The relationship between environmental factors and dust accumulation by machine learning
-
Komiljon Yakubov
,
Rustam Bazarbayev
Abstract
This study aims to explore the relationship between dust accumulation on a glass and various environmental factors including temperature, humidity, atmospheric pressure, and wind speed. The data was analyzed using Python, a popular language for data science and artificial intelligence, and regression algorithms from the scikit-learn library. The data was divided into training (80 %) and test (20 %) sets and different models were used, such as linear regression, decision tree, K-neighbor regression, random forest regression, and decision tree regression. The accuracy of the models was determined using R2 scores, where a score of 1.0 indicates a perfect fit and negative values suggest that the model is worse than predicting the mean value. The accuracy of the selected models was calculated as a percentage by multiplying the obtained R2 scores by 100. Graphs were used to visualise the data and determine the appropriate analysis model. The study found that the amount of dust is directly proportional to temperature and humidity. The accuracy levels of the linear models were suboptimal, leading to the use of nonlinear models like random forest regressor, decision tree regressor, and gradient boosting regressor, which showed improved performance.
Acknowledgements
This work is supported by the project No. PQ-307 “Production of computer-controlled equipment for the comprehensive study of the influence of various external factors on solar panels” funded by Urgench State University, Urgench, Uzbekistan.
-
Research ethics: Not applicable.
-
Author contributions: Komiljon Yakubov (Corresponding author) – Responsible for the entire content, approved submission. Rustam Bazarbayev – Data collection. Davron Qurbanov – Data visualization. Maksud Sharipov – Software development, machine learning. Jamshid Masharipov – Software development, machine learning. Smagu lKarazhanov – Manuscript preparation, coordination.
-
Competing interests: The authors state no conflict of interest.
-
Research funding: This work is supported by the project No. PQ-307 “Production of computer-controlled equipment for the comprehensive study of the influence of various external factors on solar panels” funded by Urgench State University, Urgench, Uzbekistan.
-
Data availability: The raw data can be obtained on request from the corresponding author.
The code for analyzing data can be found on GitHub.
GitHub link: https://github.com/Jamshidbek077/My_Projects/blob/master/Sun_Panels.ipynb
References
1. Jaegermann, W., Kaiser, B., Finger, F., Smirnov, V., Schäfer, R. Design Considerations of Efficient Photo-Electrosynthetic Cells and Its Realization Using Buried Junction Si Thin Film Multi Absorber Cells. Z. Phys. Chem. 2020, 234 (4), 549–604; https://doi.org/10.1515/zpch-2019-1584.Search in Google Scholar
2. Bastús, N. G., Gonzalez, E., Esteve, J., Piella, J., Patarroyo, J., Merkoçi, F., Puntes, V. Exploring New Synthetic Strategies for the Production of Advanced Complex Inorganic Nanocrystals. Z. Phys. Chem. 2015, 229 (1–2), 65–83; https://doi.org/10.1515/zpch-2014-0611.Search in Google Scholar
3. Adamu, A. A., Adamu, K. S., Mohammed, A., Sule, M. A., Ibrahim, U. S. Effect of Dust Accumulation on the Performances of Solar Panels in Static and Tracking Systems in Bauchi Metropolis of Nigeria. Int. J. Adv. Sci. Res. Eng. 2022, 8 (11), 16–32; https://doi.org/10.31695/IJASRE.2022.8.11.3.Search in Google Scholar
4. Sakarapunthip, N., Chenvidhya, D., Chuangchote, S., Kirtikara, K., Chenvidhya, T., Onreabroy, W. Effects of Dust Accumulation and Module Cleaning on Performance Ratio of Solar Rooftop System and Solar Power Plants. Jpn. J. Appl. Phys. 2017, 56 (8S2), 08ME02; https://doi.org/10.7567/JJAP.56.08ME02.Search in Google Scholar
5. Saidan, M., Albaali, A. G., Alasis, E., Kaldellis, J. K. Experimental Study on the Effect of Dust Deposition on Solar Photovoltaic Panels in Desert Environment. Renew. Energy 2016, 92, 499–505; https://doi.org/10.1016/j.renene.2016.02.031.Search in Google Scholar
6. Al Khuffash, K., Lamont, L. A., El Chaar, L. Analyzing the Effect of Desert Environment on the Performance of Photovoltaics. Appl. Sol. Energy 2014, 50 (4), 215–220; https://doi.org/10.3103/S0003701X14040070.Search in Google Scholar
7. Hussain, A., Batra, A., Pachauri, R. An Experimental Study on Effect of Dust on Power Loss in Solar Photovoltaic Module. Renew. Wind Water Sol. 2017, 4 (1); https://doi.org/10.1186/s40807-017-0043-y.Search in Google Scholar
8. Heinrich, M., Meunier, S., Samé, A., Quéval, L., Darga, A., Oukhellou, L., Multon, B. Detection of Cleaning Interventions on Photovoltaic Modules with Machine Learning. Appl. Energy, 2020, 263; https://doi.org/10.1016/j.apenergy.2020.114642.Search in Google Scholar
9. Yazdani, H., Yaghoubi, M. Dust Deposition Effect on Photovoltaic Modules Performance and Optimization of Cleaning Period: A Combined Experimental–Numerical Study. Sustain. Energy Technol. Assess. 2022; 51, https://doi.org/10.1016/j.seta.2021.101946.Search in Google Scholar
10. Bazarbayev, R. B., Yakubov, K., Kurbanov, D., Allaniyazov, A., Balakumar, S., Kamalov, A., Janabergenova, G., Wei, Q., Qian, H., Polvonnazirov, I., Karazhanov, S. Performance of Crystalline Si Solar Cells and Module on Temperature and Illumination Intensity. Mater. Today Proc. 2022, 64, 1661–1665; https://doi.org/10.1016/j.matpr.2022.04.930.Search in Google Scholar
11. Salamah, T., Ramahi, A., Alamara, K., Juaidi, A., Abdallah, R., Abdelkareem, M. A., Amer, E. C., Olabi, A. G. Effect of Dust and Methods of Cleaning on the Performance of Solar PV Module for Different Climate Regions: Comprehensive Review. Sci. Total Environ. 2022, 827, 154050; https://doi.org/10.1016/j.scitotenv.2022.154050.Search in Google Scholar PubMed
12. Aryal, Y. Evaluation of Machine-Learning Models for Predicting Aeolian Dust: A Case Study over the Southwestern USA. Climate 2022, 10 (6), 78; https://doi.org/10.3390/cli10060078.Search in Google Scholar
13. Said, S. A. M., Hassan, G., Walwil, H. M., Al-Aqeeli, N. The Effect of Environmental Factors and Dust Accumulation on Photovoltaic Modules and Dust-Accumulation Mitigation Strategies. Renew. Sust. Energ. Rev. 2018, 82, 743–760; https://doi.org/10.1016/j.rser.2017.09.042.Search in Google Scholar
14. Gholami, H., Mohamadifar, A., Sorooshian, A., Jansen, J. D. Machine-Learning Algorithms for Predicting Land Susceptibility to Dust Emissions: The Case of the Jazmurian Basin, Iran. Atmos. Pollut. Res. 2020, 11 (8), 1303–1315; https://doi.org/10.1016/j.apr.2020.05.009.Search in Google Scholar
15. Ebrahimi-Khusfi, Z., Taghizadeh-Mehrjardi, R., Mirakbari, M. Evaluation of Machine Learning Models for Predicting the Temporal Variations of Dust Storm Index in Arid Regions of Iran. Atmos. Pollut. Res. 2021, 12 (1), 134–147; https://doi.org/10.1016/j.apr.2020.08.029.Search in Google Scholar
16. Tan, C., Chen, Q., Qi, D., Xu, L., Wang, J. A Case Analysis of Dust Weather and Prediction of PM10 Concentration Based on Machine Learning at the Tibetan Plateau. Atmosphere 2022, 13 (6), 897; https://doi.org/10.3390/atmos13060897.Search in Google Scholar
17. Gupta, H. V., Kling, H., Yilmaz, K. K., Martinez, G. F. Decomposition of the Mean Squared Error and NSE Performance Criteria: Implications for Improving Hydrological Modelling. J. Hydrol. 2009, 377, 1–2; https://doi.org/10.1016/j.jhydrol.2009.08.003.Search in Google Scholar
18. Rana, M., Rahman, A. Multiple Steps Ahead Solar Photovoltaic Power Forecasting Based on Univariate Machine Learning Models and Data Re-sampling. Sustain. Energy, Grids Netw. 2020, 21, 100286; https://doi.org/10.1016/j.segan.2019.100286.Search in Google Scholar
19. Fan, J., Wu, L., Zhang, F., Cai, H., Ma, X., Bai, H. Evaluation and Development of Empirical Models for Estimating Daily and Monthly Mean Daily Diffuse Horizontal Solar Radiation for Different Climatic Regions of China. Renew. Sust. Energ. Rev. 2019, 105, 168–186; https://doi.org/10.1016/j.rser.2019.01.040.Search in Google Scholar
© 2024 Walter de Gruyter GmbH, Berlin/Boston
Articles in the same Issue
- Frontmatter
- Contributions to “Materials for Solar Water Splitting”
- Unveiling the role of rare earth dopant in metal molybdate nanocomposites via facile microwave-combustion strategy and their effect on antibacterial activity
- Effect of lanthanum (La) substitution on the magnetic and electrical properties of nickel ferrites: an investigation of its doping concentrations
- The relationship between environmental factors and dust accumulation by machine learning
- Facile formation of STO/gC3N4 hybrid composite to effectively degrade the dye and antibiotic under white light
- Investigation of the composition and morphology of raw materials from the Aral Sea region
- Chemical state and atomic structure in stoichiovariants photochromic oxidized yttrium hydride thin films
- Single crystal of barium bis para-nitrophenolate para-nitrophenol tetrahydrate for NLO applications: crystal growth and DFT analysis
- Characterization of single-crystal phenothiazine synthesized using the vertical Bridgman method
- Amidoxime functionalized mesoporous silica nanoparticles for pH-responsive delivery of anticancer drug
- Exploring optical and electrochemical studies on thulium selenite (TmSeO3)
Articles in the same Issue
- Frontmatter
- Contributions to “Materials for Solar Water Splitting”
- Unveiling the role of rare earth dopant in metal molybdate nanocomposites via facile microwave-combustion strategy and their effect on antibacterial activity
- Effect of lanthanum (La) substitution on the magnetic and electrical properties of nickel ferrites: an investigation of its doping concentrations
- The relationship between environmental factors and dust accumulation by machine learning
- Facile formation of STO/gC3N4 hybrid composite to effectively degrade the dye and antibiotic under white light
- Investigation of the composition and morphology of raw materials from the Aral Sea region
- Chemical state and atomic structure in stoichiovariants photochromic oxidized yttrium hydride thin films
- Single crystal of barium bis para-nitrophenolate para-nitrophenol tetrahydrate for NLO applications: crystal growth and DFT analysis
- Characterization of single-crystal phenothiazine synthesized using the vertical Bridgman method
- Amidoxime functionalized mesoporous silica nanoparticles for pH-responsive delivery of anticancer drug
- Exploring optical and electrochemical studies on thulium selenite (TmSeO3)
