Reservoir temperature prediction based on characterization of water chemistry data—case study of western Anatolia, Turkey

Reservoir temperature estimation is crucial for geothermal studies, but traditional methods are complex and uncertain. To address this, we collected 83 sets of water chemistry and reservoir temperature data and applied four machine learning algorithms. These models considered various input factors a...

Full description

Saved in:
Bibliographic Details
Published in:Scientific reports Vol. 14; no. 1; pp. 10339 - 15
Main Authors: Shi, Haoxin, Zhang, Yanjun, Yu, Ziwang, Yang, Yunxing
Format: Journal Article
Language:English
Published: London Nature Publishing Group UK 06.05.2024
Nature Publishing Group
Nature Portfolio
Subjects:
639/4077/909/4083
704/172
704/2151
Accuracy
Algorithms
Bayesian analysis
Boron
Carbon
Case studies
Chemistry
Geothermal power
Geothermal resources
Geothermal studies
Geothermometer
Humanities and Social Sciences
Hydrogeochemistry
Learning algorithms
Machine learning
Mathematical models
Methods
multidisciplinary
Neural networks
Predictions
Regression analysis
Reservoir temperature
Reservoirs
Science
Science (multidisciplinary)
Temperature
Water chemistry
Turkey
Hydrogeochemistry
Reservoir temperature
Geothermometer
Machine learning
ISSN:2045-2322, 2045-2322
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Reservoir temperature estimation is crucial for geothermal studies, but traditional methods are complex and uncertain. To address this, we collected 83 sets of water chemistry and reservoir temperature data and applied four machine learning algorithms. These models considered various input factors and underwent data preprocessing steps like null value imputation, normalization, and Pearson coefficient calculation. Cross-validation addressed data volume issues, and performance metrics were used for model evaluation. The results revealed that our machine learning models outperformed traditional fluid geothermometers. All machine learning models surpassed traditional methods. The XGBoost model, based on the F-3 combination, demonstrated the best prediction accuracy with an R 2 of 0.9732, while the Bayesian ridge regression model using the F-4 combination had the lowest performance with an R 2 of 0.8302. This study highlights the potential of machine learning for accurate reservoir temperature prediction, offering geothermal professionals a reliable tool for model selection and advancing our understanding of geothermal resources.
Bibliography:ObjectType-Case Study-2
SourceType-Scholarly Journals-1
content type line 14
ObjectType-Feature-4
ObjectType-Report-1
ObjectType-Article-3
ObjectType-Article-1
ObjectType-Feature-2
content type line 23
ISSN:2045-2322
2045-2322
DOI:10.1038/s41598-024-59409-5