Productivity modelling of an inclined stepped solar still for seawater desalination using boosting algorithms based on experimental data

Basit Öğe Kaydı
dc.authoridAbujazar, mohammedShadi/0000-0002-5438-0112
dc.authoridAlshwaiyat, Rami/0000-0003-3913-6397
dc.authoridK. M. Abujayyab, Sohaib/0000-0002-6692-3567
dc.authoridkabeel, Abd elnaby/0000-0003-4273-8487
dc.authoridWazirali, Raniyah/0000-0002-3609-9351
dc.contributor.authorWazirali, Raniyah
dc.contributor.authorAbujazar, Mohammed Shadi S.
dc.contributor.authorAbujayyab, Sohaib K. M.
dc.contributor.authorAhmad, Rami
dc.contributor.authorFatihah, Suja
dc.contributor.authorKabeel, A. E.
dc.contributor.authorKaraagac, Sakine Ugurlu
dc.date.accessioned2024-09-29T16:09:37Z
dc.date.available2024-09-29T16:09:37Z
dc.date.issued2022
dc.departmentKarabük Üniversitesien_US
dc.description.abstractSolar energy has recently become a viable option for desalinating seawater, primarily in arid regions. However, increasing the productivity of solar still by integrating experimental base and modelling methods is still subject to prediction errors; therefore, the main objective of this research is to postulate and test boosting algorithms for predicting the efficiency and productivity of the system. Five boosting regressors were deployed and evaluated: categorical boosting, adaptive boosting, extreme gradient boosting, gradient boosting machine, and gradient boosting machine (LightGBM). The proposed regressors are implemented based on the system's actual recorded dataset (consisting of 720 observations). The dataset consists of input variables, which are the wind speed (V), cloud cover, humidity, ambient temperature (T), solar radiation (SR), (T-io), (T-w), (T-v), and (T-t). Also, the output variable is represented by the productivity of the system. The dataset was separated into training (70%) and testing (30%) sets. In order to decrease regressors errors, hyperparameter optimization was employed. GradientBoosting approach provided the best prediction, with 95% R-2 accuracy and 39.57 root mean square error (RMSE) error. The LightGBM technique achieved 94% R-2 accuracy and 40.07 RMSE error in the testing dataset. The results reveal that GradientBoosting outperforms the cascaded forward neural network in predicting system productivity (CFNN).en_US
dc.description.sponsorshipUniversiti Kebangsaan Malaysia [GUP-2016-020]en_US
dc.description.sponsorshipThe authors thank the numerous individuals and organizations that generously supported the study, particularly Universiti Kebangsaan Malaysia through its GUP-2016-020 grant.en_US
dc.identifier.doi10.5004/dwt.2022.28960
dc.identifier.endpage39en_US
dc.identifier.issn1944-3994
dc.identifier.issn1944-3986
dc.identifier.scopus2-s2.0-85145449608en_US
dc.identifier.scopusqualityQ3en_US
dc.identifier.startpage28en_US
dc.identifier.urihttps://doi.org/10.5004/dwt.2022.28960
dc.identifier.urihttps://hdl.handle.net/20.500.14619/7677
dc.identifier.volume276en_US
dc.identifier.wosWOS:000934038900003en_US
dc.identifier.wosqualityQ4en_US
dc.indekslendigikaynakWeb of Scienceen_US
dc.indekslendigikaynakScopusen_US
dc.language.isoenen_US
dc.publisherDesalination Publen_US
dc.relation.ispartofDesalination and Water Treatmenten_US
dc.relation.publicationcategoryMakale - Uluslararası Hakemli Dergi - Kurum Öğretim Elemanıen_US
dc.rightsinfo:eu-repo/semantics/closedAccessen_US
dc.subjectSolar desalinationen_US
dc.subjectMeteorological dataen_US
dc.subjectBoosting algorithmsen_US
dc.subjectModellingen_US
dc.subjectProductivity evaluationen_US
dc.titleProductivity modelling of an inclined stepped solar still for seawater desalination using boosting algorithms based on experimental dataen_US
dc.typeArticleen_US

Dosyalar

Koleksiyon

WoS İndeksli Yayınlar Koleksiyonu
Scopus İndeksli Yayınlar Koleksiyonu