Impact of PM2.5 Pollution on Solar Photovoltaic Power Generation in Hebei Province, China
Abstract
1. Introduction
2. Materials and Methods
2.1. Study Sites and Data
2.2. Methods
2.2.1. Software Implementation and PVOD Dataset Processing Framework
2.2.2. Criteria for Selecting PM2.5 Pollution Levels and Background Days
2.2.3. Machine Learning Models
2.2.4. Experiment Design
- (1)
- Model Selection
- (2)
- Input variable configuration
- (3)
- Model Training and Hyperparameter Optimization
- (4)
- Stacking Ensemble Framework
2.2.5. Evaluation Metrics
3. Results
3.1. Spatiotemporal Dynamics of PV Power Output
3.1.1. Temporal Variation Characteristics
3.1.2. Spatial Variation Characteristics
3.2. The Response of PV Power Generation Dynamics to PM2.5 Pollution
3.3. Machine Learning-Based Assessment of Air Pollution Effects on PV Performance
3.4. Stacking Framework for Enhanced Predictive Accuracy
4. Discussion
5. Conclusions
Supplementary Materials
Author Contributions
Funding
Institutional Review Board Statement
Informed Consent Statement
Data Availability Statement
Conflicts of Interest
Abbreviations
AdaBoost | Adaptive Boosting |
ANN | Artificial Neural Network |
BP | Backpropagation Neural Network |
CHAP | ChinaHighAirPollutants |
CV-R2 | Cross-Validation Coefficient of Determination |
DHI | Diffuse Horizontal Irradiance |
DT | Decision Tree |
GHI | Global Horizontal Irradiance |
KNN | K-Nearest Neighbors |
LMD | Local Measurement Data |
MAE | Mean Absolute Error |
MAPE | Mean Absolute Percentage Error |
MSE | Mean Squared Error |
NWP | Numerical Weather Prediction |
P | Atmospheric Pressure |
PM2.5 | Particulate Matter with diameter ≤ 2.5 micrometers |
PV | Photovoltaic |
PVOD | Photovoltaic Output Dataset |
R2 | Coefficient of Determination |
RBF | Radial Basis Function |
RF | Random Forest |
RMSE | Root Mean Square Error |
STD | Standard Deviation |
SVM | Support Vector Machine |
SVR | Support Vector Regression |
T | Temperature |
WD | Wind Direction |
WS | Wind Speed |
References
- Zhang, D.; Li, Y.; Chin, K.-S. Photovoltaic technology assessment based on cumulative prospect theory and hybrid information from sustainable perspective. Sustain. Energy Technol. Assess. 2022, 52, 102116. [Google Scholar] [CrossRef]
- Kabir, E.; Kumar, P.; Kumar, S.; Adelodun, A.A.; Kim, K.-H. Solar energy: Potential and future prospects. Renew. Sustain. Energy Rev. 2018, 82, 894–900. [Google Scholar] [CrossRef]
- Hernandez, R.R.; Armstrong, A.; Burney, J.; Ryan, G.; Moore-O’Leary, K.; Diédhiou, I.; Grodsky, S.M.; Saul-Gershenz, L.; Davis, R.; Macknick, J. Techno–ecological synergies of solar energy for global sustainability. Nat. Sustain. 2019, 2, 560–568. [Google Scholar] [CrossRef]
- Queisser, H.J.; Werner, J.H. Principles and technology of photovoltaic energy conversion. In Proceedings of the 4th International Conference on Solid-State and IC Technology, Beijing, China, 24–28 October 1995; pp. 146–150. [Google Scholar]
- Yao, T.; Wang, J.; Wu, H.; Zhang, P.; Li, S.; Wang, Y.; Chi, X.; Shi, M. A photovoltaic power output dataset: Multi-source photovoltaic power output dataset with Python toolkit. Sol. Energy 2021, 230, 122–130. [Google Scholar] [CrossRef]
- Benghanem, M.; Mellit, A.; Alamri, S.N. ANN-based modelling and estimation of daily global solar radiation data: A case study. Energy Convers. Manag. 2009, 50, 1644–1655. [Google Scholar] [CrossRef]
- Gueymard, C.A.; Ruiz-Arias, J.A. Extensive worldwide validation and climate sensitivity analysis of direct irradiance predictions from 1-min global irradiance. Sol. Energy 2016, 128, 1–30. [Google Scholar] [CrossRef]
- Son, J.; Jeong, S.; Park, H.; Park, C.-E. The effect of particulate matter on solar photovoltaic power generation over the Republic of Korea. Environ. Res. Lett. 2020, 15, 84004. [Google Scholar] [CrossRef]
- Kumar, P.; Vogel, H.; Bruckert, J.; Muth, L.J.; Hoshyaripour, G.A. MieAI: A neural network for calculating optical properties of internally mixed aerosol in atmospheric models. npj Clim. Atmos. Sci. 2024, 7, 110. [Google Scholar] [CrossRef]
- Samset, B.H.; Stjern, C.W.; Andrews, E.; Kahn, R.A.; Myhre, G.; Schulz, M.; Schuster, G.L. Aerosol Absorption: Progress Towards Global and Regional Constraints. Curr. Clim. Change Rep. 2018, 4, 65–83. [Google Scholar] [CrossRef] [PubMed]
- Zhang, X.; Chen, S.; Kang, L.; Yuan, T.; Luo, Y.; Alam, K.; Li, J.; He, Y.; Bi, H.; Zhao, D. Direct Radiative Forcing Induced by Light-Absorbing Aerosols in Different Climate Regions Over East Asia. J. Geophys. Res. Atmos. 2020, 125, e2019JD032228. [Google Scholar] [CrossRef]
- Yang, Y.; Mou, S.; Wang, H.; Wang, P.; Li, B.; Liao, H. Global source apportionment of aerosols into major emission regions and sectors over 1850–2017. Atmos. Chem. Phys. 2024, 24, 6509–6523. [Google Scholar] [CrossRef]
- Ghosh, S.; Dey, S.; Ganguly, D.; Roy, S.B.; Bali, K. Cleaner air would enhance India’s annual solar energy production by 6–28 TWh. Environ. Res. Lett. 2022, 17, 54007. [Google Scholar] [CrossRef]
- Ghosh, S.; Ganguly, D.; Dey, S.; Chowdhury, S.G. Future photovoltaic potential in India: Navigating the interplay between air pollution control and climate change mitigation. Environ. Res. Lett. 2024, 19, 124030. [Google Scholar] [CrossRef]
- Song, Z.; Wang, M.; Yang, H. Quantification of the Impact of Fine Particulate Matter on Solar Energy Resources and Energy Performance of Different Photovoltaic Technologies. ACS Environ. Au 2022, 2, 275–286. [Google Scholar] [CrossRef] [PubMed]
- Sun, K.; Lu, L.; Jiang, Y.; Wang, Y.; Zhou, K.; He, Z. Integrated effects of PM2.5 deposition, module surface conditions and nanocoatings on solar PV surface glass transmittance. Renew. Sustain. Energy Rev. 2018, 82, 4107–4120. [Google Scholar] [CrossRef]
- Kim, M.J. Air Pollution and Solar Photovoltaic Power Generation: Evidence from South Korea. Energy Econ. 2024, 139, 107924. [Google Scholar] [CrossRef]
- Bao, Z.; Shi, R.; Huang, Y.; Song, X. Photovoltaic generation potential and developmental suitability in southern Hebei. Energy Rep. 2023, 9, 795–805. [Google Scholar] [CrossRef]
- Wang, P.; Zhang, S.; Pu, Y.; Cao, S.; Zhang, Y. Estimation of photovoltaic power generation potential in 2020 and 2030 using land resource changes: An empirical study from China. Energy 2021, 219, 119611. [Google Scholar] [CrossRef]
- Liang, L.; Chen, Z.; Chen, S.; Zheng, X. Evaluation of Site Suitability for Photovoltaic Power Plants in the Beijing-Tianjin-Hebei Region of China Using a Combined Weighting Method. Land 2024, 13, 40. [Google Scholar] [CrossRef]
- Wu, W.; Zhang, M.; Ding, Y. Exploring the effect of economic and environment factors on PM2.5 concentration: A case study of the Beijing-Tianjin-Hebei region. J. Environ. Manag. 2020, 268, 110703. [Google Scholar] [CrossRef] [PubMed]
- He, C.; Huang, G.; Liu, L.; Li, Y.; Zhai, M.; Cao, R. Assessment and offset of the adverse effects induced by PM2.5 from coal-fired power plants in China. J. Clean. Prod. 2021, 286, 125397. [Google Scholar] [CrossRef]
- Huang, T.; Yu, Y.; Wei, Y.; Wang, H.; Huang, W.; Chen, X. Spatial-seasonal characteristics and critical impact factors of PM2.5 concentration in the Beijing-Tianjin-Hebei urban agglomeration. PLoS ONE 2018, 13, e0201364. [Google Scholar] [CrossRef]
- Zhou, J.; Yin, T.; Tian, J. Research on the impact of Beijing-Tianjin-Hebei electric power and thermal power industry on haze pollution. Energy Rep. 2022, 8, 1698–1710. [Google Scholar] [CrossRef]
- Mayer, M.J.; Gróf, G. Extensive comparison of physical models for photovoltaic power forecasting. Appl. Energy 2021, 283, 116239. [Google Scholar] [CrossRef]
- Moreira, M.; Balestrassi, P.; Paiva, A.; Ribeiro, P.; Bonatto, B. Design of experiments using artificial neural network ensemble for photovoltaic generation forecasting. Renew. Sustain. Energy Rev. 2021, 135, 110450. [Google Scholar] [CrossRef]
- Sobri, S.; Koohi-Kamali, S.; Rahim, N.A. Solar photovoltaic generation forecasting methods: A review. Energy Convers. Manag. 2018, 156, 459–497. [Google Scholar] [CrossRef]
- Zheng, Z.; Chen, Y.; Huo, M.; Zhao, B. An overview: The development of prediction technology of wind and photovoltaic power generation. Energy Procedia 2011, 12, 601–608. [Google Scholar] [CrossRef]
- Luo, X.; Zhang, D.; Zhu, X. Deep learning based forecasting of photovoltaic power generation by incorporating domain knowledge. Energy 2021, 225, 120240. [Google Scholar] [CrossRef]
- Yadav, A.K.; Chandel, S.S. Solar radiation prediction using Artificial Neural Network techniques: A review. Renew. Sustain. Energy Rev. 2014, 33, 772–781. [Google Scholar] [CrossRef]
- Zendehboudi, A.; Baseer, M.A.; Saidur, R. Application of support vector machine models for forecasting solar and wind energy resources: A review. J. Clean. Prod. 2018, 199, 272–285. [Google Scholar] [CrossRef]
- Simon, S.M.; Glaum, P.; Valdovinos, F.S. Interpreting random forest analysis of ecological models to move from prediction to explanation. Sci. Rep. 2023, 13, 3881. [Google Scholar] [CrossRef]
- Wang, Y.; Tian, S.; Zhang, P. Novel spatio-temporal attention causal convolutional neural network for multi-site PM2.5 prediction. Front. Environ. Sci. 2024, 12, 1408370. [Google Scholar] [CrossRef]
- Mfetoum, I.M.; Ngoh, S.K.; Molu, R.J.J.; Nde Kenfack, B.F.; Onguene, R.; Naoussi, S.R.D.; Tamba, J.G.; Bajaj, M.; Berhanu, M. A multilayer perceptron neural network approach for optimizing solar irradiance forecasting in Central Africa with meteorological insights. Sci. Rep. 2024, 14, 3572. [Google Scholar]
- Feng, Y.; Hao, W.; Li, H.; Cui, N.; Gong, D.; Gao, L. Machine learning models to quantify and map daily global solar radiation and photovoltaic power. Renew. Sustain. Energy Rev. 2020, 118, 109393. [Google Scholar] [CrossRef]
- Odhiambo, M.R.O.; Abbas, A.; Wang, X.; Mutinda, G. Solar Energy Potential in the Yangtze River Delta Region-A GIS-Based Assessment. Energies 2021, 14, 143. [Google Scholar] [CrossRef]
- Wu, W.; Zhang, T.; Xie, X.; Huang, Z. Regional low carbon development pathways for the Yangtze River Delta region in China. Energy Policy 2021, 151, 112172. [Google Scholar] [CrossRef]
- Xu, C.; Xie, D.; Gu, C.; Zhao, P.; Wang, X.; Wang, Y. Sustainable development pathways for energies in Yangtze River Delta urban agglomeration. Sci. Rep. 2023, 13, 18135. [Google Scholar] [CrossRef] [PubMed]
- Xu, J.; Zhao, C.; Wang, F.; Yang, G. Industrial decarbonisation oriented distributed renewable generation towards wastewater treatment sector: Case from the Yangtze River Delta region in China. Energy 2022, 256, 124562. [Google Scholar] [CrossRef]
- Peng, Y.; Azadi, H.; Yang, L.; Scheffran, J.; Jiang, P. Assessing the Siting Potential of Low-Carbon Energy Power Plants in the Yangtze River Delta: A GIS-Based Approach. Energies 2022, 15, 2167. [Google Scholar] [CrossRef]
- Liang, M.S.; Huang, G.H.; Chen, J.P.; Li, Y.P. Energy-water-carbon nexus system planning: A case study of Yangtze River Delta urban agglomeration, China. Appl. Energy 2022, 308, 118144. [Google Scholar] [CrossRef]
- Wei, J.; Li, Z.; Lyapustin, A.; Sun, L.; Peng, Y.; Xue, W.; Su, T.; Cribb, M. Reconstructing 1-km-resolution high-quality PM2.5 data records from 2000 to 2018 in China: Spatiotemporal variations and policy implications. Remote Sens. Environ. 2021, 252, 112136. [Google Scholar] [CrossRef]
- Wei, J.; Li, Z.; Cribb, M.; Huang, W.; Xue, W.; Sun, L.; Guo, J.; Peng, Y.; Li, J.; Lyapustin, A.; et al. Improved 1 km resolution PM2.5 estimates across China using enhanced space–time extremely randomized trees. Atmos. Chem. Phys. 2020, 20, 3273–3289. [Google Scholar] [CrossRef]
- Liu, C.; Gao, Z.; Li, Y.; Gao, C.Y.; Su, Z.; Zhang, X. Surface Energy Budget Observed for Winter Wheat in the North China Plain During a Fog-Haze Event. Bound.-Layer Meteorol. 2019, 170, 489–505. [Google Scholar] [CrossRef]
- Sun, Y.; Zhang, J.; Zhang, Y. Adaboost algorithm combined multiple random forest models (Adaboost-RF) is employed for fluid prediction using well logging data. Phys. Fluids 2024, 36, 16602. [Google Scholar] [CrossRef]
- Essamlali, I.; Nhaila, H.; El Khaili, M. Supervised Machine Learning Approaches for Predicting Key Pollutants and for the Sustainable Enhancement of Urban Air Quality: A Systematic Review. Sustainability 2024, 16, 976. [Google Scholar] [CrossRef]
- Benti, N.E.; Chaka, M.D.; Semie, A.G. Forecasting Renewable Energy Generation with Machine Learning and Deep Learning: Current Advances and Future Prospects. Sustainability 2023, 15, 7087. [Google Scholar] [CrossRef]
- Vasisht, M.S.; Srinivasan, J.; Ramasesha, S.K. Performance of solar photovoltaic installations: Effect of seasonal variations. Sol. Energy 2016, 131, 39–46. [Google Scholar] [CrossRef]
- Li, X.; Wagner, F.; Peng, W.; Yang, J.; Mauzerall, D.L. Reduction of solar photovoltaic resources due to air pollution in China. Proc. Natl. Acad. Sci. USA 2017, 114, 11867–11872. [Google Scholar] [CrossRef]
- Song, Z.; Liu, J.; Yang, H. Air pollution and soiling implications for solar photovoltaic power generation: A comprehensive review. Appl. Energy 2021, 298, 117247. [Google Scholar] [CrossRef]
- Song, Z.; Cao, S.; Yang, H. Quantifying the air pollution impacts on solar photovoltaic capacity factors and potential benefits of pollution control for the solar sector in China. Appl. Energy 2024, 365, 123261. [Google Scholar] [CrossRef]
- Labordena, M.; Neubauer, D.; Folini, D.; Patt, A.; Lilliestam, J. Blue skies over China: The effect of pollution-control on solar power generation and revenues. PLoS ONE 2018, 13, e0207028. [Google Scholar] [CrossRef] [PubMed]
- Chiabrando, R.; Fabrizio, E.; Garnero, G. The territorial and landscape impacts of photovoltaic systems: Definition of impacts and assessment of the glare risk. Renew. Sustain. Energy Rev. 2009, 13, 2441–2451. [Google Scholar] [CrossRef]
- Zhang, L.; Zhang, Y.; Yi, X.; Yang, Y.; Zhao, M.; Zhou, J. Seasonal variations of the impact of urban aerosol pollution on distributed solar photovoltaic generation of nine megacities in China. Urban Clim. 2020, 34, 100723. [Google Scholar] [CrossRef]
- Luo, Y.; Zhao, T.; Yang, Y.; Zong, L.; Kumar, K.R.; Wang, H.; Meng, K.; Zhang, L.; Lu, S.; Xin, Y. Seasonal changes in the recent decline of combined high PM2.5 and O3 pollution and associated chemical and meteorological drivers in the Beijing–Tianjin–Hebei region, China. Sci. Total Environ. 2022, 838, 156312. [Google Scholar] [CrossRef]
- Wolpert, D.H. Stacked generalization. Neural Netw. 1992, 5, 241–259. [Google Scholar] [CrossRef]
- Mohanasundaram, V.; Rangaswamy, B. Photovoltaic solar energy prediction using the seasonal-trend decomposition layer and ASOA optimized LSTM neural network model. Sci. Rep. 2025, 15, 4032. [Google Scholar] [CrossRef] [PubMed]
- Hamad, S.A.; Ghalib, M.A.; Munshi, A.; Alotaibi, M.; Ebied, M.A. Evaluating machine learning models comprehensively for predicting maximum power from photovoltaic systems. Sci. Rep. 2025, 15, 10750. [Google Scholar] [CrossRef]
File | Name | Description | Units |
---|---|---|---|
Station Data [0–9] | lmd_totalirrad | Global irradiance of LMD | W/m2 |
lmd_diffuseirrad | Diffuse irradiance of LMD | W/m2 | |
lmd_temperature | Temperature of LMD | °C | |
lmd_pressure | Atmospheric pressure of LMD | hPa | |
lmd_winddirection | Wind direction of LMD | degree | |
lmd_windspeed | Wind speed of LMD | m/s | |
Model Performance Metrics | MAE | Mean absolute error | – |
RMSE | Root mean square error | – | |
R2 | Coefficient of determination | – | |
MSE | Mean squared error | – | |
MAPE | Mean absolute percentage error | – |
Station | 0 | 1 | 2 | 3 | 4 | 5 | 6 | 7 | 8 | 9 |
---|---|---|---|---|---|---|---|---|---|---|
Power (MW/h) | 3.37 | 14.81 | 10.42 | 13.17 | 18.23 | 27.76 | 7.06 | 10.62 | 11.62 | 5.69 |
Model | MAE | RMSE | MAPE | R2 | MAE | RMSE | MAPE | R2 |
---|---|---|---|---|---|---|---|---|
PM2.5-Inclusive | PM2.5-Free | |||||||
SVR | 0.597 | 1.076 | 46.645 | 0.924 | 0.615 | 1.095 | 43.875 | 0.921 |
RF | 0.497 | 0.851 | 47.926 | 0.966 | 0.535 | 0.904 | 38.7 | 0.96 |
DT | 0.616 | 1.018 | 34.673 | 0.95 | 0.637 | 1.06 | 34.984 | 0.946 |
AdaBoost | 0.888 | 1.243 | 265.147 | 0.923 | 0.89 | 1.246 | 267.616 | 0.923 |
KNN | 0.63 | 1.056 | 66.174 | 0.942 | 0.655 | 1.084 | 75.6 | 0.939 |
BP | 1.039 | 1.407 | 175.156 | 0.861 | 0.854 | 1.25 | 177.532 | 0.884 |
Model | MAE | RMSE | MAPE | R2 | MAE | RMSE | MAPE | R2 |
---|---|---|---|---|---|---|---|---|
PM2.5-Inclusive | PM2.5-Free | |||||||
Comb 1 | 0.476 | 0.838 | 47.376 | 0.965 | 0.512 | 0.891 | 44.435 | 0.960 |
Comb 2 | 0.52 | 0.888 | 55.455 | 0.96 | 0.558 | 0.944 | 45.670 | 0.956 |
Comb 3 | 0.535 | 0.914 | 36.67 | 0.96 | 0.587 | 0.992 | 26.187 | 0.952 |
Comb 4 | 0.685 | 0.981 | 180.703 | 0.955 | 0.713 | 1.027 | 178.646 | 0.949 |
Comb 5 | 0.496 | 0.849 | 44.487 | 0.965 | 0.542 | 0.910 | 38.078 | 0.959 |
Comb 6 | 0.479 | 0.832 | 41.035 | 0.967 | 0.516 | 0.885 | 50.283 | 0.961 |
Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content. |
© 2025 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Hu, A.; Duan, Z.; Zhang, Y.; Huang, Z.; Ji, T.; Yin, X. Impact of PM2.5 Pollution on Solar Photovoltaic Power Generation in Hebei Province, China. Energies 2025, 18, 4195. https://doi.org/10.3390/en18154195
Hu A, Duan Z, Zhang Y, Huang Z, Ji T, Yin X. Impact of PM2.5 Pollution on Solar Photovoltaic Power Generation in Hebei Province, China. Energies. 2025; 18(15):4195. https://doi.org/10.3390/en18154195
Chicago/Turabian StyleHu, Ankun, Zexia Duan, Yichi Zhang, Zifan Huang, Tianbo Ji, and Xuanhua Yin. 2025. "Impact of PM2.5 Pollution on Solar Photovoltaic Power Generation in Hebei Province, China" Energies 18, no. 15: 4195. https://doi.org/10.3390/en18154195
APA StyleHu, A., Duan, Z., Zhang, Y., Huang, Z., Ji, T., & Yin, X. (2025). Impact of PM2.5 Pollution on Solar Photovoltaic Power Generation in Hebei Province, China. Energies, 18(15), 4195. https://doi.org/10.3390/en18154195