知识驱动的疑似黑臭水体遥感识别方法研究

doi:10.16258/j.cnki.1674-5906.2025.03.012

生态环境学报 ›› 2025, Vol. 34 ›› Issue (3): 451-460.DOI: 10.16258/j.cnki.1674-5906.2025.03.012

• 研究论文【环境科学】 • 上一篇下一篇

知识驱动的疑似黑臭水体遥感识别方法研究

李启亮¹(), 卢辉雄²^,³^,⁴^,^*(), 孙永彬²^,³, 汪冰²^,³, 张恩²^,³^,⁴, 薛庆²^,³, 韩少飞², 牛海威²

1.河北航遥科技有限公司，河北石家庄 050002
2.核工业航测遥感中心，河北石家庄 050002
3.河北省航空探测与遥感技术重点实验室，河北石家庄 050002
4.高分辨率对地观测系统河北数据应用技术支持中心，河北石家庄 050002

收稿日期:2024-09-21 出版日期:2025-03-18 发布日期:2025-03-24
通讯作者: *卢辉雄。E-mail: 1551310706@qq.com
作者简介:李启亮（1993年生），男，硕士研究生，工程师，主要研究方向为遥感技术与应用。E-mail: leaqiliang@163.com
基金资助:
河北省航空探测与遥感技术重点实验室科研项目(202418)

Research on Knowledge-driven Remote Sensing Identification Method of Suspected Black and Odor Water Body in Cities

LI Qiliang¹(), LU Huixiong²^,³^,⁴^,^*(), SUN Yongbin²^,³, WANG Bing²^,³, ZHAGN En²^,³^,⁴, XUE Qing²^,³, HAN Shaofei², NIU Haiwei²

1. Hebei Airborne Survey and Remote Sensing Technology Co. Shijiazhuang 050002, P. R. China
2. Airborne Survey and Remote Sensing Center of Nuclear Industry, Shijiazhuang 050002, P. R. China
3. Key Laboratory of Airborne Survey and Remote Sensing, Shijiazhuang 050002, P. R. China
4. High-Resolution Earth Observation System Data Application Technical Support Center of Hebei Province, Shijiazhuang 050002, P. R. China

Received:2024-09-21 Online:2025-03-18 Published:2025-03-24

摘要/Abstract

摘要：

面积较小、位置隐蔽或突发性的黑臭水体难以通过波段比值法和深度学习技术进行有效地识别。针对这一问题，提出了一种基于高分遥感影像的、以知识为驱动的综合遥感识别方法。该方法从空间分布模式、污染源和遥感特征3个方面对黑臭水体逐步进行识别与黑臭判定，按照生活污水类、生活垃圾类、养殖粪污类和工业污水类4个类别开展分类综合研究，给出了每一类适用的遥感识别方法。以沧州市为研究区，开展疑似黑臭水体遥感识别。研究结果表明：1）基于知识驱动的疑似黑臭水体识别方法有效，通过分布位置、形成原因和影像特征3个方面在研究区识别出137处黑臭水体；2）经过精度验证，黑臭水体查准率为65.8%，查全率为97.1%，准确率为64.6%，F1 Score为0.78，错分率为34.2%，漏分率为1.9%，表明该方法能够有效全面地识别黑臭水体；3）作业耗时分析，发现该方法能够在较短的时间内获得大范围地区的黑臭水体分布位置。因此，该技术可为政府部门提供迅速的稳定的黑臭水体排查服务，为生态环境改善提供技术支持。

关键词: 黑臭水体, 知识驱动, 高分遥感, 分类识别

Abstract:

Black and odorous water bodies with small areas, hidden locations, or sudden occurrences are difficult to effectively identify using the band ratio method and deep learning technology. To solve this problem, this study proposes a comprehensive remote sensing identification method driven by high-scoring remote sensing images that identifies and judges black and odorous water bodies based on spatial distribution patterns, pollution sources, and remote sensing characteristics, as well as remote sensing identification methods for domestic sewage, domestic garbage, aquaculture manure, and industrial sewage. In this study, 16 districts and counties in Cangzhou City were used as research areas for remote-sensing identification and verification of black and odorous water bodies. The results showed that 1) 137 black and smelly water bodies were identified in the study area from three aspects: distribution location, formation reason, and image characteristics. 2) After field verification, the precision, recall, and accuracy rates of black and odorous water bodies were 65.8%, 97.1%, and 64.6%, respectively. The F1 Score was 0.78, the wrong classification rate was 34.2%, and the missing classification rate was 1.9%, which shows that this method can effectively identify black and odorous water bodies in cities. 3) Through the analysis of the operation time, it was found that this method can obtain the spatial distribution position of black and odorous water over a large area in a short time. This technology not only provides rapid and stable black and odorous water investigation services for government departments but also provides technical support for urban ecological environment improvement

Key words: black and odorous water body, knowledge-driven, high-scoring remote sensing, classification and recognition

中图分类号:

李启亮, 卢辉雄, 孙永彬, 汪冰, 张恩, 薛庆, 韩少飞, 牛海威. 知识驱动的疑似黑臭水体遥感识别方法研究[J]. 生态环境学报, 2025, 34(3): 451-460.

LI Qiliang, LU Huixiong, SUN Yongbin, WANG Bing, ZHAGN En, XUE Qing, HAN Shaofei, NIU Haiwei. Research on Knowledge-driven Remote Sensing Identification Method of Suspected Black and Odor Water Body in Cities[J]. Ecology and Environment, 2025, 34(3): 451-460.

图/表 10

图1 研究区地理位置图

Figure 1 Geographic location map of the study area

图2 知识驱动的遥感综合识别方法流程图

Figure 2 Flowchart of knowledge-driven remote sensing integrated recognition approach

图3 污染源与被污染水体的空间分布模式图

Figure 3 Map of spatial distribution patterns of pollution sources and polluted water bodies

表1 废水污染型行业和对应的关键词列表

Table 1 List of wastewater-polluting industries and corresponding keywords

废水污染型行业	关键词
畜牧业（03）	畜牧，养殖，猪场，牛场，羊场，鸡场，牧业，畜禽，屠宰，种猪，种牛，农场，牧场，养猪，养鸡，养羊，养牛，养猪
食品制造业（14）	肉联，肉加工，预制菜，豆制，豆制品，乳业，食品，酿造，制糖，酿酒，食品加工
纺织业（17）	纺织，印染，染料
皮革、毛皮、羽毛及其制品和制鞋业（19）	皮业，制革，皮革，毛皮，羽毛，制鞋
造纸和纸制品业（22）	纸业，造纸，印刷
石油、煤炭及其他燃料加工业（25）	炼油，焦化，洗煤
化学原料和化学制品制造业（26）	化工，化学，农药，农化，粉扑
医药制造业（27）	药业，制药
橡胶和塑料制品业（29）	橡胶，塑业，塑料，
金属制品业（33）	金属，合金，冶炼，矿业，有色，电镀

图4 各类别黑臭水体遥感影像图和野外照片

Figure 4 Remote sensing image maps and field photos of black stinky water bodies by category

表2 混淆矩阵表

Table 2 Confusion matrix table

类别	疑似黑臭	疑似正常	总计
实际黑臭	133	4	137
实际正常	69	0	69
总计	202	4	210

图5 错分的两处黑臭水体遥感影像和野外照片

Figure 5 Remote sensing imagery and field photos of the two misclassified black-odorized water bodies

图6 漏分的两处黑臭水体遥感影像和野外照片

Figure 6 Remote sensing images and field photos of two black-odor water bodies with missing subgrades

表3 分项作业耗时表

Table 3 Itemized operational time table

项目	分项	分项作业耗时/h
遥感影像	检索（20景）	0.5
	下载（总量40 Gb，速度10 Mb/s）	1
	处理（1景/1 h）	20
资料收集	POI	0.2
	舆情数据	1
遥感识别	识别（2403个网格，1000网格/8 h）	20
野外核查	核查（210个核查点，20个/8 h）	84
	数据整理	16

图7 黑臭水体治理前后遥感影像图

Figure 7 Remote sensing images before and after the treatment of black-smelling water bodies

参考文献 25

[1]	CARPENTER D J, CARPENTER S M, 1983. Modeling inland water quality using Landsat data[J]. Remote Sensing of Environment, 13(4): 345-352.
[2]	傲德姆, 孙菲, 冯庆标, 等, 2020. 广州市双岗涌黑臭水体整治案例分析[J]. 环境工程技术学报, 10(5): 719-725.
	AO D M, SUN F, FENG Q B, et al., 2020. Case analysis on the treatment of black and odorous water body in Shuanggangchong River, Guangzhou City[J]. Journal of Environmental Engineering Technology, 10(5): 719-725.
[3]	陈小鹏, 2023. 基于多源遥感数据的全天候水体超像素提取方法及应用研究[D]. 沈阳: 中国科学院大学(中国科学院东北地理与农业生态研究所).
	CHEN X P, 2023. Research on all-weather water body hyper pixel extraction method and application based on multi-source remote sensing data[D]. Shenyang: University of Chinese Academy of Sciences (Northeast Institute of Geography and Agroecology, Chinese Academy of Sciences).
[4]	成明旗, 孟庆峰, 2017. 广东天沙河黑臭水体综合治理方法研究[J]. 人民长江, 48(S2): 32-35.
	CHENG M Q, MENG Q F, 2017. Research on the comprehensive management method of black-odor water body of Tiansha River in Guangdong[J]. People’s Yangtze River, 48(S2): 32-35.
[5]	冯然, 刘力锋, 王宝山, 等, 2023. 基于高分一号遥感影像的农村黑臭水体识别方法研究[J]. 测绘与空间地理信息, 46(S1): 125-128.
	FENG R, LIU L F, WANG B S, et al., 2023. Research on the identification method of rural black smelly water bodies based on Gaofen-1 remote sensing image[J]. Mapping and Spatial Geographic Information, 46(S1): 125-128.
[6]	何红术, 黄晓霞, 李红旮, 等, 2020. 基于改进U-Net网络的高分遥感影像水体提取[J]. 地球信息科学学报, 22(10): 2010-2022. DOI
	HE H S, HUANG X X, LI H G, et al., 2020. Water body extraction of high resolution remote sensing image based on improved u-net network[J]. Journal of Geo-information Science, 22(10): 2010-2022.
[7]	黄祺宇, 肖晗, 于之锋, 等, 2022. 基于高分六号影像的杭州市黑臭水体遥感识别研究[J]. 杭州师范大学学报(自然科学版), 21(5): 542-552.
	HUANG Q Y, XIAO H, YU Z F, et al., 2022. Remote sensing identification of black smelly water bodies in Hangzhou based on Gaofen Six images[J]. Journal of Hangzhou Normal University (Natural Science Edition), 21(5): 542-552.
[8]	兰思香, 2024. 基于GF-2影像的黑臭水体遥感监测研究[D]. 南宁: 广西大学.
	LAN S X, 2024. Research on remote sensing monitoring of black stinky water bodies based on GF-2 images[D]. Nanning: Guangxi University.
[9]	李卫东, 2014. 沧州市种植业可持续发展研究[D]. 北京: 中国农业科学院.
	LI W D, 2014. Research on sustainable development of plantation industry in Cangzhou City[D]. Beijing: Chinese Academy of Agricultural Sciences.
[10]	刘冰, 李天宏, 2024. 基于高分影像的城市黑臭水体遥感识别方法研究[J]. 应用基础与工程科学学报, 32(2): 314-330.
	LIU B, LI T H, 2024. Research on remote sensing identification methods of urban black and odorous water bodies with Gaofen Images[J]. Journal of Basic Science and Engineering, 32(2): 314-330.
[11]	刘羿漩, 董兴鹏, 何胜文, 等, 2023. 多尺度特征融合U-Net的遥感影像黑臭水体智能检测[J]. 半导体光电, 44(5): 747-755.
	LIU Y X, DONG X P, HE S W, et al., 2023. Intelligent detection of impaired water in remote sensing images based on multi-scale feature fusion U-Net[J]. Semiconductor Optoelectronics, 44(5): 747-755.
[12]	邵琥翔, 丁凤, 杨健, 等, 2022. 基于深度学习的黑臭水体遥感信息提取模型[J]. 长江科学院院报, 39(4): 156-162. DOI
	SHAO H X, DING F, YANG J, et al., 2022. Model of extracting remotely-sensed information of black and odorous water based on deep learning[J]. Journal of Yangtze River Scientific Research Institute, 39(4): 156-162.
[13]	疏小舟, 尹球, 匡定波, 2000. 内陆水体藻类叶绿素浓度与反射光谱特征的关系[J]. 遥感学报, 4(1): 41-45.
	SHU X Z, YIN Q, KUANG D B, 2000. Relationship between algal chlorophyll concentration and spectral reflectance of inland water[J]. Journal of Remote Sensing, 4(1): 41-45.
[14]	王桂娟, 2016. 沧州市运河区养老保险事业改革研究[D]. 秦皇岛: 燕山大学.
	WANG G J, 2016. Research on the reform of pension insurance business in Yunhe district of Cangzhou City[D]. Qinhuangdao: Yanshan University.
[15]	王卷乐, 李凯, 严欣荣, 等, 2023. 地理要素分类机器学习方法发展与前景[J]. 遥感学报, 27(8): 1757-1768.
	WANG J L, LI K, YAN X R, et al., 2023. Development and prospects of machine learning methods in geographic elements classification[J]. National Remote Sensing Bulletin, 27(8): 1757-1768.
[16]	温爽, 王桥, 李云梅, 等, 2018. 基于高分影像的城市黑臭水体遥感识别: 以南京为例[J]. 环境科学, 39(1): 57-67.
	WEN S, WANG Q, LI Y M, et al., 2018. Remote sensing identification of urban black-odor water bodies based on high-resolution images: A case study in Nanjing[J]. Environmental Science, 39(1): 57-67.
[17]	解明权, 闵松寒, 杨辉, 等, 2024. 基于贝叶斯卷积网络的农村黑臭水体遥感识别算法研究[J]. 环境科学学报, 44(3): 215-226.
	XIE M Q, MIN S H, YANG H, et al., 2024. A remote sensing recognition algorithm for rural black and odorous water bodies on Bayesian convolutional networks[J]. Acta Scientiae Circumstantiae, 44(3): 215-226.
[18]	徐京萍, 张柏, 李方, 等, 2008. 基于MODIS数据的太湖藻华水体识别模式[J]. 湖泊科学, 20(2): 191-195.
	XU J P, ZHANG B, LI F, et al., 2008. Detecting modes of cyanobacteria bloom using MODIS data in Lake Taihu[J]. Journal of Lake Sciences, 20(2): 191-195.
[19]	姚月, 申茜, 朱利, 等, 2019. 高分二号的沈阳市黑臭水体遥感识别[J]. 遥感学报, 23(2): 230-242.
	YAO Y, SHEN Q, ZHU L, et al., 2019. Remote sensing identification of urban black-odor water bodies in Shen yang city based on GF-2 image[J]. Journal of Remote Sensing, 23(2): 230-242.
[20]	杨阳, 2012. 温州温瑞塘河流域水体黑臭问题研究[D]. 温州: 温州医科大学.
	YANG Y, 2012. Research on the black odor problem of water bodies in Wenruitang river basin in Wenzhou[D]. Wenzhou: Wenzhou Medical University.
[21]	杨玥, 王健, 朱娟平, 等, 2015. 城市黑臭河涌底泥-微生物燃料电池产电性能及对底泥的修复[J]. 生态环境学报, 24(3): 463-468. DOI
	YANG Y, WANG J, ZHU J P, et al., 2015. Electricity generation by urban black smelly river sediment-mfc and the effect on sediment remediation[J]. Ecology and Environmental Sciences, 24(3): 463-468.
[22]	张宝东, 王彪, 吴艳兰, 等, 2024. 安徽省农村黑臭水体特征分析及识别[J]. 生态环境学报, 33(8): 1257-1268. DOI
	ZHANG B D, WANG B, WU Y L, et al., 2024. Analysis and identification of characteristics of rural black and odorous water bodies in Anhui province[J]. Ecology and Environmental Sciences, 33(8): 1257-1268.
[23]	张淳, 葛毅, 任越, 等, 2023. 基于优化的DeeplabV3+网络和高分影像分割浮萍型农村黑臭水体[J]. 遥感技术与应用, 38(6): 1433-1444. DOI
	ZHANG C, GE Y, REN Y, et al., 2023. Semantic segmentation of rural black and odorous water body based on improved Deeplabv3+Network with remote sensing images[J]. Remote Sensing Technology and Application, 38(6): 1433-1444.
[24]	赵学伟, 张志斌, 陈龙, 等, 2024. 老工业城市污染企业空间格局演变及影响机制——以兰州市为例[J]. 经济地理, 44(6): 70-81. DOI
	ZHAO X W, ZHANG Z B, CHEN L, et al., 2024. Spatial pattern evolution and influence mechanism of polluting enterprises in old industrial city: A case of Lanzhou City[J]. Economic Geography, 44(6): 70-81.
[25]	住房城乡建设部, 环境保护部, 2015. 城市黑臭水体整治工作指南[EB/OL]. [2015-08-28]. https://www.mohurd.gov.cn/gongkai/zc/wjk/art/2015/art_17339_224828.html.
	Ministry of Housing and Urban-Rural Development, Ministry of Environmental Protection, 2015. Guide lines for urban black and odorous water body[EB/OL]. [2015-08-28]. https://www.mohurd.gov.cn/gongkai/zc/wjk/art/2015/art_17339_224828.html.

知识驱动的疑似黑臭水体遥感识别方法研究

Research on Knowledge-driven Remote Sensing Identification Method of Suspected Black and Odor Water Body in Cities

RichHTML

PDF

可视化

摘要/Abstract

引用本文

使用本文

图/表 10

参考文献 25

相关文章 1

编辑推荐

Metrics

本文评价