Review of artificial intelligence applications in geothermal energy extraction from hot dry rock

Abstract

The geothermal resources in hot dry rock (HDR) are considered the future trend in geothermal energy extraction due to their abundant reserves. However, exploitation of the resources is fraught with complexity and technical challenges arising from their unique characteristics of high temperature, high strength, and low permeability. With the continuous advancement of artificial intelligence (AI) technology, intelligent algorithms such as machine learning and evolutionary algorithms are gradually replacing or assisting traditional research methods, providing new solutions for HDR geothermal resource exploitation. This study first provides an overview of HDR geothermal resource exploitation technologies and AI methods. Then, the latest research progress is systematically reviewed in AI applications in HDR geothermal reservoir characterization, deep drilling, heat production, and operational parameter optimization. Additionally, this study discusses the potential limitations of AI methods in HDR geothermal resource exploitation and highlights the corresponding opportunities for AI's application. Notably, the study proposes the framework of an intelligent HDR exploitation system, offering a valuable reference for future research and practice.

Keywords

algorithm / artificial intelligence / hot dry rock / intelligent exploitation system / optimization / prediction

References

[1] Ahmmed B, Vesselinov VV. Prospectivity analyses of the Utah FORGE site using unsupervised machine learning. GRC Trans. 2021; 45: 1261-1273.

[2] Akin S, Kok MV, Uraz I. Optimization of well placement geothermal reservoirs using artificial intelligence. Comput Geosci. 2010; 36(6): 776-785.

[3] Al-Fakih A, Kaka S. Application of artificial intelligence in static formation temperature estimation. Arab J Sci Eng. 2023; 48(12): 16791-16804.

[4] Alkalbani AM, Chala GT. A comprehensive review of nanotechnology applications in oil and gas well drilling operations. Energies. 2024; 17(4): 798.

[5] Allahvirdizadeh P. A review on geothermal wells: well integrity issues. J Clean Prod. 2020; 275:124009.

[6] Aslam Khan MN, Ghafoor U, Abdullah A, et al. Prediction of thermal diffusivity of volcanic rocks using machine learning and genetic algorithm hybrid strategy. Int J Therm Sci. 2023; 192:108403.

[7] Bachmann CE, Wiemer S, Woessner J, Hainzl S. Statistical analysis of the induced Basel 2006 earthquake sequence: introducing a probability-based monitoring approach for enhanced geothermal systems. Geophys J Int. 2011; 186(2): 793-807.

[8] Ben Aoun MA, Madarász T. Applying machine learning to predict the rate of penetration for geothermal drilling located in the Utah FORGE site. Energies. 2022; 15(12): 4288.

[9] Castelli M, Fumagalli A. An evolutionary system for exploitation of fractured geothermal reservoirs. Comput Geosci. 2016; 20: 385-396.

[10] Chen C, Deng Y, Ma H, Kang X, Ma L, Qian J. Deep learning-based inversion framework by assimilating hydrogeological and geophysical data for an enhanced geothermal system characterization and thermal performance prediction. Energy. 2024; 302:131713.

[11] Chen J, Xu T, Liang X, Zhang S. Evaluation and optimization of heat extraction strategies based on deep neural network in the enhanced geothermal system. J Energy Eng. 2023; 149(1):04022050.

[12] Deb K, Jain H. Handling many-objective problems using an improved NSGA-II procedure. In 2012 IEEE Congress on Evolutionary Computation. IEEE; 2012: 1-8.

[13] Deng L, Li X, Wu Y, et al. Influence of cooling speed on the physical and mechanical properties of granite in geothermal-related engineering. Deep Undergr Sci Eng. 2022; 1(1): 40-57.

[14] Diaz MB, Kim KY, Shin HS, Zhuang L. Predicting rate of penetration during drilling of deep geothermal well in Korea using artificial neural networks and real-time data collection. J Nat Gas Sci Eng. 2019; 67: 225-232.

[15] Ekeopara PU, Nwosu CJ, Kelechi FM, Nwadiaro CP, ThankGod KK. Prediction of thermal conductivity of rocks in geothermal field using machine learning methods: a comparative approach. In: SPE Nigeria Annual International Conference and Exhibition. SPE; 2023: D032S028R002.

[16] Ertel W. Introduction to Artificial Intelligence. Springer; 2018.

[17] Feder J. Geothermal well construction: a step change in oil and gas technologies. J Pet Technol. 2021; 73(1): 32-35.

[18] Feng Z, Gani H, Damayanti AD, Gani H. An explainable ensemble machine learning model to elucidate the influential drilling parameters based on rate of penetration prediction. Geoener Sci Eng. 2023; 231:212231.

[19] Gao W, Zhao J. Deep-time temperature field simulation of hot dry rock: a deep learning method in both time and space dimensions. Geothermics. 2024a; 119:102978.

[20] Gao W, Zhao J. Prediction of geothermal temperature field by multi-attribute neural network. Geothermal Energy. 2024b; 12(1):22.

[21] Gul S, Aslanoglu V, Tuzen MK, Senturk E. Estimation of bottom hole and formation temperature by drilling fluid data: a machine learning approach. 44th Workshop on Geothermal Reservoir Engineering. Stanford University; 2019: 1-7.

[22] Hu B, Yang J, Ye Z, et al. Construction design and potential analysis of enhanced geothermal system in the guide basin based on multi-objective optimization. Prog Geophys. 2025; 40(1): 80-93.

[23] Hu X, Shentu J, Xie N, et al. Predicting triaxial compressive strength of high-temperature treated rock using machine learning techniques. J Rock Mech Geotech Eng. 2023; 15(8): 2072-2082.

[24] Huang Z, Zeng W, Gu Q, Wu Y, Zhong W, Zhao K. Investigations of variations in physical and mechanical properties of granite, sandstone, and marble after temperature and acid solution treatments. Constr Build Mater. 2021; 307:124943.

[25] Ji K, Tao Y, Huang FJ, Liu Y, Li H. Introduction to conceptual studies on hot dry rock geothermal energy extraction aided by prospective tunnelling. In: Chandrasekharam D, Baba A, eds. Enhanced Geothermal Systems (EGS). CRC Press; 2023: 71-87.

[26] Jiang A, Qin Z, Faulder D, Cladouhos TT, Jafarpour B. Recurrent neural networks for short-term and long-term prediction of geothermal reservoirs. Geothermics. 2022; 104:102439.

[27] Jiang A, Qin Z, Faulder D, Cladouhos TT, Jafarpour B. A multiscale recurrent neural network model for predicting energy production from geothermal reservoirs. Geothermics. 2023; 110:102643.

[28] Kang FC, Tang CA, Li YC, Li TJ, Men JL. Challenges and opportunities of enhanced geothermal systems: a review. Chin J Eng. 2022; 44(10): 1767-1777.

[29] Katoch S, Chauhan SS, Kumar V. A review on genetic algorithm: past, present, and future. Multimedia Tools Appl. 2021; 80: 8091-8126.

[30] Kelkar S, WoldeGabriel G, Rehfeldt K. Lessons learned from the pioneering hot dry rock project at Fenton Hill, USA. Geothermics. 2016; 63: 5-14.

[31] Kim KH, Ree JH, Kim Y, Kim S, Kang SY, Seo W. Assessing whether the 2017 M w 5.4 pohang earthquake in South Korea was an induced event. Science. 2018; 360(6392): 1007-1009.

[32] Kiran R, Dansena P, Salehi S, Rajak VK. Application of machine learning and well log attributes in geothermal drilling. Geothermics. 2022; 101:102355.

[33] Latrach A, Malki ML, Morales M, Mehana M, Rabiei M. A critical review of physics-informed machine learning applications in subsurface energy systems. Geoener Sci Eng. 2024; 239:212938.

[34] Li D, Li N, Jia J, et al. Development status and research recommendations for thermal extraction technology in deep hot dry rock reservoirs. Deep Undergr Sci Eng. 2024; 3(3): 317-325.

[35] Li H, Ji K, Tao Y, Tang C. Modelling a novel scheme of mining geothermal energy from hot dry rocks. Appl Sci. 2022; 12(21):11257.

[36] Li Y, Ali G, Rehman Akbar A. Advances in geothermal energy prospectivity mapping research based on machine learning in the age of big data. Sustain Energy Technol Assess. 2023; 60:103550.

[37] Li Y, Peng G, Du T, Jiang L, Kong XZ. Advancing fractured geothermal system modeling with artificial neural network and bidirectional gated recurrent unit. Appl Energy. 2024; 372:123826.

[38] Li Z. Predicting Induced Seismicity and Permeability Evolution Through Laboratory Experiments and Machine Learning Methods. Pennsylvania State University; 2021.

[39] Liang X, Xu T, Chen J, Jiang Z. A deep-learning based model for fracture network characterization constrained by induced micro-seismicity and tracer test data in enhanced geothermal system. Renew Energy. 2023; 216:119046.

[40] Ling W, Liu Y, Young R, Cladouhos TT, Jafarpour B. Efficient data-driven models for prediction and optimization of geothermal power plant operations. Geothermics. 2024; 119:102924.

[41] Liu S, Taleghani AD. Factors affecting the efficiency of closed-loop geothermal wells. Appl Therm Eng. 2023a; 222:119947.

[42] Liu S, Taleghani AD. Analysis of an enhanced closed-loop geothermal system. Geoener Sci Eng. 2023b; 231:212296.

[43] Lu SM. A global review of enhanced geothermal system (EGS). Renew Sustain Energy Rev. 2018; 81: 2902-2921.

[44] Lü Y, Yuan C, Zhu X, Gan Q, Li H. THMD analysis of fluid injection-induced fault reactivation and slip in EGS. Geothermics. 2022; 99:102303.

[45] McCulloch WS, Pitts W. A logical calculus of the ideas immanent in nervous activity. Bull Math Biophys. 1943; 5: 115-133.

[46] Mustafa A, Kelley M, Lu G, Bunger AP. A machine learning approach for stress prediction in granitoid formation at FORGE geothermal site using compressional and shear-wave slowness. GRC Trans. 2023; 47: 1-10.

[47] Muther T, Syed FI, Lancaster AT, Salsabila FD, Dahaghi AK, Negahban S. Geothermal 4.0: AI-enabled geothermal reservoir development-current status, potentials, limitations, and ways forward. Geothermics. 2022; 100:102348.

[48] Nath F, Romero NAG, Cabezudo E, et al. Predicting future heat outputs from enhanced geothermal system utilizing machine learning approach. In SPE Western Regional Meeting. SPE; 2024:D021S010R005.

[49] Okoroafor ER, Smith CM, Ochie KI, Nwosu CJ, Gudmundsdottir H, (Jabs) Aljubran M. Machine learning in subsurface geothermal energy: two decades in review. Geothermics. 2022; 102:102401.

[50] Olasolo P, Juárez MC, Morales MP, D'Amico S, Liarte IA. Enhanced geothermal systems (EGS): a review. Renew Sustain Energy Rev. 2016; 56: 133-144.

[51] Pandey SN, Singh M. Artificial neural network to predict the thermal drawdown of enhanced geothermal system. J Energy Resour Technol. 2021; 143(1):010901.

[52] Parmar A, Katariya R, Patel V. A review on random forest: an ensemble classifier. In: International Conference on Intelligent Data Communication Technologies and Internet of Things (ICICI) 2018. Springer International Publishing; 2019: 758-763.

[53] Phelan Z, Xing P, Panja P, Moore J, McLennan J. Prediction of formation properties based on drilling data of wells at Utah FORGE site using machine learning. In: ARMA US Rock Mechanics/Geomechanics Symposium. ARMA; 2022.

[54] Porkhial S, Salehpour M, Ashraf H, Jamali A. Modeling and prediction of geothermal reservoir temperature behavior using evolutionary design of neural networks. Geothermics. 2015; 53: 320-327.

[55] Qiao M, Jing Z, Feng C, et al. Review on heat extraction systems of hot dry rock: classifications, benefits, limitations, research status and future prospects. Renew Sustain Energy Rev. 2024; 196:114364.

[56] Rosenblatt F. The perceptron: a probabilistic model for information storage and organization in the brain. Psychol Rev. 1958; 65(6): 386-408.

[57] Sarwono S, Lukas L, Kartawidjaja MA, Wardana RS. Using machine learning for stuck pipe prediction as an early warning system for geothermal drilling operation in North Sumatra. AIP Conference Proceedings. AIP Publishing; 2024.

[58] Shi Y, Song X, Song G. Productivity prediction of a multilateral-well geothermal system based on a long short-term memory and multi-layer perceptron combinational neural network. Appl Energy. 2021; 282:116046.

[59] Snyder NK, Visser CF, Alfred EI, et al. Geothermal Drilling and Completions: Petroleum Practices Technology Transfer (No. NREL/TP-6A20-72277). National Renewable Energy Lab. (NREL); 2019.

[60] Soltani M, Moradi Kashkooli F, Souri M, et al. Environmental, economic, and social impacts of geothermal energy systems. Renew Sustain Energy Rev. 2021; 140:110750.

[61] Song G, Song X, Li G, et al. An integrated multi-objective optimization method to improve the performance of multilateral-well geothermal system. Renew Energy. 2021; 172: 1233-1249.

[62] Tester JW, Anderson BJ, Batchelor AS, et al. Impact of enhanced geothermal systems on US energy supply in the twenty-first century. Philos Trans R Soc A. 2007; 365(1853): 1057-1094.

[63] Thorhallsson S, Sveinbjornsson BM. Geothermal drilling cost and drilling effectiveness. In: Short Course on Geothermal Development and Geothermal Wells. Santana Tecla; 2012:1-10.

[64] Toews M, Holmes M. Eavor-lite performance update and extrapolation to commercial projects. GRC Trans. 2021; 45: 86-109.

[65] Wang F, Konietzky H, Herbst M. Influence of heterogeneity on thermo-mechanical behaviour of rocks. Comp Geotech. 2019; 116:103184.

[66] Wang G, Li K, Wen D, et al. Assessment of geothermal resources in China. In: Proceedings, Thirty–Eighth Workshop on Geothermal Reservoir Engineering. Stanford University; 2013: 11-13.

[67] Wang G, Song X, Shi Y, Yulong F, Yang R, Li J. Comparison of production characteristics of various coaxial closed-loop geothermal systems. Energy Convers Manage. 2020; 225:113437.

[68] Wu D, Yu L, Ju M, et al. Study on the mode I fracture properties of granites after heating and water-cooling treatments under different impact loadings. Rock Mech Rock Eng. 2022; 55(7): 4271-4290.

[69] Xu F, Song X, Li S, et al. A multi-objective optimization and multi-attribute decision-making analysis for technical-thermodynamic-economic evaluation considering the rock damage on production performance of hot dry rock geothermal resources. Appl Therm Eng. 2024; 241:122350.

[70] Xue Z, Yao S, Ma H, Zhang C, Zhang K, Chen Z. Thermo-economic optimization of an enhanced geothermal system (EGS) based on machine learning and differential evolution algorithms. Fuel. 2023; 340:127569.

[71] Xue Z, Zhang K, Zhang C, Ma H, Chen Z. Comparative data-driven enhanced geothermal systems forecasting models: a case study of qiabuqia field in China. Energy. 2023; 280:128255.

[72] Yang Y, Zhang Y, Cheng Y, et al. Using one-dimensional convolutional neural networks and data augmentation to predict thermal production in geothermal fields. J Clean Prod. 2023; 387:135879.

[73] Yu P, Mali A, Velaga T, et al. Crustal permeability generated through microearthquakes is constrained by seismic moment. Nat Commun. 2024; 15(1): 2057.

[74] Zhang C, Lu J, Zhao Y. Generative pre-trained transformers (GPT)-based automated data mining for building energy management: advantages, limitations and the future. Energy Built Environ. 2024; 5(1): 143-169.

[75] Zhang H, Wu B, Nie Y, Zhang X, Chen Z. Prediction of in-situ stresses by using machine learning and intelligent optimization algorithms. In: ARMA US Rock Mechanics/Geomechanics Symposium. ARMA; 2023.

[76] Zhang S, Yin S, Yuan Y. Estimation of fracture stiffness, in situ stresses, and elastic parameters of naturally fractured geothermal reservoirs. Int J Geomech. 2015; 15(1):04014033.

[77] Zhang W, Li J. CPINNs: a coupled physics-informed neural networks for the closed-loop geothermal system. Comp Math Appl. 2023; 132: 161-179.

[78] Zhou C, Liu G, Liao S. Probing dominant flow paths in enhanced geothermal systems with a genetic algorithm inversion model. Appl Energy. 2024a; 360:122841.

[79] Zhou C, Liu G, Liao S. Probing fractured reservoir of enhanced geothermal systems with fuzzy-genetic inversion model: impacts of geothermal reservoir environment. Energy. 2024b; 290:130320.

[80] Zhou L, Zhang Y, Hu Z, et al. Analysis of influencing factors of the production performance of an enhanced geothermal system (EGS) with numerical simulation and artificial neural network (ANN). Energy Build. 2019; 200: 31-46.

[81] Zhou Z, Roubinet D, Tartakovsky DM. Thermal experiments for fractured rock characterization: theoretical analysis and inverse modeling. Water Resour Res. 2021; 57(12):e2021WR030608.

[82] Zhu CY, Huang D, Yu B, Gong L, Xu MH. Enhanced geothermal system performance prediction based on deep learning neural networks. In: International Conference on Computational & Experimental Engineering and Sciences. Springer International Publishing; 2023: 1007-1022.

RIGHTS & PERMISSIONS

2025 The Author(s). Deep Underground Science and Engineering published by John Wiley & Sons Australia, Ltd on behalf of China University of Mining and Technology.