Optimizing PV Panel Segmentation in Complex Environments Using Pre-Training and Simulated Annealing Algorithm: The JSWPVI

Photovoltaic (PV) technology, as a crucial source of clean energy, can effectively mitigate the impact of climate change caused by fossil fuel-based power generation. However, improper use of PV installations may encroach upon agricultural land, grasslands, and other land uses, thereby affecting loc...

Full description

Saved in:
Bibliographic Details
Main Authors: Rui Zhang, Ruikai Hong, Qiannan Li, Xu He, Age Shama, Jichao Lv, Renzhe Wu
Format: Article
Language:English
Published: MDPI AG 2025-06-01
Series:Land
Subjects:
Online Access:https://www.mdpi.com/2073-445X/14/6/1245
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850168380648062976
author Rui Zhang
Ruikai Hong
Qiannan Li
Xu He
Age Shama
Jichao Lv
Renzhe Wu
author_facet Rui Zhang
Ruikai Hong
Qiannan Li
Xu He
Age Shama
Jichao Lv
Renzhe Wu
author_sort Rui Zhang
collection DOAJ
description Photovoltaic (PV) technology, as a crucial source of clean energy, can effectively mitigate the impact of climate change caused by fossil fuel-based power generation. However, improper use of PV installations may encroach upon agricultural land, grasslands, and other land uses, thereby affecting local ecosystems. Exploring the spatial characteristics of centralized or distributed PV installations is essential for quantifying the development of clean energy and protecting agricultural land. Due to the distinct characteristics of centralized and distributed PV installations, large-scale mapping methods based on satellite remote sensing are insufficient for creating detailed PV distribution maps. This study proposes a model called Joint Semi-Supervised Weighted Adaptive PV Panel Recognition Model (JSWPVI)to achieve reliable PV mapping using UAV datasets. The JSWPVI employs a semi-supervised approach to construct and optimize a comprehensive segmentation network, incorporating the Spatial and Channel Weight Adaptive Model (SCWA) module to integrate different feature layers by reconstructing the spatial and channel weights of feature maps. Finally, a guided filtering algorithm is used to minimize non-edge noise while preserving edge integrity. Our results demonstrate that JSWPVI can accurately extract PV panels in both centralized and distributed scenarios, with an average extraction accuracy of 91.1% and a mean Intersection over Union of 77.7%. The findings of this study will assist regional policymakers in better quantifying renewable energy potential and assessing environmental impacts.
format Article
id doaj-art-719fff7676a6438da9ae342c281e1a67
institution OA Journals
issn 2073-445X
language English
publishDate 2025-06-01
publisher MDPI AG
record_format Article
series Land
spelling doaj-art-719fff7676a6438da9ae342c281e1a672025-08-20T02:20:58ZengMDPI AGLand2073-445X2025-06-01146124510.3390/land14061245Optimizing PV Panel Segmentation in Complex Environments Using Pre-Training and Simulated Annealing Algorithm: The JSWPVIRui Zhang0Ruikai Hong1Qiannan Li2Xu He3Age Shama4Jichao Lv5Renzhe Wu6Faculty of Geosciences and Engineering, Southwest Jiaotong University, Chengdu 611756, ChinaFaculty of Geosciences and Engineering, Southwest Jiaotong University, Chengdu 611756, ChinaHenan Provincial Key Laboratory of Ecological Environment Remote Sensing, Zhengzhou 450046, ChinaFaculty of Geosciences and Engineering, Southwest Jiaotong University, Chengdu 611756, ChinaFaculty of Geosciences and Engineering, Southwest Jiaotong University, Chengdu 611756, ChinaFaculty of Geosciences and Engineering, Southwest Jiaotong University, Chengdu 611756, ChinaFaculty of Geosciences and Engineering, Southwest Jiaotong University, Chengdu 611756, ChinaPhotovoltaic (PV) technology, as a crucial source of clean energy, can effectively mitigate the impact of climate change caused by fossil fuel-based power generation. However, improper use of PV installations may encroach upon agricultural land, grasslands, and other land uses, thereby affecting local ecosystems. Exploring the spatial characteristics of centralized or distributed PV installations is essential for quantifying the development of clean energy and protecting agricultural land. Due to the distinct characteristics of centralized and distributed PV installations, large-scale mapping methods based on satellite remote sensing are insufficient for creating detailed PV distribution maps. This study proposes a model called Joint Semi-Supervised Weighted Adaptive PV Panel Recognition Model (JSWPVI)to achieve reliable PV mapping using UAV datasets. The JSWPVI employs a semi-supervised approach to construct and optimize a comprehensive segmentation network, incorporating the Spatial and Channel Weight Adaptive Model (SCWA) module to integrate different feature layers by reconstructing the spatial and channel weights of feature maps. Finally, a guided filtering algorithm is used to minimize non-edge noise while preserving edge integrity. Our results demonstrate that JSWPVI can accurately extract PV panels in both centralized and distributed scenarios, with an average extraction accuracy of 91.1% and a mean Intersection over Union of 77.7%. The findings of this study will assist regional policymakers in better quantifying renewable energy potential and assessing environmental impacts.https://www.mdpi.com/2073-445X/14/6/1245photovoltaic panelscontrast learningsimulated annealing algorithmimage segmentationaerial remote sensingadaptive weights
spellingShingle Rui Zhang
Ruikai Hong
Qiannan Li
Xu He
Age Shama
Jichao Lv
Renzhe Wu
Optimizing PV Panel Segmentation in Complex Environments Using Pre-Training and Simulated Annealing Algorithm: The JSWPVI
Land
photovoltaic panels
contrast learning
simulated annealing algorithm
image segmentation
aerial remote sensing
adaptive weights
title Optimizing PV Panel Segmentation in Complex Environments Using Pre-Training and Simulated Annealing Algorithm: The JSWPVI
title_full Optimizing PV Panel Segmentation in Complex Environments Using Pre-Training and Simulated Annealing Algorithm: The JSWPVI
title_fullStr Optimizing PV Panel Segmentation in Complex Environments Using Pre-Training and Simulated Annealing Algorithm: The JSWPVI
title_full_unstemmed Optimizing PV Panel Segmentation in Complex Environments Using Pre-Training and Simulated Annealing Algorithm: The JSWPVI
title_short Optimizing PV Panel Segmentation in Complex Environments Using Pre-Training and Simulated Annealing Algorithm: The JSWPVI
title_sort optimizing pv panel segmentation in complex environments using pre training and simulated annealing algorithm the jswpvi
topic photovoltaic panels
contrast learning
simulated annealing algorithm
image segmentation
aerial remote sensing
adaptive weights
url https://www.mdpi.com/2073-445X/14/6/1245
work_keys_str_mv AT ruizhang optimizingpvpanelsegmentationincomplexenvironmentsusingpretrainingandsimulatedannealingalgorithmthejswpvi
AT ruikaihong optimizingpvpanelsegmentationincomplexenvironmentsusingpretrainingandsimulatedannealingalgorithmthejswpvi
AT qiannanli optimizingpvpanelsegmentationincomplexenvironmentsusingpretrainingandsimulatedannealingalgorithmthejswpvi
AT xuhe optimizingpvpanelsegmentationincomplexenvironmentsusingpretrainingandsimulatedannealingalgorithmthejswpvi
AT ageshama optimizingpvpanelsegmentationincomplexenvironmentsusingpretrainingandsimulatedannealingalgorithmthejswpvi
AT jichaolv optimizingpvpanelsegmentationincomplexenvironmentsusingpretrainingandsimulatedannealingalgorithmthejswpvi
AT renzhewu optimizingpvpanelsegmentationincomplexenvironmentsusingpretrainingandsimulatedannealingalgorithmthejswpvi