
1.中国电建集团西北勘测设计研究院,陕西 西安 710100
2.西安理工大学,陕西 西安 710048
3.宁波银行股份有限公司,浙江 宁波 315000
4.天津国际工程咨询集团有限公司,天津 300220
Received:12 June 2026,
Revised:2026-07-22,
Accepted:24 July 2026,
Online First:31 July 2026,
移动端阅览
任苇,杨元园,高建等.基于U-Net地物识别的城区雨水资源潜力评估[J].人民珠江,DOI:10.3969/j.issn.1001-9235.XXXX.XX.001.
REN Wei,YANG Yuanyuan,GAO Jian,et al.Urban Rainwater Harvesting Potential Assessment Using U-Net Land-Cover Recognition Model[J].PEARL RIVER,
任苇,杨元园,高建等.基于U-Net地物识别的城区雨水资源潜力评估[J].人民珠江,DOI:10.3969/j.issn.1001-9235.XXXX.XX.001. DOI:
REN Wei,YANG Yuanyuan,GAO Jian,et al.Urban Rainwater Harvesting Potential Assessment Using U-Net Land-Cover Recognition Model[J].PEARL RIVER, DOI:10.3969/j.issn.1001-9235...001.
雨水收集利
用是缓解城市水资源紧张与排水压力的重要途径。构建基于遥感数据集的U-Net地物识别模型,提取水体、裸地、林草地、建筑屋面、道路等5类地物;考虑地物、土壤和降雨季节性变化等,分别采用综合径流系数法和SCS-CN地表产流模型计算径流系数,结合坡度因子进行修正,推求不同降雨情景的雨水资源潜力。西安市城六区的案例研究表明:U-Net模型对城区复杂地物的分类精度和边界识别表现出显著的适用性和稳定性,超参数训练能有效平衡模型识别性能与效率;相较于综合径流系数法,SCS-CN的径流系数值更大、空间异质性更强,更能精细刻画土壤水文条件差异对产流的影响,更适用城区雨水资源潜力评估及后续规划建设与管理;在10%、50%、90%频率及多年平均降雨情景下,U-Net地物识别模型对结果修正后,雨水资源潜力分别为2.85亿、2.20亿、1.73亿、2.26亿m
3
/a;建筑屋面和道路是雨水资源的主要贡献区。该成果可为城市雨洪韧性管理提供参考。
Rainwater harvesting is an important strategy for alleviating urban water shortages
reducing drainage pressure
and improving the resilience of urban stormwater management systems. Accurate land-cover recognition is essential for estimating surface runoff and rainwater harvesting potential
particularly in highly urbanized areas where impervious surfaces
vegetated land
roads
rooftops
and water bodies are spatially mixed. In this study
an urban rainwater harvesting potential assessment framework was developed by integrating high-resolution remote sensing interpretation
a U-Net land-cover recognition model
and hydrological estimation methods. The six urban districts of Xi'an
China
were selected as the study area. Five major land-cover types
including water bodies
bare land
vegetated land
building rooftops
and roads
were identified from remote sensing imagery. The U-Net model was constructed using ArcGIS Learn with a ResNet-34 backbone
and a support vector machine (SVM) model was introduced as a traditional supervised classification method for comparison. Classification performance was evaluated using overall accuracy
Kappa coefficient
precision
recall
F1-score
and confusion matrices. Based on the land-cover recognition results
runoff coefficients were estimated using both the composite runoff coefficient method and the Soil Conservation Service Curve Number (SCS-CN) model. The composite runoff coefficient method assigns empirical runoff coefficients according to land-cover types
whereas the SCS-CN model further incorporates hydrological soil groups and antecedent moisture conditions to represent differences in infiltration and retention capacity. A slope correction factor was also introduced to adjust runoff coefficients under different terrain conditions. Precipitation records from 1961 to 2023 were analyzed to establish rainfall scenarios corresponding to 10%
50%
and 90% frequency levels
as well as the long-term mean annual rainfall. In addition
classification error propagation was considered using the U-Net confusion matrix to evaluate the influence of land-cover recognition uncertainty on rainwater harvesting potential estimates. The results show that the U-Net model achieved an overall accuracy of 0.780 and a Kappa coefficient of 0.725
outperforming the SVM model
which achieved an overall accuracy of 0.430 and a Kappa coefficient of 0.276. The U-Net model showed relatively good recognition performance for building rooftops and roads
while some confusion remained among water bodies
bare land
and vegetated land. Compared with the composite runoff coefficient method
the SCS-CN model produced higher runoff coefficients and stronger spatial heterogeneity
indicating that it can better reflect the effects of land-cover types and hydrological soil conditions on runoff generation. Under rainfall scenarios corresponding to the 10%
50%
and 90% frequency levels and the long-term mean annual rainfall
the corrected rainwater harvesting potentials were estimated as 285
220
173
and 226 million m³·yr⁻¹
respectively. Building rooftops and roads were identified as the dominant contributors to rainwater harvesting potential. The proposed framework provides a technical reference for urban rainwater resource assessment and resilient stormwater management.
朱文彬 , 吕爱锋 , 曲波 . 我国城市雨水资源化利用的效益评价 [J]. 给水排水 , 2017 , 53 ( S1 ): 123 - 127 .
Zhu Wenbin , Lyu Aifeng , Qu Bo . Benefit Evaluation of Urban Rainwater Resource Utilization in China [J]. Water & Wastewater Engineering , 2017 , 53 ( S1 ): 123 - 127 . (in Chinese)
Raimondi A , Quinn R , Gnecco I , et al . New Advances in Rainwater Harvesting and Treatment [J]. Water , 2024 , 16 ( 11 ): 1591 .
胡庆芳 , 王银堂 , 邓鹏鑫 , 等 . 对雨洪资源利用的再认识 [J]. 水利水运工程学报 , 2023 ( 1 ): 149 - 160 .
Hu Qingfang , Wang Yintang , Deng Pengxin , et al . Reconsideration of Stormwater Resource Utilization [J]. Hydro-Science and Engineering , 2023 ( 1 ): 149 - 160 . (in Chinese)
Farooq S , Mahmood K , Faizi F . Comparative Simulation of GIS-Based Rainwater Management Solutions [J]. Water Resources Management , 2022 , 36 ( 9 ): 3049 - 3065 .
余宇 , 陈磊 , 张普 , 等 . 基于文献计量学的城市雨水管理发展研究 [J]. 人民珠江 , 2019 , 40 ( 10 ): 50 - 59, 103 .
Yu Yu , Chen Lei , Zhang Pu , et al . Development of Urban Rainwater Management Based on Bibliometrics [J]. Pearl River , 2019 , 40 ( 10 ): 50 - 59, 103 . (in Chinese)
Yang Y Y . Study on Ideal Way of Water Environment Improvement by China's Sponge City Construction [D]. Tokyo : Nihon University , 2017 .
Shadmehri T A , Ghasemi T E , Ghassemi S A , et al . A multi-criteria decision analysis approach towards efficient rainwater harvesting [J]. Journal of Hydrology , 2020 , 582 : 124501 .
Zhou Jinjun , Pang Yali , Fu Guangtao , et al . A review of urban rainwater harvesting in China [J]. Journal of Water Reuse and Desalination , 2023 , 13 ( 1 ): 1 - 17 .
Gavhane K P , Mishra A K , Sarangi A , et al . Targeting of rainwater harvesting structures using geospatial tools and analytical hierarchy process (AHP) in the semi-arid region of Rajasthan (India) [J]. Environmental Science and Pollution Research , 2023 , 30 ( 22 ): 61682 - 61709 .
Ssekyanzi G , Ahmad M J , Choi K S . Geospatial Assessment of Stormwater Harvesting Potential in Uganda's Cattle Corridor [J]. Water , 2025 , 17 ( 3 ): 349 .
李雅楠 . 西安市城区雨洪资源利用潜力研究 [D]. 西安 : 西安科技大学 , 2017 .
Li Yanan . Study on Utilization Potential of Stormwater Resources in Xi'an Urban Area [D]. Xi'an : Xi'an University of Science and Technology , 2017 . (in Chinese)
Tiwari K , Goyal R , Sarkar A . GIS-based Methodology for Identification of Suitable Locations for Rainwater Harvesting Structures [J]. Water Resources Management , 2018 , 32 ( 5 ): 1811 - 1825 .
王超 , 孙玉秋 , 徐石瑶 , 等 . 自适应直方图均衡化图像增强算法研究 [J]. 长江大学学报(自科版) , 2018 , 15 ( 1 ): 55 - 59, 7 .
Wang Chao , Sun Yuqiu , Xu Shiyao , et al . Research on Image Enhancement Algorithm Based on Adaptive Histogram Equalization [J]. Journal of Yangtze University (Natural Science Edition) , 2018 , 15 ( 1 ): 55 - 59, 7 . (in Chinese)
Hu Jianwen , Wang Zeping , Hu Pei . A review of pansharpening methods based on deep learning [J]. Remote Sensing for Natural Resources , 2023 , 35 ( 1 ): 1 - 14 .
杨瑞 , 祁元 , 苏阳 . 深度学习U-Net方法及其在高分辨卫星影像分类中的应用 [J]. 遥感技术与应用 , 2020 , 35 ( 4 ): 767 - 774 .
Yang Rui , Qi Yuan , Su Yang . Deep Learning U-Net Method and Its Application in High-Resolution Satellite Image Classification [J]. Remote Sensing Technology and Application , 2020 , 35 ( 4 ): 767 - 774 . (in Chinese)
杨鹏飞 , 秦力 , 王英 , 等 . 城市雨水补给地下水利用研究进展 [J]. 人民珠江 , 2025 , 46 ( 4 ): 76 - 82 .
Yang Pengfei , Qin Li , Wang Ying , et al . Research Progress on Urban Rainwater Recharge for Groundwater Utilization [J]. Pearl River , 2025 , 46 ( 4 ): 76 - 82 . (in Chinese)
土地利用现状分类 : GB/T 21010—2017 [S]. doi: 10.1016/j.landusepol.2016.12.024 http://dx.doi.org/10.1016/j.landusepol.2016.12.024
Current Land Use Classification : GB/T 21010—2017 [S]. (in Chinese)
李国清 , 柏永青 , 杨轩 , 等 . 基于深度学习的高分辨率遥感影像土地覆盖自动分类方法 [J]. 地球信息科学学报 , 2021 , 23 ( 9 ): 1690 - 1704 . doi: 10.12082/dqxxkx.2021.200795 http://dx.doi.org/10.12082/dqxxkx.2021.200795
Li Guoqing , Bai Yongqing , Yang Xuan , et al . Automatic Land Cover Classification Method for High-Resolution Remote Sensing Images Based on Deep Learning [J]. Journal of Geo-information Science , 2021 , 23 ( 9 ): 1690 - 1704 . (in Chinese)
赵世明 , 赵锂 , 王耀堂 , 等 . 《建筑与小区雨水利用工程技术规范》部分内容的确定 [J]. 给水排水 , 2007 ( 4 ): 117 - 120 . doi: 10.3969/j.issn.1002-8471.2007.04.030 http://dx.doi.org/10.3969/j.issn.1002-8471.2007.04.030
Zhao Shiming , Zhao Li , Wang Yaotang , et al . Determination of Some Contents in Technical Code for Rainwater Utilization in Building and Sub-District Engineering [J]. Water & Wastewater Engineering , 2007 ( 4 ): 117 - 120 . (in Chinese)
室外排水设计规范 : GB 50014-2021 [S]. doi: 10.12173/j.issn.1004-5511.202302011 http://dx.doi.org/10.12173/j.issn.1004-5511.202302011
GB 50014—2021 Code for Design of Outdoor Wastewater Engineering [S]. (in Chinese)
Alivio M B , Radinja M , Šraj M , et al . Comparative analysis of event runoff coefficients and curve numbers in contrasting urban environments based on observed rainfall-runoff data [J]. Journal of Hydrology , 2024 , 645 : 132135 .
Patil D , Kumar G , Kumar A , et al . A systematic basin-wide approach for locating and assessing volumetric potential of rainwater harvesting sites in the urban area [J]. Environmental Science and Pollution Research , 2023 , 30 ( 6 ): 14707 - 14721 .
Zhan Xiaoyong , Huang Minlang . ArcCN-Runoff: an ArcGIS tool for generating curve number and runoff maps [J]. Environmental Modelling & Software , 2004 , 19 ( 10 ): 875 - 879 .
Al-Ghobari H , Dewidar A Z . Integrating GIS-Based MCDA Techniques and the SCS-CN Method for Identifying Potential Zones for Rainwater Harvesting in a Semi-Arid Area [J]. Water , 2021 , 13 ( 5 ): 704 .
Kadam A K , Kale S S , Pande N N , et al . Identifying Potential Rainwater Harvesting Sites of a Semi-arid, Basaltic Region of Western India, Using SCS-CN Method [J]. Water Resources Management , 2012 , 26 ( 9 ): 2537 - 2554 .
侯爽 . 城市绿地产流过程的影响因素及径流系数研究 [D]. 北京 : 北京建筑大学 , 2021 .
Hou Shuang . Study on Influencing Factors of Runoff Generation Process and Runoff Coefficient of Urban Green Space [D]. Beijing : Beijing University of Civil Engineering and Architecture , 2021 . (in Chinese)
海绵城市雨水控制与利用工程设计规范 : DB 11/ 685—2021 [S]. doi: 10.5194/egusphere-egu21-3301 http://dx.doi.org/10.5194/egusphere-egu21-3301
Code for Design of Stormwater Management and Harvest Engineering in Sponge City : DB 11/ 685—2021 [S]. (in Chinese)
胡振龙 . 山地城市典型下垫面径流系数研究 [D]. 重庆 : 重庆大学 , 2016 .
Hu Zhenlong . Study on Runoff Coefficients of Typical Underlying Surfaces in Mountain Cities [D]. Chongqing : Chongqing University , 2016 . (in Chinese)
张文慧 , 杨元园 . 基于ArcGIS Pro的西安市雨水资源潜力分析 [C]// 第十三届雨洪管理与水环境综合治理研讨会论文集 . 成都 : 中国给水排水出版社 , 2024 .
Zhang Wenhui , Yang Yuanyuan . Analysis of Rainwater Resource Potential in Xi’an Based on ArcGIS Pro [C]// Proceedings of the 13th Symposium on Stormwater Management and Integrated Water Environment Governance . Chengdu : China Water & Wastewater Press , 2024 . (in Chinese)
赵雪婷 , 程龙 , 张高锋 , 等 . 基于SCS模型的西安市主城区雨水资源化利用分析 [J]. 西北水电 , 2023 ( 6 ): 1 - 6 .
Zhao Xueting , Cheng Long , Zhang Gaofeng , et al . Analysis of Rainwater Resource Utilization in the Main Urban Area of Xi'an Based on the SCS Model [J]. Northwest Hydropower , 2023 ( 6 ): 1 - 6 . (in Chinese)
代仕铖 , 黎浩 , 蔡汶翰 , 等 . 城市立交桥桥面雨水收集的水文效应分析 [J/OL]. 人民珠江 : 1 - 20 [ 2026-07-21 ]. https://link.cnki.net/urlid/44.1037.tv.20260605.1132.002 https://link.cnki.net/urlid/44.1037.tv.20260605.1132.002 .
Dai Shicheng , Li Hao , Cai Wenhan , et al . Hydrological Effects Analysis of Rainwater Harvesting from Urban Interchange Bridge Decks [J/OL]. Pearl River : 1 - 20 [ 2026-07-21 ]. https://link.cnki.net/urlid/44.1037.tv.20260605.1132.002 https://link.cnki.net/urlid/44.1037.tv.20260605.1132.002 . (in Chinese)
冯憬 , 卫伟 , 冯青郁 . 黄土丘陵区SCS-CN模型径流曲线数的计算与校正 [J]. 生态学报 , 2021 , 41 ( 10 ): 4170 - 4181 . doi: 10.5846/stxb201912082665 http://dx.doi.org/10.5846/stxb201912082665
Feng Jing , Wei Wei , Feng Qingyu . Calculation and Correction of Runoff Curve Number of SCS-CN Model in Loess Hilly Region [J]. Acta Ecologica Sinica , 2021 , 41 ( 10 ): 4170 - 4181 . (in Chinese)
石虹远 , 梅超 , 刘家宏 , 等 . 中国北方典型城市雨水资源化利用潜力评估 [J]. 水利水运工程学报 , 2025 ( 6 ): 46 - 55 .
Shi Hongyuan , Mei Chao , Liu Jiahong , et al . Assessment of Rainwater Resource Utilization Potential in Typical Cities of Northern China [J]. Hydro-Science and Engineering , 2025 ( 6 ): 46 - 55 .. (in Chinese)
0
Views
0
下载量
0
CSCD
Publicity Resources
Related Articles
Related Author
Related Institution
京公网安备11010802024621