A comparative study on ensemble soft-computing methods for geothermal power production potential forecasting

Raif Kenanoğlu, İlker Mert, Ceyhun Baydar, Özkan Köse and Hüseyin Yağlı

Energy, 2024, vol. 303, issue C

Abstract: Many developed countries are increasingly interested in renewable energy sources (RESs) as a result of environmental changes and the depletion of fossil fuels in recent years. Since geothermal energy can be used as both a source of electricity and heat, it occupies an important spot among renewable energy sources. In this study, soft-computing ensemble models (SCEMs) based on supervised deep neural network (SDNN) models supported by the forward stepwise regression (FSR) method are used in estimating the power generation from geothermal resources. Outputs of the FSR process led SDNN phase. Adaptive Moment Estimation (ADAM) and Nesterov-accelerated Adaptive Moment Estimation (NADAM) methods were used to optimize SDNN models. For the daily power generation, the best performance has been shown by the model of SDNN optimized using ADAM optimizer with a coefficient of determination (R2) of 0.9807 and root mean square error (RMSE) of 0.0466, respectively.

Keywords: Geothermal energy; Supervised deep neural network; Adaptive moment estimation; Nesterov-accelerated adaptive moment estimation (search for similar items in EconPapers)
Date: 2024
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
http://www.sciencedirect.com/science/article/pii/S0360544224016748
Full text for ScienceDirect subscribers only

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:eee:energy:v:303:y:2024:i:c:s0360544224016748

DOI: 10.1016/j.energy.2024.131901

Access Statistics for this article

Energy is currently edited by Henrik Lund and Mark J. Kaiser

More articles in Energy from Elsevier
Bibliographic data for series maintained by Catherine Liu ().