Optimization of geological carbon storage operations with multimodal latent dynamic model and deep reinforcement learning
Not on the map. Why?
Abstract (arXiv)
Maximizing storage performance in geological carbon storage (GCS) is crucial for commercial deployment, but traditional optimization demands resource-intensive simulations, posing computational challenges. This study introduces the multimodal latent dynamic (MLD) model, a deep learning framework for fast flow prediction and well control optimization in GCS. The MLD model includes a representation module for compressed latent representations, a transition module for system state evolution, and a prediction module for flow responses. A novel training strategy combining regression loss and joint-embedding consistency loss enhances temporal consistency and multi-step prediction accuracy. Unlike existing models, the MLD supports diverse input modalities, allowing comprehensive data interactions. The MLD model, resembling a Markov decision process (MDP), can train deep reinforcement learning agents, specifically using the soft actor-critic (SAC) algorithm, to maximize net present value (NPV) through continuous interactions. The approach outperforms traditional methods, achieving the highest NPV while reducing computational resources by over 60%. It also demonstrates strong generalization performance, providing improved decisions for new scenarios based on knowledge from previous ones.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 32 of its 129 references that are in the map. First posted on arXiv 7 Jun 2024.
Builds on
32 of 129 references.
References · 32
- 2017Attention Is All You Needcited by 59,932
- 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
- 2018Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actorcited by 4,635
- 2018World Modelscited by 1,444
- 2018Learning Latent Dynamics for Planning from Pixelscited by 1,221
- 2018Soft Actor-Critic Algorithms and Applicationscited by 1,179
- 2020Mastering Atari with Discrete World Modelscited by 990
- 2017A Brief Survey of Deep Reinforcement Learningcited by 466
- 2022Temporal Difference Learning for Model Predictive Controlcited by 375
- 2018An Introduction to Deep Reinforcement Learningcited by 201
- 2018Bayesian Deep Convolutional Encoder-Decoder Networks for Surrogate Modeling and Uncertainty Quantificationcited by 199
- 2022Mastering the Game of Stratego with Model-Free Multiagent Reinforcement Learningcited by 129
20 more
- 2017Visual Interaction Networkscited by 94
- 2019A deep-learning-based surrogate model for data assimilation in dynamic subsurface flow problemscited by 59
- 2018Deep convolutional encoder-decoder networks for uncertainty quantification of dynamic multiphase flow in heterogeneous mediacited by 56
- 2022Real-time high-resolution CO2 geological storage prediction using nested Fourier neural operatorscited by 47
- 2022Learning to Accelerate Partial Differential Equations via Latent Global Evolutioncited by 38
- 2019Deep Learning of Subsurface Flow via Theory-guided Neural Networkcited by 32
- 2020Theory-guided hard constraint projection (HCP): a knowledge-based data-driven scientific machine learning methodcited by 29
- 2018Deep autoregressive neural networks for high-dimensional inverse problems in groundwater contaminant source identificationcited by 26
- 2020Symbolic Pregression: Discovering Physical Laws from Distorted Videocited by 21
- 2021A Deep Learning-Accelerated Data Assimilation and Forecasting Workflow for Commercial-Scale Geologic Carbon Storagecited by 14
- 2020Real-Time Model Calibration with Deep Reinforcement Learningcited by 12
- 2022Use of Multifidelity Training Data and Transfer Learning for Efficient Construction of Subsurface Flow Surrogate Modelscited by 11
- 2022Deep reinforcement learning for optimal well control in subsurface systems with uncertain geologycited by 9
- 2022Deep Learning-Accelerated 3D Carbon Storage Reservoir Pressure Forecasting Based on Data Assimilation Using Surface Displacement from InSARcited by 7
- 2021Identifying optimal cycles in quantum thermal machines with reinforcement-learningcited by 6
- 2021Deep Reinforcement Learning for Constrained Field Development Optimization in Subsurface Two-phase Flowcited by 5
- 2022Convolutional-Recurrent Neural Network Proxy for Robust Optimization and Closed-Loop Reservoir Managementcited by 4
- 2022Stochastic optimal well control in subsurface reservoirs using reinforcement learningcited by 4
- 2020Model-Free Voltage Regulation of Unbalanced Distribution Network Based on Surrogate Model and Deep Reinforcement Learningcited by 2
- 2022Surrogate-assisted level-based learning evolutionary search for heat extraction optimization of enhanced geothermal systemcited by 1
Built on by
Not cited yet.