Machine Learning-Assisted High-Temperature Reservoir Thermal Energy Storage Optimization: Numerical Modeling and Machine Learning Input and Output Files
This data set includes the numerical modeling input files and output files used to synthesize data, and the reduced-order machine learning models trained from the synthesized data for reservoir thermal energy storage site identification.
In this study, a machine-learning-assisted computational framework is presented to identify High-Temperature Reservoir Thermal Energy Storage (HT-RTES) site with optimal performance metrics by combining physics-based simulation with stochastic hydrogeologic formation and thermal energy storage operation parameters, artificial neural network regression of the simulation data, and genetic algorithm-enabled multi-objective optimization. A doublet well configuration with a layered (aquitard-aquifer-aquitard) generic reservoir is simulated for cases of continuous operation and seasonal-cycle operation scenarios. Neural network-based surrogate models are developed for the two scenarios and applied to generate the Pareto fronts of the HT-RTES performance for four potential HT-RTES sites. The developed Pareto optimal solutions indicate the performance of HT-RTES is operation-scenario (i.e., fluid cycle) and reservoir-site dependent, and the performance metrics have competing effects for a given site and a given fluid cycle. The developed neural network models can be applied to identify suitable sites for HT-RTES, and the proposed framework sheds light on the design of resilient HT-RTES systems.
All the simulations and the neural network model were done by Idaho National Laboratory. A detailed description of the work was reported in publication linked below.
Citation Formats
TY - DATA
AB - This data set includes the numerical modeling input files and output files used to synthesize data, and the reduced-order machine learning models trained from the synthesized data for reservoir thermal energy storage site identification.
In this study, a machine-learning-assisted computational framework is presented to identify High-Temperature Reservoir Thermal Energy Storage (HT-RTES) site with optimal performance metrics by combining physics-based simulation with stochastic hydrogeologic formation and thermal energy storage operation parameters, artificial neural network regression of the simulation data, and genetic algorithm-enabled multi-objective optimization. A doublet well configuration with a layered (aquitard-aquifer-aquitard) generic reservoir is simulated for cases of continuous operation and seasonal-cycle operation scenarios. Neural network-based surrogate models are developed for the two scenarios and applied to generate the Pareto fronts of the HT-RTES performance for four potential HT-RTES sites. The developed Pareto optimal solutions indicate the performance of HT-RTES is operation-scenario (i.e., fluid cycle) and reservoir-site dependent, and the performance metrics have competing effects for a given site and a given fluid cycle. The developed neural network models can be applied to identify suitable sites for HT-RTES, and the proposed framework sheds light on the design of resilient HT-RTES systems.
All the simulations and the neural network model were done by Idaho National Laboratory. A detailed description of the work was reported in publication linked below.
AU - Jin, Wencheng
A2 - Atkinson, Trevor A.
A3 - Doughty, Christine
A4 - Neupane, Ghanashyam
A5 - Spycher, Nicolas
A6 - McLing, Travis L.
A7 - Dobson, Patrick F.
A8 - Smith, Robert
A9 - Podgorney, Robert
DB - Geothermal Data Repository
DP - Open EI | National Renewable Energy Laboratory
DO - 10.15121/1891881
KW - Reservoir Thermal Energy Storage
KW - Stochastic Simulation
KW - GeoTES
KW - Machine Learning
KW - Modeling
KW - TES
KW - HT-RTES
KW - characterization
KW - numerical model
KW - stochastic
KW - hydrogeologic formation
KW - simulated data
KW - simulation data
KW - High-Temperature
KW - Thermal Energy Storage
KW - Optimization
KW - artificial neural network regression
KW - ANN
KW - neural network
KW - operation scenarios
KW - seasonal-cycle
KW - Pareto fronts
KW - seasonal operation
KW - continuous operation
KW - Falcon
KW - MOOSE
LA - English
DA - 2022/04/15
PY - 2022
PB - Idaho National Laboratory
T1 - Machine Learning-Assisted High-Temperature Reservoir Thermal Energy Storage Optimization: Numerical Modeling and Machine Learning Input and Output Files
UR - https://doi.org/10.15121/1891881
ER -
Jin, Wencheng, et al. Machine Learning-Assisted High-Temperature Reservoir Thermal Energy Storage Optimization: Numerical Modeling and Machine Learning Input and Output Files. Idaho National Laboratory, 15 April, 2022, Geothermal Data Repository. https://doi.org/10.15121/1891881.
Jin, W., Atkinson, T., Doughty, C., Neupane, G., Spycher, N., McLing, T., Dobson, P., Smith, R., & Podgorney, R. (2022). Machine Learning-Assisted High-Temperature Reservoir Thermal Energy Storage Optimization: Numerical Modeling and Machine Learning Input and Output Files. [Data set]. Geothermal Data Repository. Idaho National Laboratory. https://doi.org/10.15121/1891881
Jin, Wencheng, Trevor A. Atkinson, Christine Doughty, Ghanashyam Neupane, Nicolas Spycher, Travis L. McLing, Patrick F. Dobson, Robert Smith, and Robert Podgorney. Machine Learning-Assisted High-Temperature Reservoir Thermal Energy Storage Optimization: Numerical Modeling and Machine Learning Input and Output Files. Idaho National Laboratory, April, 15, 2022. Distributed by Geothermal Data Repository. https://doi.org/10.15121/1891881
@misc{GDR_Dataset_1412,
title = {Machine Learning-Assisted High-Temperature Reservoir Thermal Energy Storage Optimization: Numerical Modeling and Machine Learning Input and Output Files},
author = {Jin, Wencheng and Atkinson, Trevor A. and Doughty, Christine and Neupane, Ghanashyam and Spycher, Nicolas and McLing, Travis L. and Dobson, Patrick F. and Smith, Robert and Podgorney, Robert},
abstractNote = {This data set includes the numerical modeling input files and output files used to synthesize data, and the reduced-order machine learning models trained from the synthesized data for reservoir thermal energy storage site identification.
In this study, a machine-learning-assisted computational framework is presented to identify High-Temperature Reservoir Thermal Energy Storage (HT-RTES) site with optimal performance metrics by combining physics-based simulation with stochastic hydrogeologic formation and thermal energy storage operation parameters, artificial neural network regression of the simulation data, and genetic algorithm-enabled multi-objective optimization. A doublet well configuration with a layered (aquitard-aquifer-aquitard) generic reservoir is simulated for cases of continuous operation and seasonal-cycle operation scenarios. Neural network-based surrogate models are developed for the two scenarios and applied to generate the Pareto fronts of the HT-RTES performance for four potential HT-RTES sites. The developed Pareto optimal solutions indicate the performance of HT-RTES is operation-scenario (i.e., fluid cycle) and reservoir-site dependent, and the performance metrics have competing effects for a given site and a given fluid cycle. The developed neural network models can be applied to identify suitable sites for HT-RTES, and the proposed framework sheds light on the design of resilient HT-RTES systems.
All the simulations and the neural network model were done by Idaho National Laboratory. A detailed description of the work was reported in publication linked below.},
url = {https://gdr.openei.org/submissions/1412},
year = {2022},
howpublished = {Geothermal Data Repository, Idaho National Laboratory, https://doi.org/10.15121/1891881},
note = {Accessed: 2025-04-23},
doi = {10.15121/1891881}
}
https://dx.doi.org/10.15121/1891881
Details
Data from Apr 15, 2022
Last updated Oct 12, 2022
Submitted Sep 1, 2022
Organization
Idaho National Laboratory
Contact
Wencheng Jin
404.906.7832
Authors
Keywords
Reservoir Thermal Energy Storage, Stochastic Simulation, GeoTES, Machine Learning, Modeling, TES, HT-RTES, characterization, numerical model, stochastic, hydrogeologic formation, simulated data, simulation data, High-Temperature, Thermal Energy Storage, Optimization, artificial neural network regression, ANN, neural network, operation scenarios, seasonal-cycle, Pareto fronts, seasonal operation, continuous operation, Falcon, MOOSEDOE Project Details
Project Name Dynamic Earth Energy Storage: Terawatt-year, Grid-scale Energy Storage using Planet Earth as a Thermal Battery (GeoTES): Phase II
Project Lead Jeffrey Bowman
Project Number FY22 AOP 2.8.1.1