Transforming Wind Data into Insights: A Comparative Study of Stochastic and Machine Learning Models in Wind Speed Forecasting

dc.authorid0000-0001-7547-847X
dc.authorid0000-0003-2906-0771
dc.authorid0000-0002-1870-3535
dc.contributor.authorTuğrul, Türker
dc.contributor.authorOruç, Sertaç
dc.contributor.authorHınıs, Mehmet Ali
dc.date.accessioned2025-07-11T07:06:57Z
dc.date.available2025-07-11T07:06:57Z
dc.date.issued2025
dc.departmentMühendislik Fakültesi
dc.description.abstractWind speed is a critical parameter for both energy applications and climate studies, particularly under changing climatic conditions and has attracted increasing research interest from the scientific comunity. This parameter is of interest to both researchers interested in climate change and researchers working on issues related to energy production. Based on this, in this study, prospective analyses were made with various machine learning algorithms, the long-short term memory (LSTM), the artificial neural network (ANN), and the support vector machine (SVM) algorithms, and one of the stochastic methods, the seasonal autoregressive integrated moving average (SARIMA), using the monthly wind data obtained from Bodo. In these analyses, five different models were created with the assistance of cross-correlation. The models obtained from the analyses were improved with the wavelet transformation (WT), and the results obtained were evaluated for the correlation coefficient (R), the Nash–Sutcliffe model efficiency (NSE), the Kling–Gupta efficiency (KGE), the performance index (PI), the root mean standard deviation ratio (RSR), and the root mean square error (RMSE). The results obtained from this study unveiled that LSTM emerged as the best performance metric in the M04 model among other models (R = 0.9532, NSE = 0.8938, KGE = 0.9463, PI = 0.0361, RSR = 0.0870, and RMSE = 0.3248). Another notable finding obtained from this study was that the best performance values in analyses without WT were obtained with SARIMA. The results of this study provide information on forward-looking modeling for institutions and decision-makers related to energy and climate change.
dc.identifier.doi10.3390/app15073543
dc.identifier.issue7
dc.identifier.scopus105002277128
dc.identifier.urihttps://dx.doi.org/10.3390/app15073543
dc.identifier.uri20763417
dc.identifier.urihttps://hdl.handle.net/20.500.12451/13255
dc.identifier.volume15
dc.identifier.wosWOS:001463643300001
dc.identifier.wosqualityQ2
dc.indekslendigikaynakScopus
dc.indekslendigikaynakWeb of Science
dc.institutionauthorHınıs, Mehmet Ali
dc.institutionauthorid0000-0002-1870-3535
dc.language.isoen
dc.publisherMultidisciplinary Digital Publishing Institute (MDPI)
dc.relation.ispartofApplied Sciences (Switzerland)
dc.relation.publicationcategoryMakale - Uluslararası Hakemli Dergi - Kurum Öğretim Elemanı
dc.rightsinfo:eu-repo/semantics/openAccess
dc.subjectANN
dc.subjectLSTM
dc.subjectMachine Learning
dc.subjectSVM
dc.subjectWavelet Transform
dc.subjectWind Speed
dc.titleTransforming Wind Data into Insights: A Comparative Study of Stochastic and Machine Learning Models in Wind Speed Forecasting
dc.typeArticle

Dosyalar

Orijinal paket
Listeleniyor 1 - 1 / 1
Yükleniyor...
Küçük Resim
İsim:
turker-tugrul-2025.pdf
Boyut:
5.22 MB
Biçim:
Adobe Portable Document Format
Lisans paketi
Listeleniyor 1 - 1 / 1
[ X ]
İsim:
license.txt
Boyut:
1.17 KB
Biçim:
Item-specific license agreed upon to submission
Açıklama: