Multi-fidelity machine learning with knowledge transfer enhances geothermal energy system design and optimization
Abstract view|55|times PDF download|28|times
Abstract
Designing and optimizing the control schemes of geothermal energy systems is a challenging and time-consuming work due to the vast parameter space and computationally intensive simulations. Canonical evolutionary optimization approaches are laborious, slow to converge, and may not provide optimal well-control scheme for geothermal energy systems. To tackle these issues, this work reports a machine learning-guided real-time flow control optimization for enhanced geothermal systems. This approach fully leverages existing data throughout the optimization phase by creating multi-fidelity surrogate models, which comprise coarse and fine models. The coarse model strategically selects a subset of variables to develop a low-fidelity representation, while the fine model utilizes all available variables to construct a high-fidelity surrogate. Knowledge transfer from coarse surrogate can guide the fine surrogate search into a promising subspace. Active learning technique is further leveraged to improve the accuracy of surrogate by iteratively querying the most informative data points. To evaluate effectiveness of the proposed approach, benchmark function suites and two fractured geothermal energy systems are employed in comparison with conventional evolutionary algorithms and advanced surrogate-assisted methods. The results illustrate the capability of the workflow to enhance the efficiency and effectiveness of real-time decision making. This workflow paves a new path for complex and computationally intensive design optimization problems.
Document Type: Original article
Cited as: Chen, G., Jiao, J. J., Wang, Z., Dai, Q. Multi-fidelity machine learning with knowledge transfer enhances geothermal energy system design and optimization. Advances in Geo-Energy Research, 2025, 16(3): 244-259. https://doi.org/10.46690/ager.2025.06.05
Keywords
Full Text:
PDFReferences
Asai, P., Panja, P., McLennan, J., et al. Performance evaluation of enhanced geothermal system(EGS): Surrogate models, sensitivity study and ranking key parameters. Renewable Energy, 2018, 122: 184-195.
Bastek, J. H., Kochmann, D. M. Inverse design of nonlinear mechanical metamaterials via video denoising diffusion models. Nature Machine Intelligence, 2023, 5(12): 1466-1475.
Chen, G., Jiao, J., Jiang, C., et al. Surrogate-assisted level based learning evolutionary search for geothermal heat extraction optimization. Renewable and Sustainable Energy Reviews, 2024a, 189: 113860.
Chen, G., Jiao, J., Liu, Q.,et al. Machine-learning-accelerated multi-objective design of fractured geothermal systems. Nexus, 2024b, 1(4): 100044.
Chen, G., Luo, X., Jiao, J., et al. Data-driven evolutionary algorithm for oil reservoir well-placement and control optimization. Fuel, 2022, 326: 125125.
Chen, G., Luo, X., Jiao, J., et al. Fracture network characterization with deep generative model based stochastic inversion. Energy, 2023, 273: 127302.
Chen, M., Tompson, A. F. B., Mellors, R. J., et al. An efficient optimization of well placement and control for a geothermal prospect under geological uncertainty. Applied Energy, 2015, 137: 352-363.
Deng, C., Wang, Y., Qin, C., et al. Self-directed online machine learning for topology optimization. Nature Communications, 2022, 13(1): 388.
Ding, P., Zhang, K., Yuan, Z., et al. Multi-objective optimization and exergoeconomic analysis of geothermal-based electricity and cooling system using zeotropic mixtures as the working fluid. Journal of Cleaner Production, 2021, 294: 126237.
Du, X., Damewood, J. K., Lunger, J. R., et al. Machine learning-accelerated simulations to enable automatic surface reconstruction. Nature Computational Science, 2023, 3(12): 1-11.
Eiben, A. E., Smith, J. J. N. From evolutionary computation to the evolution of things. Nature, 2015, 521(7553): 476-482.
Fan, D., Jodin, G., Consi, T. R., et al. A robotic intelligent towing tank for learning complex fluid-structure dynamics. Science Robotics, 2019, 4(36): eaay5063.
Ghanizadeh, A., Clarkson, C. R., Deglint, H., et al. Unpropped/propped fracture permeability and proppant embedment evaluation: A rigorous core-analysis/imaging methodology. Paper URTEC-2459818 Presented at the SPE/AAPG/SEG Unconventional Resources Technology Conference, San Antonio, Texas, USA, 1-3 August, 2016.
Gupta, A., Ong, Y. S., Feng, L. Multifactorial evolution: Toward evolutionary multitasking. IEEE Transactions on Evolutionary Computation, 2015, 20(3): 343-357.
Gupta, A., Ong, Y. S., Feng, L. Insights on transfer optimization: Because experience is the best teacher. IEEE Transactions on Emerging Topics in Computational Intelligence, 2017, 2(1): 51-64.
Hsieh, P. A., Neuman, S. P., Stiles, G. K., et al. Field determination of the three-dimensional hydraulic conductivity tensor of anisotropic media: 2. Methodology and application to fractured rocks. Water Resources Research, 1985, 21(11): 1667-1676.
Hyman, J. D., Dentz, M., Hagberg, A., et al. Emergence of stable laws for first passage times in three-dimensional random fracture networks. Physical Review Letters, 2019, 123(24): 248501.
Jiang, Z., Ringel, L. M., Bayer, P., et al. Fracture network characterization in reservoirs by joint inversion of microseismicity and thermal breakthrough data: Method development and verification. Water Resources Research, 2023, 59(9): e2022WR034339.
Jin, Y. Knowledge Incorporation in Evolutionary Computation. Luxembourg, Germany, Springer, 2013.
Jin, Y., Wang, H., Chugh, T., et al. Data-driven evolutionary optimization: An overview and case studies. IEEE Transactions on Evolutionary Computation, 2018, 23(3): 442-458.
Jolie, E., Scott, S., Faulds, J., et al. Geological controls on geothermal resources for power generation. Nature Reviews Earth & Environment, 2021, 2(5): 324-339.
Li, B., Wei, Z., Wu, J., et al. Machine learning-enabled globally guaranteed evolutionary computation. Nature Machine Intelligence, 2023a, 5(4): 457-467.
Li, L., Ning, C., Qiu, H., et al. Online data-stream-driven distributionally robust optimal energy management for hydrogen-based multimicrogrids. IEEE Transactions on Industrial Informatics, 2023b, 20(3): 4370-4384.
Li, S., Feng, X., Zhang, D., et al. Coupled thermo-hydro mechanical analysis of stimulation and production for fractured geothermal reservoirs. Applied Energy, 2019, 247: 40-59.
Liu, B., Zhang, Q., Gielen, G. G. E. A gaussian process surrogate model assisted evolutionary algorithm for medium scale expensive optimization problems. IEEE Transactions on Evolutionary Computation, 2013, 18(2): 180-192.
Liu, Y., Liu, J., Ding, J., et al. A surrogate-assisted differential evolution with knowledge transfer for expensive incremental optimization problems. IEEE Transactions on Evolutionary Computation, 2023, 28(4): 1039-1053.
Menberg, K., Pfister, S., Blum, P., et al. A matter of meters: State of the art in the life cycle assessment of enhanced geothermal systems. Energy & Environmental Science, 2016, 9(9): 2720-2743.
Pan, D., Li, S., Xu, Z., et al. A deterministic-stochastic identification and modelling method of discrete fracture networks using laser scanning: Development and case study. Engineering Geology, 2019, 262: 105310.
Parisio, F., Vilarrasa, V., Wang, W., et al. The risks of long term re-injection in supercritical geothermal systems. Nature Communications, 2019, 10(1): 4391.
Sanchez-Lengeling, B., Aspuru-Guzik, A. Inverse molecular design using machine learning: Generative models for matter engineering. Science, 2018, 361(6400): 360-365.
Song, G., Song, X., Xu, F., et al. Numerical parametric investigation of thermal extraction from the enhanced geothermal system based on the thermal-hydraulic-chemical coupling model. Journal of Cleaner Production, 2022, 352: 131609.
Specht, D. F. A general regression neural network. IEEE Transactions on neural networks, 1991, 2(6): 568-576.
Sun, C., Jin, Y., Cheng, R., et al. Surrogate-assisted cooperative swarm optimization of high-dimensional expensive problems. IEEE Transactions on Evolutionary Computation, 2017, 21(4): 644-660.
Sun, J., Meng, X., Qiao, J. Data-driven optimal control for municipal solid waste incineration process. IEEE Transactions on Industrial Informatics, 2023, 19(12): 11444-11454.
Wang, C., Liu, J., Wu, K., et al. Solving multitask optimization problems with adaptive knowledge transfer via anomaly detection. IEEE Transactions on Evolutionary Computation, 2021, 26(2): 304-318.
Wang, J., Zhao, Z., Liu, G., et al. A robust optimization approach of well placement for doublet in heterogeneous geothermal reservoirs using random forest technique and genetic algorithm. Energy, 2022, 254: 124427.
Wang, X., Wang, G. G., Song, B., et al. A novel evolutionary sampling assisted optimization method for high dimensional expensive problems. IEEE Transactions on Evolutionary Computation, 2019, 23(5): 815-827.
Wang, Z., Zhang, K., Chen, G., et al. Evolutionary-assisted reinforcement learning for reservoir real-time production optimization under uncertainty. Petroleum Science, 2023, 20(1): 261-276.
Wang, Z., Chen, Y., Chen, G., et al. Optimization of geological carbon storage operations with multimodal latent dynamic model and deep reinforcement learning. Geoenergy Science and Engineering, 2025, 244: 213407.
Wen, G., Li, Z., Long, Q., et al. Real-time high-resolution CO2 geological storage prediction using nested fourier neural operators. Energy & Environmental Science, 2023, 16(4): 1732-1741.
Xu, T., Liang, X., Xia, Y., et al. Performance evaluation of the habanero enhanced geothermal system, australia: Optimization based on tracer and induced micro-seismicity data. Renewable Energy, 2022, 181: 1197-1208.
Xue, X., Chen, G., Zhang, K., et al. A divide-and-conquer optimization paradigm for waterflooding production optimization. Journal of Petroleum Science and Engineering, 2022, 211: 110050.
Xue, X., Yang, C., Hu, Y., et al. Evolutionary sequential transfer optimization for objective-heterogeneous problems. IEEE Transactions on Evolutionary Computation, 2021, 26(6): 1424-1438.
Xue, X., Zhang, K., Tan, K. C., et al. Affine transformation enhanced multifactorial optimization for heterogeneous problems. IEEE Transactions on Cybernetics, 2020, 52(7): 6217-6231.
Yan, B., Gudala, M., Sun, S. Robust optimization of geothermal recovery based on a generalized thermal decline model and deep learning. Energy Conversion and Management, 2023, 286: 117033.
Yang, C., Ding, J., Jin, Y., et al. Offline data-driven multiobjective optimization: Knowledge transfer between surrogates and generation of final solutions. IEEE Transactions on Evolutionary Computation, 19: 409-423.
Yao, Z., Lum, Y., Johnston, A., et al. Machine learning for a sustainable energy future. Nature Reviews Materials, 2023, 8(3): 202-215.
Yu, H., Tan, Y., Zeng, J., et al. Surrogate-assisted hierarchical particle swarm optimization. Information Sciences, 2018, 454: 59-72.
Zhang, K., Wang, Z., Chen, G., et al. Training effective deep reinforcement learning agents for real-time life-cycle production optimization. Journal of Petroleum Science and Engineering, 2022, 208: 109766.
Zhang, K., Zhao, X., Chen, G., et al. A double-model differential evolution for constrained waterflooding production optimization. Journal of Petroleum Science Engineering, 2021a, 207: 109059.
Zhang, S., Jiang, Z., Zhang, S., et al. Well placement optimization for large-scale geothermal energy exploitation considering nature hydro-thermal processes in the gonghe basin, china. Journal of Cleaner Production, 2021b, 317: 128391.
Zimmerman, R. W., Chen, G., Hadgu, T., et al. A numerical dual-porosity model with semianalytical treatment of fracture/matrix flow. Water Resources Research, 1993, 29(7): 2127-2137.
DOI: https://doi.org/10.46690/ager.2025.06.05
Refbacks
- There are currently no refbacks.
Copyright (c) 2025 The Author(s)
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.