Assessment of regional-scale geothermal production based on a hybrid deep learning model: A case study of the southern Songliao Basin, China

Weifei Yang, Changlai Xiao and Xiujuan Liang

Renewable Energy, 2024, vol. 223, issue C

Abstract: Geothermal resources represent clean and reliable renewable energy, and as such have attracted global attention. Abundant hydrothermal geothermal resources exist in sedimentary basins globally, which could be exploited. However, regional-scale rapid and accurate prediction of geothermal production remains a challenge. This study constructed a novel hybrid deep learning model to identify the nonlinear mapping relationship between reservoir parameters and production potential. The hybrid model was used to extend the small-scale simulations of the hydrothermal coupling to a regional scale to achieve the rapid and accurate assessment of geothermal production potential. Furthermore, using the geothermal reservoir of the third member of the Quantou Formation (K1q3) in the southern Songliao Basin as an example, prediction of geothermal production potential based on the hybrid model was expounded and the accuracy of prediction was assessed. The newly proposed Deep Belief Network + Long and Short Memory Network (DBN + LSTM) hybrid model takes the entire time series as the training and prediction target without the prior given initial values (e.g., initial flow rate) and has high prediction accuracy. The absolute errors of the predicted flow rate, outlet temperature, heat generation power, and thermal breakthrough distance were less than 15 m3/d, 2.2 °C, 0.03 MW, and 20 m, respectively. This study proposes a novel approach for the rapid and accurate assessment of regional-scale geothermal production potential.

Keywords: Deep belief network; Long and short memory network; Hybrid model; Geothermal production potential; Songliao Basin (search for similar items in EconPapers)
Date: 2024
References: Add references at CitEc
Citations: View citations in EconPapers (1)

Downloads: (external link)
http://www.sciencedirect.com/science/article/pii/S0960148124001277
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:renene:v:223:y:2024:i:c:s0960148124001277

DOI: 10.1016/j.renene.2024.120062

Access Statistics for this article

Renewable Energy is currently edited by Soteris A. Kalogirou and Paul Christodoulides

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