Edge-enhanced SAM for extracting photovoltaic power plants from remote sensing imagery

Accurate geospatial extent data of photovoltaic (PV) power plants is essential for assessing their socioeconomic benefits and environmental impacts. However, existing semantic segmentation models often result in over-smoothed edges and the inaccurate delineation of PV power plants. To address these...

Full description

Saved in:
Bibliographic Details
Main Authors: Yuehong Chen, Jiayue Zhou, Yu Chen, Jiawei Wang, Xiaoxiang Zhang, Yong Ge, Hongyuan Ma
Format: Article
Language:English
Published: Elsevier 2025-06-01
Series:International Journal of Applied Earth Observations and Geoinformation
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S1569843225002274
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850123796440154112
author Yuehong Chen
Jiayue Zhou
Yu Chen
Jiawei Wang
Xiaoxiang Zhang
Yong Ge
Hongyuan Ma
author_facet Yuehong Chen
Jiayue Zhou
Yu Chen
Jiawei Wang
Xiaoxiang Zhang
Yong Ge
Hongyuan Ma
author_sort Yuehong Chen
collection DOAJ
description Accurate geospatial extent data of photovoltaic (PV) power plants is essential for assessing their socioeconomic benefits and environmental impacts. However, existing semantic segmentation models often result in over-smoothed edges and the inaccurate delineation of PV power plants. To address these limitations, we proposed a novel edge-enhanced Segment Anything Model (ESAM) tailored for PV power plant extraction. It is designed as a multi-task network that integrates three key components: semantic segmentation, edge detection, and semantic and edge fusion. The semantic model leverages a modified Segment Anything Model (SAM) foundation model to extract semantic features of PV power plants. An edge module is developed to improve the edge delineation ability of ESAM. Additionally, a learning-based fusion module is designed to combine semantic and edge information to enhance PV power plant identifications. Validation demonstrates that ESAM achieved a high overall accuracy (OA = 98.46 %). Meanwhile, it outperformed three state-of-the-art models by providing higher accuracy metrics and more accurate edges of PV power plants. Thus, the proposed ESAM offers a robust tool for PV power plant extraction.
format Article
id doaj-art-d409124bb9d7454e9e61126ad5d3dee2
institution OA Journals
issn 1569-8432
language English
publishDate 2025-06-01
publisher Elsevier
record_format Article
series International Journal of Applied Earth Observations and Geoinformation
spelling doaj-art-d409124bb9d7454e9e61126ad5d3dee22025-08-20T02:34:31ZengElsevierInternational Journal of Applied Earth Observations and Geoinformation1569-84322025-06-0114010458010.1016/j.jag.2025.104580Edge-enhanced SAM for extracting photovoltaic power plants from remote sensing imageryYuehong Chen0Jiayue Zhou1Yu Chen2Jiawei Wang3Xiaoxiang Zhang4Yong Ge5Hongyuan Ma6Jiangsu Key Laboratory of Soil and Water Processes in Watershed, College of Geography and Remote Sensing, Hohai University, Nanjing 211100, ChinaJiangsu Key Laboratory of Soil and Water Processes in Watershed, College of Geography and Remote Sensing, Hohai University, Nanjing 211100, ChinaSchool of Geography, Nanjing Normal University, Nanjing 210023, China; Corresponding authors.Jiangsu Key Laboratory of Soil and Water Processes in Watershed, College of Geography and Remote Sensing, Hohai University, Nanjing 211100, ChinaJiangsu Key Laboratory of Soil and Water Processes in Watershed, College of Geography and Remote Sensing, Hohai University, Nanjing 211100, China; Corresponding authors.State Key Laboratory of Resources and Environmental Information System, Institute of Geographic Sciences and Natural Resources Research, Chinese Academy of Sciences, Beijing 100101, ChinaQinghai Huanghe Hydropower Development Co., LTD, Xining 810008, ChinaAccurate geospatial extent data of photovoltaic (PV) power plants is essential for assessing their socioeconomic benefits and environmental impacts. However, existing semantic segmentation models often result in over-smoothed edges and the inaccurate delineation of PV power plants. To address these limitations, we proposed a novel edge-enhanced Segment Anything Model (ESAM) tailored for PV power plant extraction. It is designed as a multi-task network that integrates three key components: semantic segmentation, edge detection, and semantic and edge fusion. The semantic model leverages a modified Segment Anything Model (SAM) foundation model to extract semantic features of PV power plants. An edge module is developed to improve the edge delineation ability of ESAM. Additionally, a learning-based fusion module is designed to combine semantic and edge information to enhance PV power plant identifications. Validation demonstrates that ESAM achieved a high overall accuracy (OA = 98.46 %). Meanwhile, it outperformed three state-of-the-art models by providing higher accuracy metrics and more accurate edges of PV power plants. Thus, the proposed ESAM offers a robust tool for PV power plant extraction.http://www.sciencedirect.com/science/article/pii/S1569843225002274PV power plantsSemantic segmentationEdge detectionLearning-based FusionSAM
spellingShingle Yuehong Chen
Jiayue Zhou
Yu Chen
Jiawei Wang
Xiaoxiang Zhang
Yong Ge
Hongyuan Ma
Edge-enhanced SAM for extracting photovoltaic power plants from remote sensing imagery
International Journal of Applied Earth Observations and Geoinformation
PV power plants
Semantic segmentation
Edge detection
Learning-based Fusion
SAM
title Edge-enhanced SAM for extracting photovoltaic power plants from remote sensing imagery
title_full Edge-enhanced SAM for extracting photovoltaic power plants from remote sensing imagery
title_fullStr Edge-enhanced SAM for extracting photovoltaic power plants from remote sensing imagery
title_full_unstemmed Edge-enhanced SAM for extracting photovoltaic power plants from remote sensing imagery
title_short Edge-enhanced SAM for extracting photovoltaic power plants from remote sensing imagery
title_sort edge enhanced sam for extracting photovoltaic power plants from remote sensing imagery
topic PV power plants
Semantic segmentation
Edge detection
Learning-based Fusion
SAM
url http://www.sciencedirect.com/science/article/pii/S1569843225002274
work_keys_str_mv AT yuehongchen edgeenhancedsamforextractingphotovoltaicpowerplantsfromremotesensingimagery
AT jiayuezhou edgeenhancedsamforextractingphotovoltaicpowerplantsfromremotesensingimagery
AT yuchen edgeenhancedsamforextractingphotovoltaicpowerplantsfromremotesensingimagery
AT jiaweiwang edgeenhancedsamforextractingphotovoltaicpowerplantsfromremotesensingimagery
AT xiaoxiangzhang edgeenhancedsamforextractingphotovoltaicpowerplantsfromremotesensingimagery
AT yongge edgeenhancedsamforextractingphotovoltaicpowerplantsfromremotesensingimagery
AT hongyuanma edgeenhancedsamforextractingphotovoltaicpowerplantsfromremotesensingimagery