Joana Madeira Krieger , Cicero Manoel dos Santos , Gustavo Bastos Lyra , José Leonaldo de Souza , Ricardo Araujo Ferreira Junior , Anthony Carlos Silva Porfirio , Guilherme Bastos Lyra , Marcel Carvalho Abreu
{"title":"用于估算巴西东北部阿拉戈斯州每小时漫射太阳辐射的经验模型和人工智能","authors":"Joana Madeira Krieger , Cicero Manoel dos Santos , Gustavo Bastos Lyra , José Leonaldo de Souza , Ricardo Araujo Ferreira Junior , Anthony Carlos Silva Porfirio , Guilherme Bastos Lyra , Marcel Carvalho Abreu","doi":"10.1016/j.jastp.2024.106269","DOIUrl":null,"url":null,"abstract":"<div><p>Diffuse solar irradiation (H<sub>D</sub>) data are essential for the design and management of photovoltaic solar systems, biosphere-atmosphere modeling, and other applications. However, H<sub>D</sub> observations are scarce in several locations, especially in tropical regions. Employing hourly diffuse solar irradiation (<span><math><msubsup><mi>H</mi><mi>D</mi><mi>h</mi></msubsup></math></span>) and global solar irradiation (<span><math><msubsup><mi>H</mi><mi>G</mi><mi>h</mi></msubsup></math></span>) data collected between 2002─2003 and 2007─2008 in Alagoas State, Northeast Brazil, this study assesses various modeling techniques. Empirical models, including third-degree polynomial, logistic, sigmoidal, and rational functions, were compared with AI methods such as artificial neural networks (ANN), support vector machine (SVM), and adaptive neuro-fuzzy inference system (ANFIS). Additionally, it explores how solarimetric and meteorological variables impact the performance of these models. The empirical models showed similar performance in estimating <span><math><mspace></mspace><msubsup><mi>K</mi><mi>D</mi><mi>h</mi></msubsup><mspace></mspace><mo>(</mo><mo>=</mo><mspace></mspace><msubsup><mi>H</mi><mi>D</mi><mi>h</mi></msubsup><mspace></mspace><mo>/</mo><mspace></mspace><msubsup><mi>H</mi><mi>G</mi><mi>h</mi></msubsup><mo>)</mo><mspace></mspace><mspace></mspace></math></span> (r<sup>2</sup> > 0.726, modified Willmott – d<sub>m</sub> > 0.704, and RMSD < 0.103), with the third-degree polynomial model standing out. The empirical models had difficulty estimating <span><math><mrow><msubsup><mi>K</mi><mi>D</mi><mi>h</mi></msubsup></mrow></math></span> for hourly atmospheric transmittance <span><math><mo>(</mo><msubsup><mi>K</mi><mi>T</mi><mi>h</mi></msubsup><mo>)</mo></math></span> > 0.80, which indicated that they are not able to adequately simulate clear sky conditions, mostly due to surface reflections and clouds at the end of the day. ANN (r<sup>2</sup> > 0.718, d<sub>m</sub> > 0.702, and RMSD < 0.105) showed better precision and accuracy of estimates for a greater number of schemes in relation to SVM and ANFIS (r<sup>2</sup> > 0.704, d<sub>m</sub> > 0.699, RMSD < 0.108) and to empirical models. AI methods were able to represent the complexity of these conditions, with overall performance in estimating <span><math><mrow><msubsup><mi>K</mi><mi>D</mi><mi>h</mi></msubsup></mrow></math></span> superior or equivalent to empirical models. This study underscores the significance of exploring diverse methods for H<sub>D</sub> estimation, demonstrating promising potential for accurate and reliable estimation of hourly diffuse solar irradiation.</p></div>","PeriodicalId":15096,"journal":{"name":"Journal of Atmospheric and Solar-Terrestrial Physics","volume":"261 ","pages":"Article 106269"},"PeriodicalIF":1.8000,"publicationDate":"2024-06-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Empirical models and artificial intelligence for estimating hourly diffuse solar radiation in the state of Alagoas, Northeastern Brazil\",\"authors\":\"Joana Madeira Krieger , Cicero Manoel dos Santos , Gustavo Bastos Lyra , José Leonaldo de Souza , Ricardo Araujo Ferreira Junior , Anthony Carlos Silva Porfirio , Guilherme Bastos Lyra , Marcel Carvalho Abreu\",\"doi\":\"10.1016/j.jastp.2024.106269\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<div><p>Diffuse solar irradiation (H<sub>D</sub>) data are essential for the design and management of photovoltaic solar systems, biosphere-atmosphere modeling, and other applications. However, H<sub>D</sub> observations are scarce in several locations, especially in tropical regions. Employing hourly diffuse solar irradiation (<span><math><msubsup><mi>H</mi><mi>D</mi><mi>h</mi></msubsup></math></span>) and global solar irradiation (<span><math><msubsup><mi>H</mi><mi>G</mi><mi>h</mi></msubsup></math></span>) data collected between 2002─2003 and 2007─2008 in Alagoas State, Northeast Brazil, this study assesses various modeling techniques. Empirical models, including third-degree polynomial, logistic, sigmoidal, and rational functions, were compared with AI methods such as artificial neural networks (ANN), support vector machine (SVM), and adaptive neuro-fuzzy inference system (ANFIS). Additionally, it explores how solarimetric and meteorological variables impact the performance of these models. The empirical models showed similar performance in estimating <span><math><mspace></mspace><msubsup><mi>K</mi><mi>D</mi><mi>h</mi></msubsup><mspace></mspace><mo>(</mo><mo>=</mo><mspace></mspace><msubsup><mi>H</mi><mi>D</mi><mi>h</mi></msubsup><mspace></mspace><mo>/</mo><mspace></mspace><msubsup><mi>H</mi><mi>G</mi><mi>h</mi></msubsup><mo>)</mo><mspace></mspace><mspace></mspace></math></span> (r<sup>2</sup> > 0.726, modified Willmott – d<sub>m</sub> > 0.704, and RMSD < 0.103), with the third-degree polynomial model standing out. The empirical models had difficulty estimating <span><math><mrow><msubsup><mi>K</mi><mi>D</mi><mi>h</mi></msubsup></mrow></math></span> for hourly atmospheric transmittance <span><math><mo>(</mo><msubsup><mi>K</mi><mi>T</mi><mi>h</mi></msubsup><mo>)</mo></math></span> > 0.80, which indicated that they are not able to adequately simulate clear sky conditions, mostly due to surface reflections and clouds at the end of the day. ANN (r<sup>2</sup> > 0.718, d<sub>m</sub> > 0.702, and RMSD < 0.105) showed better precision and accuracy of estimates for a greater number of schemes in relation to SVM and ANFIS (r<sup>2</sup> > 0.704, d<sub>m</sub> > 0.699, RMSD < 0.108) and to empirical models. AI methods were able to represent the complexity of these conditions, with overall performance in estimating <span><math><mrow><msubsup><mi>K</mi><mi>D</mi><mi>h</mi></msubsup></mrow></math></span> superior or equivalent to empirical models. This study underscores the significance of exploring diverse methods for H<sub>D</sub> estimation, demonstrating promising potential for accurate and reliable estimation of hourly diffuse solar irradiation.</p></div>\",\"PeriodicalId\":15096,\"journal\":{\"name\":\"Journal of Atmospheric and Solar-Terrestrial Physics\",\"volume\":\"261 \",\"pages\":\"Article 106269\"},\"PeriodicalIF\":1.8000,\"publicationDate\":\"2024-06-13\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Journal of Atmospheric and Solar-Terrestrial Physics\",\"FirstCategoryId\":\"89\",\"ListUrlMain\":\"https://www.sciencedirect.com/science/article/pii/S136468262400097X\",\"RegionNum\":4,\"RegionCategory\":\"地球科学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q3\",\"JCRName\":\"GEOCHEMISTRY & GEOPHYSICS\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Atmospheric and Solar-Terrestrial Physics","FirstCategoryId":"89","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S136468262400097X","RegionNum":4,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"GEOCHEMISTRY & GEOPHYSICS","Score":null,"Total":0}
Empirical models and artificial intelligence for estimating hourly diffuse solar radiation in the state of Alagoas, Northeastern Brazil
Diffuse solar irradiation (HD) data are essential for the design and management of photovoltaic solar systems, biosphere-atmosphere modeling, and other applications. However, HD observations are scarce in several locations, especially in tropical regions. Employing hourly diffuse solar irradiation () and global solar irradiation () data collected between 2002─2003 and 2007─2008 in Alagoas State, Northeast Brazil, this study assesses various modeling techniques. Empirical models, including third-degree polynomial, logistic, sigmoidal, and rational functions, were compared with AI methods such as artificial neural networks (ANN), support vector machine (SVM), and adaptive neuro-fuzzy inference system (ANFIS). Additionally, it explores how solarimetric and meteorological variables impact the performance of these models. The empirical models showed similar performance in estimating (r2 > 0.726, modified Willmott – dm > 0.704, and RMSD < 0.103), with the third-degree polynomial model standing out. The empirical models had difficulty estimating for hourly atmospheric transmittance > 0.80, which indicated that they are not able to adequately simulate clear sky conditions, mostly due to surface reflections and clouds at the end of the day. ANN (r2 > 0.718, dm > 0.702, and RMSD < 0.105) showed better precision and accuracy of estimates for a greater number of schemes in relation to SVM and ANFIS (r2 > 0.704, dm > 0.699, RMSD < 0.108) and to empirical models. AI methods were able to represent the complexity of these conditions, with overall performance in estimating superior or equivalent to empirical models. This study underscores the significance of exploring diverse methods for HD estimation, demonstrating promising potential for accurate and reliable estimation of hourly diffuse solar irradiation.
期刊介绍:
The Journal of Atmospheric and Solar-Terrestrial Physics (JASTP) is an international journal concerned with the inter-disciplinary science of the Earth''s atmospheric and space environment, especially the highly varied and highly variable physical phenomena that occur in this natural laboratory and the processes that couple them.
The journal covers the physical processes operating in the troposphere, stratosphere, mesosphere, thermosphere, ionosphere, magnetosphere, the Sun, interplanetary medium, and heliosphere. Phenomena occurring in other "spheres", solar influences on climate, and supporting laboratory measurements are also considered. The journal deals especially with the coupling between the different regions.
Solar flares, coronal mass ejections, and other energetic events on the Sun create interesting and important perturbations in the near-Earth space environment. The physics of such "space weather" is central to the Journal of Atmospheric and Solar-Terrestrial Physics and the journal welcomes papers that lead in the direction of a predictive understanding of the coupled system. Regarding the upper atmosphere, the subjects of aeronomy, geomagnetism and geoelectricity, auroral phenomena, radio wave propagation, and plasma instabilities, are examples within the broad field of solar-terrestrial physics which emphasise the energy exchange between the solar wind, the magnetospheric and ionospheric plasmas, and the neutral gas. In the lower atmosphere, topics covered range from mesoscale to global scale dynamics, to atmospheric electricity, lightning and its effects, and to anthropogenic changes.