基于对象图像分析与Sentinel影像的光伏电站精细化提取

doi:10.13474/j.cnki.11-2246.2025.0621

测绘通报 ›› 2025, Vol. 0 ›› Issue (6): 123-129.doi: 10.13474/j.cnki.11-2246.2025.0621

• 技术交流 • 上一篇

基于对象图像分析与Sentinel影像的光伏电站精细化提取

周超辉¹, 李林泽¹, 章继成^2,3, 毛宏智⁴, 韩涛^2,3

1. 中国长江三峡集团有限公司, 湖北武汉 430010;
2. 中国长江电力股份有限公司, 湖北宜昌 443002;
3. 三峡电能有限公司, 湖北武汉 430024;
4. 华中科技大学环境科学与工程学院, 湖北武汉 430074

收稿日期:2024-11-25 发布日期:2025-07-04
通讯作者: 毛宏智。E-mail:maohongzhi@hust.edu.cn
作者简介:周超辉(1992—),男,博士,主要从事可再生能源设备的遥感识别与规划研究。E-mail:zch_hui@foxmail.com
基金资助:
中国长江电力股份有限公司科研项目(Z342302008)

Optimized extraction of photovoltaic power stations based on object image analysis and Sentinel images

ZHOU Chaohui¹, LI Linze¹, ZHANG Jicheng^2,3, MAO Hongzhi⁴, HAN Tao^2,3

1. China Three Gorges Corporation, Wuhan 430010, China;
2. China Yangtze Power Co., Ltd., Yichang 443002, China;
3. Three Gorges Electric Energy Co., Ltd., Wuhan 430024, China;
4. School of Environmental Science and Engineering, Huazhong University of Science and Technology, Wuhan 430074, China

Received:2024-11-25 Published:2025-07-04

摘要/Abstract

摘要： 为实现碳达峰碳中和的能源目标,光伏电站的建设迅速增长,统计光伏电站的分布与规模有利于能源管理与规划。现有的应用遥感影像数据提取光伏电站的方法,存在提取精细程度不高与小面积光伏电站丢失的情况。本文采用基于对象的图像分析方法,利用Sentinel-2与Sentinel-1影像数据提取光谱特征、指数特征与几何特征,建立随机森林提取模型,并分析了多尺度分割在不同地形下的最佳分割参数。最优的全局分割参数是分割尺度、形状因子与紧凑度,分别为50、0.7、0.5。本文模型在验证集上得到的光伏电站用户精度为98.21%,生产者精度为95.85%。最终绘制了2024年湖北省光伏电站分布地图,全省光伏电站安装面积为230.8km²。

关键词: 光伏电站, 基于对象的图像分析, Sentinel影像, 湖北省

Abstract: To achieve the energy goal of carbon peak and carbon neutrality, the construction of photovoltaic (PV) power stations has been growing rapidly, and the statistics of distribution and scale of PV power stations are beneficial to energy management and planning. Existing methods of applying remote sensing image data for PV power stations extraction suffer from the lack of extraction fineness and the loss of small-area PV power stations. In this study, an object-based image analysis method is adopted to extract spectral, index and geometric features using Sentinel-2 and Sentinel-1 image data, establish a random forest extraction model, and analyze the optimal segmentation parameters for multi-scale segmentation in different terrains. The optimal global segmentation parameters are segmentation scale, shape factor and compactness of 50, 0.7 and 0.5 respectively. The model established in this paper obtaines an accuracy of 98.21% for PV plant users and 95.85% for producers on the validation set. Finally, the distribution map of PV power stations in Hubei province in 2024 is drawn, and the installed area of PV power stations in the province is 230.8 km².

Key words: photovoltaic power plants, object-based image analysis, Sentinel images, Hubei province

中图分类号:

P237

周超辉, 李林泽, 章继成, 毛宏智, 韩涛. 基于对象图像分析与Sentinel影像的光伏电站精细化提取[J]. 测绘通报, 2025, 0(6): 123-129.

ZHOU Chaohui, LI Linze, ZHANG Jicheng, MAO Hongzhi, HAN Tao. Optimized extraction of photovoltaic power stations based on object image analysis and Sentinel images[J]. Bulletin of Surveying and Mapping, 2025, 0(6): 123-129.

/ 推荐

参考文献

[1] 国家能源局.2023年光伏发电建设情况[R/OL].(2024-02-28) [2024-10-22].https://www.nea.gov.cn/2024-02/28/c_1310765696.htm.
[2] ASSOCIATION S E I.U.S.Solar Market Insight 2023 Year in Review [R/OL].(2024-03-06) [2024-10-15].https://www.seia.org/us-solar-market-insight.
[3] 王胜利,张连蓬,朱寿红,等.多共性特征联合的Landsat 8 OLI遥感影像光伏电站提取[J].测绘通报,2018(11): 46-52.
[4] 李彦甫,刘勇.基于对象影像分析方法支持下的多源遥感影像光伏电场提取[J].测绘与空间地理信息,2016,39(3): 68-72.
[5] XIA Zilong,LI Yingjie,CHEN Ruishan,et al.Mapping the rapid development of photovoltaic power stations in northwestern China using remote sensing[J].Energy Reports,2022,8: 4117-4127.
[6] GE Fan,WANG Guizhou,HE Guojin,et al.A hierarchical information extraction method for large-scale centralized photovoltaic power plants based on multi-source remote sensing images[J].Remote Sensing,2022,14(17): 4211.
[7] KRUITWAGEN L,STORY K T,FRIEDRICH J,et al.A global inventory of photovoltaic solar energy generating units[J].Nature,2021,598(7882): 604-610.
[8] MAO Hongzhi,CHEN Xie,LUO Yongqiang,et al.Advances and prospects on estimating solar photovoltaic installation capacity and potential based on satellite and aerial images[J].Renewable and Sustainable Energy Reviews,2023,179: 113276.
[9] 陈笛,彭秋志,黄培依,等.采用注意力机制与改进YOLOv5的光伏用地检测[J].自然资源遥感,2023,35(4): 90-95.
[10] FENG Q,NIU B,REN Y,et al.A 10-m national-scale map of ground-mounted photovoltaic power stations in China of 2020[J].Scientific Data,2024,11(1): 198.
[11] ZHANG Xunhe,ZERAATPISHEH M,RAHMAN M M,et al.Texture is important in improving the accuracy of mapping photovoltaic power plants: a case study of Ningxia autonomous region,China[J].Remote Sensing,2021,13(19): 3909.
[12] JIANG Wenhao,TIAN Bo,DUAN Yuanqiang,et al.Rapid mapping and spatial analysis on the distribution of photovoltaic power stations with Sentinel-1&2 images in Chinese coastal provinces[J].International Journal of Applied Earth Observation and Geoinformation,2023,118: 103280.
[13] 梁斯铭.基于卫星和航拍正射图像的光伏目标识别与提取方法研究[D].杭州: 浙江大学,2021.
[14] PLAKMAN V,ROSIER J,VAN VLIET J.Solar park detection from publicly available satellite imagery[J].GIScience & Remote Sensing,2022,59(1): 462-481.
[15] LADISA C,CAPOLUPO A,RIPA M N,et al.Combining OBIA approach and machine learning algorithm to extract photovoltaic panels from Sentinel-2 images automatically[C]//Proceedings of 2022 Remote Sensing for Agriculture,Ecosystems,and Hydrology XXIV.Berlin:SPIE,2022.
[16] WANG Zirui,HAO Zhen,JIA Xiaofeng,et al.Unravelling spatiotemporal patterns of solar photovoltaic plants development in China in the 21st century[J].Environmental Research Letters,2024,19(3): 034005.

基于对象图像分析与Sentinel影像的光伏电站精细化提取

Optimized extraction of photovoltaic power stations based on object image analysis and Sentinel images

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 4

编辑推荐

Metrics

本文评价

[1]	周玄德, 窦文章, 詹庆明, 孜比布拉·司马义, 邓祖涛, 曾勇. 基于县域单元的湖北省碳排放时空格局演变特征[J]. 测绘通报, 2022, 0(11): 149-156,161.
[2]	洪亮, 黄露, 史晓明, 余晓敏. 湖北省资源环境承载能力监测预警长效机制建立初探[J]. 测绘通报, 2018, 0(11): 103-106,110.
[3]	王胜利, 张连蓬, 朱寿红, 吉莉, 柴琪, 沈扬, 张蕊. 多共性特征联合的Landsat 8 OLI遥感影像光伏电站提取[J]. 测绘通报, 2018, 0(11): 46-52.
[4]	王胜利, 张连蓬, 李行, 赵卓文, 沈扬, 柴琪. 面向特定目标地物提取的改进最佳波段组合方法研究[J]. 测绘通报, 2017, 0(7): 49-54.