴影水体)

Figure 5. Value range box diagram of each water extraction model

下载: 全尺寸图片幻灯片

图 6 各水体提取模型水体提取分类图

Figure 6. Extraction and classification of water bodies in each water extraction model

下载: 全尺寸图片幻灯片

图 7 基于决策树模型与CWI模型图像对比

Figure 7. Comparison of images based on decision tree classification and CWI models

下载: 全尺寸图片幻灯片

表 1 应用于高分辨率影像的6种水体提取模型

Table 1. Six water extraction models applied to high-resolution images

模型	方程	特征
B₄	b₄>R	R为根据研究区水体信息判断的经验阈值，特点是操作简单，便于实现
NDWI	$N D W I=\left(b_2-b_4\right) /\left(b_2+b_4\right)$	有效抑制非水体，但难以区分土壤和阴影
ENDWI	$\mathit{ENDWI}=\left(b_2-b_4\right) /\left(2 b_2\right)$	增强水体与冰雪、阴影的反差，减少背景噪音
CWI	$C W I=3 b_4-b_2-b_1$	抑制阴影
C₃/NIR	$C_3=\tan ^{-1}\left(b_1 / \max \left(b_3, b_2\right)\right), C_3 / b_4$	提取阴影，突出阴影中的水体
SI	$S I=\left(F C_3-P C I_1\right) /\left(F C_3+P C I_1\right)$	PCI₁为主成分变换后的第一分量；F为补偿系数，根据C₃PCI₁的值域经验判断得出F=1 000较为合适。特点是能突出阴影，增强水体信息
注：NDWI表示归一化差值水体指数；CWI表示综合水体指数；ENDWI表示改进的归一化水体指数；SI表示阴影指数法；b₁代表蓝波段；b₂代表绿波段；b₃代表红波段；b₄代表近红外波段；C₃代表彩色不变特征空间方法中的C₃分量; 下同

下载: 导出CSV

表 2 分类精度

Table 2. Classification accuracy

		分类类别			总计	用户精度/%
斜坡	阴影水体	水体			总计	用户精度/%
分类类别	斜坡	52	16	0	68	74.47
	阴影水体	0	34	0	34	100.00
	水体	0	1	56	57	98.25
总计		52	51	56	159	—
制图精度/%		100	66.67	100	—	—
注：总体精度为89.31%，Kappa系数为0.84

下载: 导出CSV

参考文献(49)

[1]	BAZAI N A, CUI P, CARLING P, et al. Increasing glacial lake outburst flood hazard in response to surge glaciers in the Karakoram[J]. Earth-Science Reviews, 2021, 212: 103432. doi: 10.1016/j.earscirev.2020.103432
[2]	高旭. 南天山大龙池堰塞体形成演化过程分析[J]. 地质科技通报, 2024, 43(1): 229-240. doi: 10.19509/j.cnki.dzkq.tb20230322 GAO X. Analysis of the formation and evolution process of the Dalongchi landslide dam in the South Tianshan Mountains[J]. Bulletin of Geological Science and Technology, 2024, 43(1): 229-240. (in Chinese with English abstract) doi: 10.19509/j.cnki.dzkq.tb20230322
[3]	CHEN X Q, CUI P, YOU Y, et al. Dam-break risk analysis of the Attabad landslide dam in Pakistan and emergency countermeasures[J]. Landslides, 2017, 14(2): 675-683. doi: 10.1007/s10346-016-0721-7
[4]	殷坤龙, 张宇, 汪洋. 水库滑坡涌浪风险研究现状和灾害链风险管控实践[J]. 地质科技通报, 2022, 41(2): 1-12. doi: 10.19509/j.cnki.dzkq.2022.0064 YIN K L, ZHANG Y, WANG Y. A review of landslide-generated waves risk and practice of management of hazard chain risk from reservoir landslide[J]. Bulletin of Geological Science and Technology, 2022, 41(2): 1-12. (in Chinese with English abstract) doi: 10.19509/j.cnki.dzkq.2022.0064
[5]	PAUL A, TRIPATHI D, DUTTA D. Application and comparison of advanced supervised classifiers in extraction of water bodies from remote sensing images[J]. Sustainable Water Resources Management, 2018, 4(4): 905-919. doi: 10.1007/s40899-017-0184-6
[6]	王承振. 中巴交通廊道滑坡堵江堰塞湖风险调控选线对策[D]. 成都: 西南交通大学, 2019. WANG C Z. Countermeasures of risk control and line selection for blocking river barrier lake caused by traffic corridor landslide between China and Pakistan[D]. Chengdu: Southwest Jiaotong University, 2019. (in Chinese with English abstract)
[7]	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. doi: 10.1016/j.rse.2013.08.029
[8]	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. doi: 10.1080/01431169608948714
[9]	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. XU H Q. A study on information extraction of water body with the modified normalized difference water index(MNDWI)[J]. National Remote Sensing Bulletin, 2005, 9(5): 589-595. (in Chinese with English abstract)
[10]	毕海芸, 王思远, 曾江源, 等. 基于TM影像的几种常用水体提取方法的比较和分析[J]. 遥感信息, 2012, 27(5): 77-82. BI H Y, WANG S Y, ZENG J Y, et al. Comparison and analysis of several common water extraction methods based on TM image[J]. Remote Sensing Information, 2012, 27(5): 77-82. (in Chinese with English abstract)
[11]	董哲, 王凌, 朱西存, 等. 光谱模型结合面向对象法的山区水体提取[J]. 遥感信息, 2022, 37(4): 121-127. DONG Z, WANG L, ZHU X C, et al. Water extraction in mountainous area based on spectral model and object-oriented method[J]. Remote Sensing Information, 2022, 37(4): 121-127. (in Chinese with English abstract)
[12]	张成才, 李艳桦, 姚亮亮. 面向对象的ETM +影像分割尺度与水体信息提取[J]. 人民黄河, 2014, 36(7): 54-56. ZHANG C C, LI Y H, YAO L L. Object-oriented method of water extraction based on ETM + images[J]. Yellow River, 2014, 36(7): 54-56. (in Chinese with English abstract)
[13]	段秋亚, 孟令奎, 樊志伟, 等. GF-1卫星影像水体信息提取方法的适用性研究[J]. 国土资源遥感, 2015, 27(4): 79-84. DUAN Q Y, MENG L K, FAN Z W, et al. Applicability of the water information extraction method based on GF-1 image[J]. Remote Sensing for Natural Resources, 2015, 27(4): 79-84. (in Chinese with English abstract)
[14]	都金康, 黄永胜, 冯学智, 等. SPOT卫星影像的水体提取方法及分类研究[J]. 遥感学报, 2001, 5(3): 214-219. DU J K, HUANG Y S, FENG X Z, et al. Study on water bodies extraction and classification from SPOT image[J]. National Remote Sensing Bulletin, 2001, 5(3): 214-219. (in Chinese with English abstract)
[15]	陈超, 傅姣琪, 随欣欣, 等. 面向灾后水体遥感信息提取的知识决策树构建及应用[J]. 遥感学报, 2018, 22(5): 792-801. CHEN C, FU J Q, SUI X X, et al. Construction and application of knowledge decision tree after a disaster for water body information extraction from remote sensing images[J]. National Remote Sensing Bulletin, 2018, 22(5): 792-801. (in Chinese with English abstract)
[16]	FRAZIER P S, PAGE K J. Water body detection and delineation with Landsat TM data[J]. Photogrammetric Engineering and Remote Sensing, 2000, 66(12): 1461-1467.
[17]	梁泽毓. 基于深度学习的多源遥感水体信息提取方法及其应用研究[D]. 合肥: 安徽大学, 2019. LIANG Z Y. Research on water information extraction method of multi-source remote sensing based on deep learning and its application[D]. Hefei: Anhui University, 2019. (in Chinese with English abstract)
[18]	王雪, 隋立春, 钟棉卿, 等. 全卷积神经网络用于遥感影像水体提取[J]. 测绘通报, 2018(6): 41-45. WANG X, SUI L C, ZHONG M Q, et al. Fully convolution neural networks for water extraction of remote sensing images[J]. Bulletin of Surveying and Mapping, 2018(6): 41-45. (in Chinese with English abstract)
[19]	廖旋芝, 熊显名, 张文涛. 基于ENVI/IDL的遥感影像阴影区域内水陆分割线的提取方法[J]. 桂林电子科技大学学报, 2016, 36(6): 500-503. LIAO X Z, XIONG X M, ZHANG W T. An approach for split line extraction of water and land from shadow area of remote sensing images based on ENVI/IDL[J]. Journal of Guilin University of Electronic Technology, 2016, 36(6): 500-503. (in Chinese with English abstract)
[20]	符雅盛, 张利华, 朱志儒, 等. 基于决策树-山体阴影模型的植被信息提取研究[J]. 长江流域资源与环境, 2020, 29(2): 386-393. FU Y S, ZHANG L H, ZHU Z R, et al. Using decision tree and hillshade method to improve the accuracy of vegetation classification[J]. Resources and Environment in the Yangtze Basin, 2020, 29(2): 386-393. (in Chinese with English abstract)
[21]	李文萍, 王伟, 高星, 等. 融合面向对象和分水岭算法的山地湖泊提取方法[J]. 地球信息科学学报, 2021, 23(7): 1272-1285. LI W P, WANG W, GAO X, et al. A lake extraction method in mountainous regions based on the integration of object-oriented approach and watershed algorithm[J]. Journal of Geo-Information Science, 2021, 23(7): 1272-1285. (in Chinese with English abstract)
[22]	OUMA Y O, TATEISHI R. A water index for rapid mapping of shoreline changes of five East African Rift Valley Lakes: An empirical analysis using Landsat TM and ETM+ data[J]. International Journal of Remote Sensing, 2006, 27(15): 3153-3181. doi: 10.1080/01431160500309934
[23]	沈占锋, 夏列钢, 李均力, 等. 采用高斯归一化水体指数实现遥感影像河流的精确提取[J]. 中国图象图形学报, 2013, 18(4): 421-428. SHEN Z F, XIA L G, LI J L, et al. Automatic and high-precision extraction of rivers from remotely sensed images with Gaussian normalized water index[J]. Journal of Image and Graphics, 2013, 18(4): 421-428. (in Chinese with English abstract)
[24]	LI Y S, YANG H K, QI Y H, et al. Changes in the hydrological characteristics of the attabad landslide-dammed lake on the karakoram highway[J]. Water, 2024, 16(5): 714.
[25]	SU X J, ZHANG Y, MENG X M, et al. Landslide mapping and analysis along the China-Pakistan Karakoram Highway based on SBAS-InSAR detection in 2017[J]. Journal of Mountain Science, 2021, 18(10): 2540-2564.
[26]	DING M H, HUAI B J, SUN W J, et al. Surge-type glaciers in Karakoram Mountain and possible catastrophes alongside a portion of the Karakoram Highway[J]. Natural Hazards, 2018, 90(2): 1017-1020.
[27]	KHAN H, SHAFIQUE M, KHAN M A, et al. Landslide susceptibility assessment using Frequency Ratio: A case study of northern Pakistan[J]. The Egyptian Journal of Remote Sensing and Space Science, 2019, 22(1): 11-24.
[28]	王冰, 安慧君, 刘怀鹏, 等. QuickBird影像城市阴影信息的提取与消除[J]. 地球信息科学学报, 2016, 18(2): 255-262. WANG B, AN H J, LIU H P, et al. Study on city shadow extraction and elimination in QuickBird images[J]. Journal of Geo-Information Science, 2016, 18(2): 255-262. (in Chinese with English abstract)
[29]	王冬梅, 陈琳, 冯峰. 面向对象的GF-2影像水体信息提取研究[J]. 人民黄河, 2021, 43(5): 80-83. WANG D M, CHEN L, FENG F. Study on water information extraction from GF-2 images based on object-oriented method[J]. Yellow River, 2021, 43(5): 80-83. (in Chinese with English abstract)
[30]	张强, 吴波, 杨艳魁. 一种结合坡度信息调节的水体指数[J]. 遥感信息, 2018, 33(4): 98-107. ZHANG Q, WU B, YANG Y K. Extraction of open water in rugged area with a novel slope adjusted water index[J]. Remote Sensing Information, 2018, 33(4): 98-107. (in Chinese with English abstract)
[31]	王灿星, 朱杰勇, 喻聪骏, 等. 基于皮尔逊Ⅲ型曲线的不同降雨工况下的崩滑地质灾害危险性评价. 地质科技通报: 1-11[2024-04-14]. https://doi.org/10.19509/j.cnki.dzkq.tb20230472. WANG C X, ZHU J Y, YU C J, et al. Risk assessment of landslide geological hazards under different rainfall conditions based on P-Ⅲ curve[J]. Bulletin of Geological Science and Technology: 1-11[2024-04-14]. https://doi.org/10.19509/j.cnki.dzkq.tb20230472. (in Chinese with English abstract)
[32]	邓开元, 任超. 多光谱光学遥感影像水体提取模型[J]. 测绘学报, 2021, 50(10): 1370-1379. DENG K Y, REN C. Water extraction model of multispectral optical remote sensing image[J]. Acta Geodaetica et Cartographica Sinica, 2021, 50(10): 1370-1379. (in Chinese with English abstract)
[33]	陈华芳, 王金亮, 陈忠, 等. 山地高原地区TM影像水体信息提取方法比较: 以香格里拉县部分地区为例[J]. 遥感技术与应用, 2004, 19(6): 479-484. CHEN H F, WANG J L, CHEN Z, et al. Comparison of water extraction methods in mountainous plateau region from TM image: Taking some areas of Shangri-La County as an example[J]. Remote Sensing Technology and Application, 2004, 19(6): 479-484. (in Chinese with English abstract)
[34]	程乾, 陈金凤. 基于高分1号杭州湾南岸滨海陆地土地覆盖信息提取方法研究[J]. 自然资源学报, 2015, 30(2): 350-360. CHENG Q, CHEN J F. Research on the extraction method of landcover information in southern coastal land of Hangzhou Bay based on GF-1 image[J]. Journal of Natural Resources, 2015, 30(2): 350-360.
[35]	王小标, 谢顺平, 都金康. 水体指数构建及其在复杂环境下有效性研究[J]. 遥感学报, 2018, 22(2): 360-372. WANG X B, XIE S P, DU J K. Water index formulation and its effectiveness research on the complicated surface water surroundings[J]. National Remote Sensing Bulletin, 2018, 22(2): 360-372. (in Chinese with English abstract)
[36]	YU Q, GONG P, CLINTON N, et al. Object-based detailed vegetation classification with airborne high spatial resolution remote sensing imagery[J]. Photogrammetric Engineering & Remote Sensing, 2006, 72(7): 799-811.
[37]	SUI H G, CHEN G, HUA L. An automatic integrated image segmentation, registration and change detection method for water-body extraction using HSR images and GIS data[J]. ISPRS - International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, 2013, XL7: 237-242.
[38]	王春霞, 张俊, 李屹旭, 等. 复杂环境下GF-2影像水体指数的构建及验证[J]. 自然资源遥感, 2022, 34(3): 50-58. WANG C X, ZHANG J, LI Y X, et al. The construction and verification of a water index in the complex environment based on GF-2 images[J]. Remote Sensing for Natural Resources, 2022, 34(3): 50-58. (in Chinese with English abstract)
[39]	张国庆, 王蒙蒙, 周陶, 等. 青藏高原湖泊面积、水位与水量变化遥感监测研究进展[J]. 遥感学报, 2022, 26(1): 115-125. ZHANG G Q, WANG M M, ZHOU T, et al. Progress in remote sensing monitoring of lake area, water level, and volume changes on the Tibetan Plateau[J]. National Remote Sensing Bulletin, 2022, 26(1): 115-125. (in Chinese with English abstract)
[40]	廖静娟, 薛辉, 陈嘉明. 卫星测高数据监测青藏高原湖泊2010年—2018年水位变化[J]. 遥感学报, 2020, 24(12): 1534-1547. LIAO J J, XUE H, CHEN J M. Monitoring lake level changes on the Tibetan Plateau from 2000 to 2018 using satellite altimetry data[J]. National Remote Sensing Bulletin, 2020, 24(12): 1534-1547. (in Chinese with English abstract)
[41]	BUTT M J, UMAR M, QAMAR R. Landslide dam and subsequent dam-break flood estimation using HEC-RAS model in northern Pakistan[J]. Natural Hazards, 2013, 65(1): 241-254.
[42]	赫晓慧, 李满堂, 郭恒亮, 等. 高分二号卫星影像中城市建筑物阴影检测方法[J]. 中国科技论文, 2019, 14(7): 789-796. HE X H, LI M T, GUO H L, et al. Shadow detection method for urban buildings in GF-2 satellite images[J]. China Science Paper, 2019, 14(7): 789-796. (in Chinese with English abstract)
[43]	HONG S, JANG H, KIM N, et al. Water area extraction using RADARSAT SAR imagery combined with landsat imagery and terrain information[J]. Sensors, 2015, 15(3): 6652-6667.
[44]	段纪维, 钟九生, 江丽, 等. 基于GF-2影像的雨后洪涝区超绿水体指数提取方法[J]. 地理与地理信息科学, 2021, 37(3): 35-41. DUAN J W, ZHONG J S, JIANG L, et al. Extraction method of ultra-green water index for flood area after rain based on GF-2 image[J]. Geography and Geo-Information Science, 2021, 37(3): 35-41. (in Chinese with English abstract)
[45]	KLEMENJAK S, WASKE B, VALERO S, et al. Automatic detection of rivers in high-resolution SAR data[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2012, 5(5): 1364-1372.
[46]	张青, 冯志敏, 陈鹏. 高分一号卫星遥感影像提取冰川堰塞湖水体方法比较[J]. 测绘与空间地理信息, 2021, 44(1): 17-19. ZHANG Q, FENG Z M, CHEN P. The comparison of method for extracting water body from glacier barrier lake by GF-1 satellite remote sensing images[J]. Geomatics & Spatial Information Technology, 2021, 44(1): 17-19. (in Chinese with English abstract)
[47]	TSAI V J D. Automatic shadow detection and radiometric restoration on digital aerial images[C]//Anon. 2003 IEEE International Geoscience and Remote Sensing Symposium. [S. l. ]: [s. n. ], 2003: 732-733.
[48]	崔璐, 杜华强, 周国模, 等. 决策树结合混合像元分解的中国竹林遥感信息提取[J]. 遥感学报, 2019, 23(1): 166-176. CUI L, DU H Q, ZHOU G M, et al. Combination of decision tree and mixed pixel decomposition for extracting bamboo forest information in China[J]. National Remote Sensing Bulletin, 2019, 23(1): 166-176. (in Chinese with English abstract)
[49]	希丽娜依·多来提, 阿里木江·卡斯木, 如克亚·热合曼, 等. 基于四种水体指数的艾比湖水面提取及时空变化分析[J]. 长江科学院院报, 2022, 39(10): 134-140. DUOLAITI X, KASIM A, REHEMAN R, et al. Water body extraction of Ebinur Lake based on four water indexes and analysis of spatial-temporal changes[J]. Journal of Yangtze River Scientific Research Institute, 2022, 39(10): 134-140. (in Chinese with English abstract)