Please use this identifier to cite or link to this item:
https://hdl.handle.net/20.500.13091/5404
Full metadata record
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Unal, R.E. | - |
dc.contributor.author | Guzel, M.H. | - |
dc.contributor.author | Sen, M.A. | - |
dc.contributor.author | Aksoy, M.H. | - |
dc.date.accessioned | 2024-04-20T13:05:49Z | - |
dc.date.available | 2024-04-20T13:05:49Z | - |
dc.date.issued | 2024 | - |
dc.identifier.issn | 1735-1472 | - |
dc.identifier.uri | https://doi.org/10.1007/s13762-024-05571-2 | - |
dc.identifier.uri | https://hdl.handle.net/20.500.13091/5404 | - |
dc.description.abstract | This study proposed a model for estimating monthly solar radiation values using the adaptive network-based fuzzy inference systems (ANFIS-SR). The ANFIS-SR model is obtained by training the meteorological measurement data from the Adana province from 2017 to 2021. The monthly average sunshine duration and ambient temperature are inputs for the ANFIS-SR. The investigation evaluates the impact of different membership functions and data selection methodologies for training and testing on the ANFIS-SR outcomes. Four types of membership functions, Triangular (Trim), Gaussian, Trapezoidal, and Generalized Bell-Shaped (Gbell), are considered to study the input's influence. Additionally, two data selection cases are examined: one involving a serial date (S cases) arrangement and the other with a random (R cases) order. According to the errors, Gbell ensures higher estimating performance with the lowest error than other membership functions in training and testing data in S cases. In the case of R, Gbell is more successful in the training, while Trim can provide better estimates on the testing data. The test results show that the mean absolute percentage error and regression values are 4.364% and 0.984 for S cases and 4.265% and 0.981 for R cases, respectively. According to the obtained results, the Gbell membership function provides more solar radiation prediction performance than the others for the examined location. It also shows that random data selection outperforms serial data selection. The results prove that the proposed model ANFIS-SR can effectively model solar radiation estimation within an acceptable error range, thus offering substantial application potential in this field. © The Author(s) under exclusive licence to Iranian Society of Environmentalists (IRSEN) and Science and Research Branch, Islamic Azad University 2024. | en_US |
dc.language.iso | en | en_US |
dc.publisher | Springer Nature | en_US |
dc.relation.ispartof | International Journal of Environmental Science and Technology | en_US |
dc.rights | info:eu-repo/semantics/closedAccess | en_US |
dc.subject | Ambient temperature | en_US |
dc.subject | ANFIS | en_US |
dc.subject | Estimation | en_US |
dc.subject | Solar radiation | en_US |
dc.subject | Sunshine duration | en_US |
dc.subject | Data reduction | en_US |
dc.subject | Errors | en_US |
dc.subject | Fuzzy inference | en_US |
dc.subject | Fuzzy neural networks | en_US |
dc.subject | Solar radiation | en_US |
dc.subject | Temperature | en_US |
dc.subject | ANFIS | en_US |
dc.subject | ANFIS model | en_US |
dc.subject | Data Selection | en_US |
dc.subject | Memberships function | en_US |
dc.subject | Model evaluation | en_US |
dc.subject | Solar radiation estimation | en_US |
dc.subject | Sunshine duration | en_US |
dc.subject | Sunshine-duration | en_US |
dc.subject | Testing data | en_US |
dc.subject | Training and testing | en_US |
dc.subject | Membership functions | en_US |
dc.title | Solar radiation estimation using ANFIS model: evaluation of membership function types and data selection | en_US |
dc.type | Article | en_US |
dc.identifier.doi | 10.1007/s13762-024-05571-2 | - |
dc.identifier.scopus | 2-s2.0-85189447896 | en_US |
dc.department | KTÜN | en_US |
dc.identifier.wos | WOS:001197110100006 | en_US |
dc.institutionauthor | … | - |
dc.relation.publicationcategory | Makale - Uluslararası Hakemli Dergi - Kurum Öğretim Elemanı | en_US |
dc.authorscopusid | 57222162653 | - |
dc.authorscopusid | 57222168588 | - |
dc.authorscopusid | 58970493700 | - |
dc.authorscopusid | 55823803400 | - |
item.openairecristype | http://purl.org/coar/resource_type/c_18cf | - |
item.languageiso639-1 | en | - |
item.openairetype | Article | - |
item.fulltext | No Fulltext | - |
item.grantfulltext | none | - |
item.cerifentitytype | Publications | - |
crisitem.author.dept | 07. 16. Department of Machinery and Metal Technologies | - |
crisitem.author.dept | 02.10. Department of Mechanical Engineering | - |
Appears in Collections: | Scopus İndeksli Yayınlar Koleksiyonu / Scopus Indexed Publications Collections WoS İndeksli Yayınlar Koleksiyonu / WoS Indexed Publications Collections |
CORE Recommender
Items in GCRIS Repository are protected by copyright, with all rights reserved, unless otherwise indicated.