Efficient machine-learning surrogates for large-scale geological carbon and energy storage

Geological carbon and energy storage are pivotal for achieving net-zero carbon emissions and addressing climate change. However, they face uncertainties due to geological factors and operational limitations, resulting in possibilities of induced seismic events or groundwater contamination. To overcome these challenges, we propose a specialized machine-learning (ML) model to manage extensive reservoir models efficiently. While ML approaches hold promise for geological carbon storage, the substantial computational resources required for large-scale analysis are the obstacle. We've developed a method to reduce the training cost for deep neural operator models, using domain decomposition and a topology embedder to link spatio-temporal points. This approach allows accurate predictions within the model's domain, even for untrained data, enhancing ML efficiency for large-scale geological storage applications.

[1]  H. Nasrabadi,et al.  Capacity assessment and cost analysis of geologic storage of hydrogen: A case study in Intermountain-West Region USA , 2022, International Journal of Hydrogen Energy.

[2]  K. Azizzadenesheli,et al.  Real-time High-resolution CO2 Geological Storage Prediction using Nested Fourier Neural Operators , 2022, Energy & Environmental Science.

[3]  Jan N. Fuhg,et al.  Enhancing high-fidelity nonlinear solver with reduced order model , 2022, Scientific Reports.

[4]  G. Karniadakis,et al.  Learning two-phase microstructure evolution using neural operators and autoencoder architectures , 2022, npj Computational Materials.

[5]  Youngsoo Choi,et al.  Reduced order modeling for flow and transport problems with Barlow Twins self-supervised learning , 2022, Scientific Reports.

[6]  F. Ballarin,et al.  Non-intrusive reduced order modeling of natural convection in porous media using convolutional autoencoders: comparison with linear subspace techniques , 2021, Advances in Water Resources.

[7]  Hari S. Viswanathan,et al.  A framework for data-driven solution and parameter estimation of PDEs using conditional generative adversarial networks , 2021, Nature Computational Science.

[8]  S. W. Cheung,et al.  Reduced order models for Lagrangian hydrodynamics , 2021, Computer Methods in Applied Mechanics and Engineering.

[9]  K. Chang,et al.  Mitigating Injection‐Induced Seismicity Along Basement Faults by Extraction: Application to 2016–2018 Pohang Earthquakes , 2021, Journal of Geophysical Research: Solid Earth.

[10]  F. Ballarin,et al.  Data-driven reduced order modeling of poroelasticity of heterogeneous media based on a discontinuous Galerkin approximation , 2021, GEM - International Journal on Geomathematics.

[11]  Youngsoo Choi,et al.  Efficient nonlinear manifold reduced order model , 2020, ArXiv.

[12]  Youngsoo Choi,et al.  Component-wise reduced order model lattice-type structure design , 2020, Computer Methods in Applied Mechanics and Engineering.

[13]  Kamyar Azizzadenesheli,et al.  Neural Operator: Graph Kernel Network for Partial Differential Equations , 2020, ICLR 2020.

[14]  T. Jørgensen,et al.  Physics-informed neural networks for solving nonlinear diffusivity and Biot’s equations , 2020, PloS one.

[15]  Andrea Manzoni,et al.  A Comprehensive Deep Learning-Based Approach to Reduced Order Modeling of Nonlinear Time-Dependent Parametrized PDEs , 2020, Journal of Scientific Computing.

[16]  George Em Karniadakis,et al.  Learning nonlinear operators via DeepONet based on the universal approximation theorem of operators , 2019, Nature Machine Intelligence.

[17]  Youngsoo Choi,et al.  Space-time reduced order model for large-scale linear dynamical systems with application to Boltzmann transport problems , 2019, J. Comput. Phys..

[18]  S. Salimzadeh,et al.  An investigation of hydromechanical effect on well productivity in fractured porous media using full factorial experimental design , 2019, Journal of Petroleum Science and Engineering.

[19]  Alessio Fumagalli,et al.  PorePy: an open-source software for simulation of multiphysics processes in fractured porous media , 2019, Computational Geosciences.

[20]  S. Geiger,et al.  Assessment of CO2 Storage Potential in Naturally Fractured Reservoirs With Dual‐Porosity Models , 2018 .

[21]  Chaopeng Shen,et al.  A Transdisciplinary Review of Deep Learning Research and Its Relevance for Water Resources Scientists , 2017, Water Resources Research.

[22]  Youngsoo Choi,et al.  Conservative model reduction for finite-volume models , 2017, J. Comput. Phys..

[23]  Suyog Gupta,et al.  To prune, or not to prune: exploring the efficacy of pruning for model compression , 2017, ICLR.

[24]  WaiChing Sun,et al.  Effects of spatial heterogeneity and material anisotropy on the fracture pattern and macroscopic effective toughness of Mancos Shale in Brazilian tests , 2017 .

[25]  Z. Obermeyer,et al.  Predicting the Future - Big Data, Machine Learning, and Clinical Medicine. , 2016, The New England journal of medicine.

[26]  Frank Hutter,et al.  SGDR: Stochastic Gradient Descent with Warm Restarts , 2016, ICLR.

[27]  H. Greenspan,et al.  Guest Editorial Deep Learning in Medical Imaging: Overview and Future Promise of an Exciting New Technique , 2016, IEEE Trans. Medical Imaging.

[28]  Song Han,et al.  Deep Compression: Compressing Deep Neural Network with Pruning, Trained Quantization and Huffman Coding , 2015, ICLR.

[29]  J. Hesthaven,et al.  Certified Reduced Basis Methods for Parametrized Partial Differential Equations , 2015 .

[30]  David Amsallem,et al.  An adaptive and efficient greedy procedure for the optimal training of parametric reduced‐order models , 2015 .

[31]  M. Blunt,et al.  Reservoir Modeling for Flow Simulation by Use of Surfaces, Adaptive Unstructured Meshes, and an Overlapping-Control-Volume Finite-Element Method , 2015 .

[32]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[33]  Robert J. Finley,et al.  An overview of the Illinois Basin – Decatur Project , 2014 .

[34]  Damiano Pasetto,et al.  A reduced‐order model for groundwater flow equation with random hydraulic conductivity: Application to Monte Carlo methods , 2013 .

[35]  Hongkyu Yoon,et al.  Highly parameterized inverse estimation of hydraulic conductivity and porosity in a three‐dimensional, heterogeneous transport experiment , 2012 .

[36]  Albert J. Valocchi,et al.  Pore‐scale simulation of mixing‐induced calcium carbonate precipitation and dissolution in a microfluidic pore network , 2012 .

[37]  M. Bickle,et al.  Geological Carbon Storage , 2009, Geophysical Monograph Series.

[38]  Hamidreza M. Nick,et al.  Upscaling two-phase flow in naturally fractured reservoirs , 2009 .

[39]  Marcel Bauer,et al.  Numerical Methods for Partial Differential Equations , 1994 .

[40]  G. Karniadakis,et al.  Deep transfer learning for partial differential equations under conditional shift with DeepONet , 2022, ArXiv.

[41]  K. Chang,et al.  Journal of Geophysical Research: Solid Earth 3-D Modeling of Induced Seismicity Along Multiple Faults: Magnitude, Rate, and Location in a Poroelasticity System , 2018 .

[42]  Brian Straughan,et al.  Convection in Porous Media , 2008 .