基于多特征融合的面向对象冰川边界提取

doi:10.13866/j.azr.2025.06.07

干旱区研究 ›› 2025, Vol. 42 ›› Issue (6): 1032-1042.doi: 10.13866/j.azr.2025.06.07 cstr: 32277.14.AZR.20250607

基于多特征融合的面向对象冰川边界提取

林洲艳¹(), 王霞迎¹^,²^,³^,⁴, 夏元平¹^,²^,³^,⁴()

1.东华理工大学测绘与空间信息工程学院，江西南昌 330013
2.东华理工大学自然资源部环鄱阳湖区域矿山环境监测与治理重点实验室，江西南昌 330013
3.东华理工大学江西省流域生态过程与信息重点实验室，江西南昌 330013
4.东华理工大学南昌市景观过程与国土空间生态修复重点实验室，江西南昌 330013

收稿日期:2024-12-19 修回日期:2025-02-13 出版日期:2025-06-15 发布日期:2025-06-11
通讯作者: 夏元平. E-mail: ypxia@ecut.edu.cn
作者简介:林洲艳（1998-），女，硕士研究生，主要从事冰川变化与气候响应研究. E-mail: 2023110417@ecut.edu.cn
基金资助:
国家自然科学基金项目(42174055);国家自然科学基金项目(42374040);东华理工大学博士启动基金(DHBK2019187)

Object-based glacier boundary extraction utilizing multi-feature fusion

LIN Zhouyan¹(), WANG Xiaying¹^,²^,³^,⁴, XIA Yuanping¹^,²^,³^,⁴()

1. School of Geomatics and Spatial Information Engineering, East China University of Technology, Nanchang 330013, Jiangxi, China
2. Key Laboratory of Mine Environmental Monitoring and Improving Around Poyang Lake, Ministry of Natural Resources, East China University of Technology, Nanchang 330013, Jiangxi, China
3. Jiangxi Key Laboratory of Watershed Ecological Process and Information, East China University of Technology, Nanchang, 330013, Jiangxi, China
4. Nanchang Key Laboratory of Landscape Process and Territorial Spatial Ecological Restoration, East China University of Technology, Nanchang 330013, Jiangxi, China

Received:2024-12-19 Revised:2025-02-13 Published:2025-06-15 Online:2025-06-11

摘要/Abstract

摘要：

鉴于像素级分类在光谱特征相近情况下难以准确识别冰川变化，特别是表碛覆盖区的光谱特征与周围山地、岩石相似度高，导致其提取精度较低。为此，本文以音苏盖提冰川和雅弄冰川为研究区，基于Google Earth Engine平台，结合光谱指数、微波纹理和地形特征，采用面向对象（OB）的机器学习算法进行冰川自动提取，并与基于像素（PB）分类方法进行对比。结果表明：（1）基于多特征融合的OB分类方法有助于提高冰川提取精度。其中，OB_RF分类的总体精度、Kappa系数和F1分数分别为98.1%、0.97和98.67%，优于OB_CART和OB_GTB方法。与PB_RF分类相比，总体精度、Kappa系数和F1分数分别提升了1.7%、0.024和5.57%。（2） 2001—2022年音苏盖提冰川和雅弄冰川年平均退缩率分别为0.08%、0.13%。（3）音苏盖提冰川表碛区主要分布在海拔5000 m以下，而雅弄冰川表碛区主要分布在海拔4800 m以下，2001—2022年两条冰川表碛覆盖区均呈现向上扩张趋势。

关键词: 冰川边界提取, 面向对象, 基于像素, 机器学习, 多特征融合

Abstract:

Pixel-based classification struggles with the accurate identification of glacier changes in areas with similar spectral characteristics, particularly in debris-covered areas where spectral features closely resemble the surrounding mountains and rocks, thereby resulting in low extraction accuracy. This study investigates the Yinsugaiti and Yalong Glaciers using Google Earth Engine to integrate spectral indices, microwave texture features, and topographic data. An object-based (OB) machine learning algorithm is applied for automated glacier extraction and compared to pixel-based (PB) classification methods. The results show the following. (1) The OB classification approach, integrating multi-feature fusion, significantly improved the glacier extraction accuracy. The OB_RF classifier achieved an overall accuracy of 98.1%, a Kappa coefficient of 0.97, and an F1-score of 98.67%, outperforming the OB_CART and OB_GTB classifiers. When compared to PB_RF, the overall accuracy, Kappa coefficient, and F1-score increased by 1.7%, 0.024, and 5.57%, respectively. (2) Between 2001-2022, the Yinsugaiti and Yalong Glaciers retreated at average annual rates of 0.08% and 0.13%, respectively. (3) Supraglacial debris was primarily distributed below 5000 and 4800 m on the Yinsugaiti and Yalong Glacier, respectively. Over the same period, debris-covered areas on both glaciers expanded upward.

Key words: glacier boundary extraction, object-based, pixel-based, machine learning, multi-feature fusion

林洲艳, 王霞迎, 夏元平. 基于多特征融合的面向对象冰川边界提取[J]. 干旱区研究, 2025, 42(6): 1032-1042.

LIN Zhouyan, WANG Xiaying, XIA Yuanping. Object-based glacier boundary extraction utilizing multi-feature fusion[J]. Arid Zone Research, 2025, 42(6): 1032-1042.

图/表 12

图1

表1

图2

图3

表2

图4

表3

图5

图6

表4

图7

图8

参考文献 41

[1]	Cogley J G, Hock R, Rasmussen L A, et al. Glossary of glacier mass balance and related terms[J]. Arctic Antarctic and Alpine Research, 2012, 44(2): 256-258.
[2]	Hewitt K. Rock avalanches that travel onto glaciers and related developments, Karakoram Himalaya, Inner Asia[J]. Geomorphology, 2009, 103(1): 66-79.
[3]	张勇, 刘时银, 王欣. 青藏高原及周边冰川区表碛影响研究进展[J]. 冰川冻土, 2022, 44(3): 900-913. doi: 10.7522/j.issn.1000-0240.2022.0086
	[Zhang Yong, Liu Shiyin, Wang Xin. Debris-cover effect in the Tibetan Plateau and surroundings: A review[J]. Journal of Glaciology and Geocryology, 2022, 44(3): 900-913.]
[4]	Cauvy-Fraunié S, Andino P, Espinosa R, et al. Ecological responses to experimental glacier-runoff reduction in alpine rivers[J]. Nature Communications, 2016, 7(1): 12025.
[5]	Millan R, Mouginot J, Rabatel A, et al. Ice velocity and thickness of the world’s glaciers[J]. Nature Geoscience, 2022, 15(2): 124-129.
[6]	Zemp M, Huss M, Thibert E, et al. Global glacier mass changes and their contributions to sea-level rise from 1961 to 2016[J]. Nature, 2019, 568(7752): 382-386.
[7]	Hall D K, Riggs G A, Salomonson V V. Development of methods for mapping global snow cover using moderate resolution imaging spectroradiometer data[J]. Remote Sensing of Environment, 1995, 54(2): 127-140.
[8]	陈逸青, 段克勤, 石培宏, 等. 1990—2020年帕米尔高原无表碛覆盖冰川变化态势研究——基于Google Earth Engine平台[J]. 冰川冻土, 2024, 46(3): 742-753. doi: 10.7522/j.issn.1000-0240.2024.0061
	[Chen Yiqing, Duan Keqin, Shi Peihong, et al. Change trend of debris-free glaciers in the Pamir based on Google Earth Engine from 1990 to 2020[J]. Journal of Glaciology and Geocryology, 2024, 46(3): 742-753.] doi: 10.7522/j.issn.1000-0240.2024.0061
[9]	黄晓然, 包安明, 郭浩, 等. 近20 a中国天山东段典型冰川变化及其气候响应[J]. 干旱区研究, 2017, 34(4): 870-880.
	[Huang Xiaoran, Bao Anming, Guo Hao, et al. Change of typical glaciers and its response to meteorological factors in the Eastern Tianshan Mountains in China in recent 20 years[J]. Arid Zone Research, 2017, 34(4): 870-880.]
[10]	Zhang M, Wang X H, Shi C L, et al. Automated glacier extraction index by optimization of Red/SWIR and NIR/SWIR ratio index for glacier mapping using Landsat imagery[J]. Water, 2019, 11(6): 1223.
[11]	都伟冰, 李均力, 包安明, 等. 高山冰川多时相多角度遥感信息提取方法[J]. 测绘学报, 2015, 44(1): 59-66. doi: 10.11947/j.AGCS.2015.20130514
	[Du Weibing, Li Junli, Bao Anming, et al. Information extraction method of alpine glaciers with multitemporal and multiangle remote sensing[J]. Acta Geodactica et Cartographica Sinica, 2015, 44(1): 59-66.]
[12]	Huang L, Li Z, Tian B S, et al. Classification and snow line detection for glacial areas using the polarimetric SAR image[J]. Remote Sensing of Environment, 2011, 115(7): 1721-1732.
[13]	Walter V. Object-based classification of remote sensing data for change detection[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2004, 58(3-4): 225-238.
[14]	怀保娟, 李忠勤, 孙美平, 等. 多种遥感分类方法提取冰川边界探讨——以喀纳斯河源地区为例[J]. 干旱区研究, 2013, 30(2): 372-377.
	[Huai Baojuan, Li Zhongqin, Sun Meiping, et al. Discussion on RS methods for glacier outline detection——A case study in headwaters of the Kanas River[J]. Arid Zone Research, 2013, 30(2): 372-377.]
[15]	Shukla A, Arora M K, Gupta R P. Synergistic approach for mapping debris-covered glaciers using optical-thermal remote sensing data with inputs from geomorphometric parameters[J]. Remote Sensing of Environment, 2010, 114(7): 1378-1387.
[16]	雷赛月, 方立, 李辰德, 等. 改进光学卫星图像中表碛覆盖型冰川区域提取算法[J]. 计算机工程, 2025, 2(51): 269-277.
	[Lei Saiyue, Fang Li, Li Chende, et al. Improving the algorithm for extracting debris-covered glaciers in optical satellite images[J]. Computer Engineering, 2025, 2(51): 269-277.]
[17]	薛娇, 姚晓军, 张聪, 等. 表碛覆盖型冰川的提取方法及变化[J]. 冰川冻土, 2022, 44(5): 1653-1664. doi: 10.7522/j.issn.1000-0240.2022.0145
	[Xue Jiao, Yao Xiaojun, Zhang Cong, et al. Extraction method and change of debris-covered glaciers[J]. Journal of Glaciology and Geocryology, 2022, 44(5): 1653-1664.] doi: 10.7522/j.issn.1000-0240.2022.0145
[18]	Holobâcă I-H, Tielidze L G, Ivan K, et al. Multi-sensor remote sensing to map glacier debris cover in the Greater Caucasus, Georgia[J]. Journal of Glaciology, 2021, 67(264): 685-696.
[19]	周建民, 李震, 邢强. 基于雷达干涉失相干特性提取冰川边界方法研究[J]. 冰川冻土, 2010, 32(1): 133-138.
	[Zhou Jianmin, Li Zhen, Xing Qiang. Deriving glacier border information based on analysis of decorrelation in SAR interferometry[J]. Journal of Glaciology and Geocryology, 2010, 32(1): 133-138.]
[20]	李若楠, 李均力, 李爽爽, 等. 基于Sentinel-2的依连哈比尔尕冰川变化监测[J]. 干旱区研究, 2024, 41(6): 940-950. doi: 10.13866/j.azr.2024.06.04
	[Li Ruonan, Li Junli, Li Shuangshuang, et al. Monitoring the glacier changes in Yilian Habirga Mountain using Sentinel-2 data[J]. Arid Zone Research, 2024, 41(6): 940-950.] doi: 10.13866/j.azr.2024.06.04
[21]	Yousuf B, Shukla A, Arora M K, et al. On drivers of subpixel classification accuracy—An example from glacier facies[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2020, 13(1): 601-608.
[22]	Aftab A K, Akhtar J, Dostdar H, et al. Machine-learning algorithms for mapping debris-covered glaciers: The Hunza Basin case study[J]. IEEE Access, 2020, 8(1): 12725-12734.
[23]	Xie Z Y, Asari V K, Haritashya U K. Evaluating deep-learning models for debris-covered glacier mapping[J]. Applied Computing and Geosciences, 2021, 12(1): 100071.
[24]	Yang S J, Wang F T, Xie Y D, et al. Delineation evaluation and variation of debris-covered glaciers based on the multi-source remote sensing images, Take glaciers in the eastern Tomur Peak region for example[J]. Remote Sensing, 2023, 15(10): 2575.
[25]	Racoviteanu A, Williams M W. Decision tree and texture analysis for mapping debris-covered glaciers in the Kangchenjunga area, Eastern Himalaya[J]. Remote Sensing, 2012, 4(10): 3078-3109.
[26]	Zhao Q, Yu L, Li X C, et al. Progress and trends in the application of Google Earth and Google Earth Engine[J]. Remote Sensing, 2021, 13(18): 3778.
[27]	Amani M, Mahdavi S, Afshar M, et al. Canadian wetland inventory using Google Earth Engine: The first map and preliminary results[J]. Remote Sensing, 2019, 11(7): 842.
[28]	喻彩丽, 陆健强, 窦旭峰, 等. 基于GEE的多源遥感影像青梅种植信息提取[J]. 江苏农业学报, 2024, 40(8): 1455-1463.
	[Yu Caili, Lu Jianqiang, Dou Xufeng, et al. Extraction of greengage planting information from multi-source remote sensing images based on GEE[J]. Jiangsu Journal of Agricultural Sciences, 2024, 40(8): 1455-1463.]
[29]	马东岭, 刘卫星, 张春红. 基于谷歌地球引擎和分形理论的黄河三角洲土地利用空间结构研究[J]. 土壤, 2024, 56(3): 655-665.
	[Ma Dongling, Liu Weixing, Zhang Chunhong. Study on land use spatial structure based on Google Earth Engine and fractal theory: A case study of ecological function reserve in Yellow River Delta[J]. Soils, 2024, 56(3): 655-665.]
[30]	Bevington A R, Menounos B. Accelerated change in the glaciated environments of western Canada revealed through trend analysis of optical satellite imagery[J]. Remote Sensing of Environment, 2022, 270(1): 112862.
[31]	Hu M C, Zhou G S, Lv X M, et al. A new automatic extraction method for glaciers on the Tibetan Plateau under clouds, shadows and snow cover[J]. Remote Sensing, 2022, 14(13): 3084.
[32]	Huang L, Li Z, Zhou J M, et al. An automatic method for clean glacier and nonseasonal snow area change estimation in High Mountain Asia from 1990 to 2018[J]. Remote Sensing of Environment, 2021, 258(1): 112376.
[33]	Ali A, Dunlop P, Coleman S, et al. Glacier area changes in Novaya Zemlya from 1986-89 to 2019-21 using object-based image analysis in Google Earth Engine[J]. Journal of Glaciology, 2023, 69(277): 1305-1316.
[34]	刘时银, 姚晓军, 郭万钦, 等. 基于第二次冰川编目的中国冰川现状[J]. 地理学报, 2015, 70(1): 3-16. doi: 10.11821/dlxb201501001
	[Liu Shiyin, Yao Xiaojun, Guo Wanqin, et al. The contemporary glaciers in China based on the Second Chinese Glacier Inventory[J]. Acta Geographica Sinica, 2015, 70(1): 3-16.] doi: 10.11821/dlxb201501001
[35]	Achanta R, Susstrunk S. Superpixels and polygons using simple non-iterative clustering[C]// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. New York: IEEE Computer Society, 2017: 4651-4660.
[36]	裴欢, 孙天娇, 王晓妍. 基于 Landsat 8 OLI 影像纹理特征的面向对象土地利用/覆盖分类[J]. 农业工程学报, 2018, 34(2): 248-255.
	[Pei Huan, Sun Tianjiao, Wang Xiaoyan. Object-oriented land use/cover classification based on texture features of Landsat 8 OLI image[J]. Transactions of the Chinese Society of Agricultural Engineering, 2018, 34(2): 248-255.]
[37]	Paul F, Huggel C, Kääb A. Combining satellite multispectral image data and a digital elevation model for mapping debris-covered glaciers[J]. Remote Sensing of Environment, 2004, 89(4): 510-518.
[38]	Östrem G. Ice melting under a thin layer of moraine, and the existence of ice cores in moraine ridges[J]. Geografiska Annaler, 1959, 41(4): 228-230.
[39]	Zhuang L C, Ke C Q, Cai Y, et al. Measuring glacier changes in the Tianshan Mountains over the past 20 years using Google Earth Engine and machine learning[J]. Journal of Geographical Sciences, 2023, 33(9): 1939-1964. doi: 10.1007/s11442-023-2160-4
[40]	许艾文. 近40年中国喀喇昆仑山冰川变化的遥感监测[D]. 兰州: 兰州大学, 2017.
	[Xu Aiwen. Monitoring Glacier Change Based on Remote Sensing in China Karakoram for the Last Four Decades[D]. Lanzhou: Lanzhou University, 2017.]
[41]	赵晋彪. 藏东南地区冰川变化与运动特征研究[D]. 安徽: 安徽理工大学, 2024.
	[Zhao Jinbiao. Study on Characteristics of Glacier Change and Movement in Southeast Xizang[D]. Anhui: Anhui University of Science and Technology, 2024.]

影像源	获取时间	分辨率/m	GEE来源
Landsat 5	2010-08-23	30	LANDSAT/LT05/C02/T1_L2/LT05_148035_20100823
Landsat 7	2001-07-03	30	LANDSAT/LE07/C02/T1_L2/LE07_134040_20010703
Landsat 7	2001-07-21	30	LANDSAT/LE07/C02/T1_L2/LE07_148035_20010721
Landsat 7	2009-09-27	30	LANDSAT/LE07/C02/T1_L2/LE07_134040_20090927
Landsat 8	2022-07-23	30	LANDSAT/LC08/C02/T1_L2/LC08_148035_20220723
Landsat 8	2022-07-05	30	LANDSAT/LC08/C02/T1_L2/LC08_134040_20200705
PALSAR/PALSAR-2	2009-2010年	25	JAXA/ALOS/PALSAR/YEARLY/SAR
Sentinel-1	2022年	25	COPERNICUS/S1_GRD
NASADEM	2000年	30	NASA/NASADEM_HGT/001

超像素种子	OB_RF		OB_GTB		OB_CART
超像素种子	OA/%	Kappa系数	OA/%	Kappa系数	OA/%	Kappa系数
6	95.95	0.94	94.80	0.92	88.44	0.82
13	98.84	0.98	96.53	0.94	93.06	0.89
21	93.64	0.90	91.33	0.86	91.91	0.87
30	95.35	0.93	93.60	0.90	87.21	0.80
40	87.35	0.80	89.16	0.83	87.95	0.81

方法	准确率/%	召回率/%	F1分数/%
OB_RF	98.37	98.97	98.67
OB_GTB	96.27	97.60	96.87
OB_CART	93.53	93.93	93.73
PB_RF	91.47	94.80	93.10
PB_GTB	90.87	94.83	92.77
PB_CART	85.93	89.43	87.53

	音苏盖提冰川面积/km²			雅弄冰川面积/km²			总面积/km²
	裸冰区	表碛区	冰川区	裸冰区	表碛区	冰川区	裸冰区	表碛区	冰川区
2001年	318.88	37.38	356.26	170.25	9.76	180.01	489.14	47.14	536.27
2010年	313.79	39.47	353.25	166.35	12.20	178.55	480.14	51.67	531.81
2022年	308.70	41.84	350.54	161.43	13.51	174.94	470.12	55.36	525.48
相对变化/km²	-10.19	4.47	-5.72	-8.82	3.75	-5.07	-19.01	8.22	-10.79
绝对变化/%	-3.19	11.95	-1.61	-5.18	38.44	-2.82	-3.89	17.44	-2.01
年变化量/km²	-0.49	0.21	-0.27	-0.42	0.18	-0.24	-0.91	0.39	-0.51
年变化率/%	-0.15	0.57	-0.08	-0.25	1.83	-0.13	-0.19	0.83	-0.10

基于多特征融合的面向对象冰川边界提取

Object-based glacier boundary extraction utilizing multi-feature fusion

RichHTML

PDF (PC)

赞

可视化

摘要/Abstract

引用本文

使用本文

图/表 12

参考文献 41

相关文章 10

Metrics

本文评价

推荐阅读 0

[1]	王艺璇, 邓晓红, 范慧文青, 韩江哲, 李宗省. 水资源承载力评价耦合模型的研究进展与干旱区应用[J]. 干旱区研究, 2025, 42(6): 1004-1020.
[2]	龙威夷, 施建飞, 李双媛, 孙金金, 王玉刚. 流域绿洲土壤盐分多模型反演效果评估[J]. 干旱区研究, 2024, 41(7): 1120-1130.
[3]	洪国军, 谢俊博, 张灵, 范振岐, 喻彩丽, 付仙兵, 李旭. 基于多光谱影像的阿拉尔垦区棉田土壤盐分反演[J]. 干旱区研究, 2024, 41(5): 894-904.
[4]	庞海威,余殿,任成宝,张玉,郑彩之,郭佳诚,边振,桑国庆. 宁夏东部半干旱区典型植物群落遥感分类特征[J]. 干旱区研究, 2022, 39(6): 1930-1941.
[5]	白建铎,彭杰,史舟,王玉珍,柳维扬,李洪义. 基于多源数据的干旱区盐渍化农田精准管理分区研究[J]. 干旱区研究, 2022, 39(2): 646-655.
[6]	宋奇,史舟,冯春晖,马自强,纪文君,彭杰,高琪,蒋学玮. 基于1990—2019年多时相影像的干旱区绿洲景观格局分析[J]. 干旱区研究, 2022, 39(2): 594-604.
[7]	王晓燕,李净,邢立亭. 基于3种机器学习方法的农业干旱监测比较[J]. 干旱区研究, 2022, 39(1): 322-332.
[8]	杨雪峰,叶茂,木尼热·买买提. 基于WorldView-2高分影像的胡杨林结构参数获取研究[J]. 干旱区研究, 2021, 38(6): 1659-1667.
[9]	陈春秀,陈蜀江,徐世薇,陈孟禹,贾翔,黄铁成,李春蕾. 多特征辅助下的GF-6 WFV影像准噶尔山楂识别研究[J]. 干旱区研究, 2021, 38(2): 553-561.
[10]	怀保娟, 李忠勤, 孙美平, 夏明营. 多种遥感分类方法提取冰川边界探讨[J]. 干旱区研究, 2013, 30(2): 372-377.