A hybrid framework for estimating photovoltaic dust content based on UAV hyperspectral images

Dust is one of the key factors influencing photovoltaic (PV) power generation. The ability to accurately capture PV dust information is essential for PV operation and sustainable utilization. This study employs uncrewed aerial vehicle (UAV) hyperspectral imaging to monitor PV dust deposition. To add...

Full description

Saved in:
Bibliographic Details
Main Authors: Peng Zhu, Hao Li, Pan Zheng
Format: Article
Language:English
Published: Elsevier 2025-05-01
Series:International Journal of Applied Earth Observations and Geoinformation
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S1569843225001475
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850032967926153216
author Peng Zhu
Hao Li
Pan Zheng
author_facet Peng Zhu
Hao Li
Pan Zheng
author_sort Peng Zhu
collection DOAJ
description Dust is one of the key factors influencing photovoltaic (PV) power generation. The ability to accurately capture PV dust information is essential for PV operation and sustainable utilization. This study employs uncrewed aerial vehicle (UAV) hyperspectral imaging to monitor PV dust deposition. To address the problems of information redundancy in hyperspectral data and the backpropagation neural network (BPNN) easily falling into local optimum, a high-precision UAV hyperspectral PV dust estimation method is proposed. The fractional order derivative (FOD) is applied to the spectral reflectance of PV dust accumulation, and a PV dust estimation model with sine map tuna swarm optimized backpropagation neural network (STSO-BPNN) is established, which is validated using UAV hyperspectral images and ground measured dust data. The results show that FOD improves the spectral signal-to-noise ratio, and the 0.2 order STSO-BPNN model achieves higher accuracy (R2 = 0.95, RMSE = 0.79 g/m2, RPIQ = 7.98). These findings provide a scientific basis for the rapid and accurate estimation and mapping of PV dust accumulation while proposing a novel strategy for efficient PV implementation and management.
format Article
id doaj-art-5eccafc4dd78464ea533b13e95651598
institution DOAJ
issn 1569-8432
language English
publishDate 2025-05-01
publisher Elsevier
record_format Article
series International Journal of Applied Earth Observations and Geoinformation
spelling doaj-art-5eccafc4dd78464ea533b13e956515982025-08-20T02:58:25ZengElsevierInternational Journal of Applied Earth Observations and Geoinformation1569-84322025-05-0113910450010.1016/j.jag.2025.104500A hybrid framework for estimating photovoltaic dust content based on UAV hyperspectral imagesPeng Zhu0Hao Li1Pan Zheng2School of Earth Sciences and Engineering, Hohai University, Nanjing 211100, ChinaCorresponding author at: School of Earth Sciences and Engineering, Hohai University, No. 8 Fochengxi Road, Nanjing, Jiangsu 211100, China.; School of Earth Sciences and Engineering, Hohai University, Nanjing 211100, ChinaSchool of Earth Sciences and Engineering, Hohai University, Nanjing 211100, ChinaDust is one of the key factors influencing photovoltaic (PV) power generation. The ability to accurately capture PV dust information is essential for PV operation and sustainable utilization. This study employs uncrewed aerial vehicle (UAV) hyperspectral imaging to monitor PV dust deposition. To address the problems of information redundancy in hyperspectral data and the backpropagation neural network (BPNN) easily falling into local optimum, a high-precision UAV hyperspectral PV dust estimation method is proposed. The fractional order derivative (FOD) is applied to the spectral reflectance of PV dust accumulation, and a PV dust estimation model with sine map tuna swarm optimized backpropagation neural network (STSO-BPNN) is established, which is validated using UAV hyperspectral images and ground measured dust data. The results show that FOD improves the spectral signal-to-noise ratio, and the 0.2 order STSO-BPNN model achieves higher accuracy (R2 = 0.95, RMSE = 0.79 g/m2, RPIQ = 7.98). These findings provide a scientific basis for the rapid and accurate estimation and mapping of PV dust accumulation while proposing a novel strategy for efficient PV implementation and management.http://www.sciencedirect.com/science/article/pii/S1569843225001475UAV hyperspectral imageryPV dustFractional order derivativeMachine learning
spellingShingle Peng Zhu
Hao Li
Pan Zheng
A hybrid framework for estimating photovoltaic dust content based on UAV hyperspectral images
International Journal of Applied Earth Observations and Geoinformation
UAV hyperspectral imagery
PV dust
Fractional order derivative
Machine learning
title A hybrid framework for estimating photovoltaic dust content based on UAV hyperspectral images
title_full A hybrid framework for estimating photovoltaic dust content based on UAV hyperspectral images
title_fullStr A hybrid framework for estimating photovoltaic dust content based on UAV hyperspectral images
title_full_unstemmed A hybrid framework for estimating photovoltaic dust content based on UAV hyperspectral images
title_short A hybrid framework for estimating photovoltaic dust content based on UAV hyperspectral images
title_sort hybrid framework for estimating photovoltaic dust content based on uav hyperspectral images
topic UAV hyperspectral imagery
PV dust
Fractional order derivative
Machine learning
url http://www.sciencedirect.com/science/article/pii/S1569843225001475
work_keys_str_mv AT pengzhu ahybridframeworkforestimatingphotovoltaicdustcontentbasedonuavhyperspectralimages
AT haoli ahybridframeworkforestimatingphotovoltaicdustcontentbasedonuavhyperspectralimages
AT panzheng ahybridframeworkforestimatingphotovoltaicdustcontentbasedonuavhyperspectralimages
AT pengzhu hybridframeworkforestimatingphotovoltaicdustcontentbasedonuavhyperspectralimages
AT haoli hybridframeworkforestimatingphotovoltaicdustcontentbasedonuavhyperspectralimages
AT panzheng hybridframeworkforestimatingphotovoltaicdustcontentbasedonuavhyperspectralimages