A Deep-Learning Iterative Stacked Approach for Prediction of Reactive Dissolution in Porous Media

2025-03-11

AI Summary

To address the high computational cost and lack of real-time decision support in simulating reactive mineral dissolution in porous media, this paper proposes a physics-informed deep learning framework for efficient spatiotemporal forecasting. Methodologically, we design an iterative stacked architecture coupling convolutional neural networks (CNNs) with recurrent modules, enabling multi-step, joint prediction of evolving porosity, solute concentration, and Darcy velocity—while explicitly capturing long-range temporal dependencies. Trained on high-fidelity numerical simulation data, the model achieves prediction accuracy comparable to state-of-the-art numerical solvers, yet accelerates inference by approximately four orders of magnitude. This framework overcomes the efficiency bottleneck of conventional simulations and establishes a scalable, high-fidelity rapid simulation paradigm for subsurface engineering applications—including carbon capture and storage (CCS), geothermal energy extraction, and enhanced oil recovery.

Technology Category

• Data Mining & Knowledge Management: Mining of Spatial, Temporal or Spatio-Temporal Data
• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning
• Cognitive Modeling & Cognitive Systems: Conceptual Inference and Reasoning

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Web Mining and Content Analysis: Web data generation and simulation
• Systems and Infrastructure for Web, Mobile and WoT: Sustainability and carbon-aware systems for Web, mobile, and WoT

Abstract

Simulating reactive dissolution of solid minerals in porous media has many subsurface applications, including carbon capture and storage (CCS), geothermal systems and oil&gas recovery. As traditional direct numerical simulators are computationally expensive, it is of paramount importance to develop faster and more efficient alternatives. Deep-learning-based solutions, most of them built upon convolutional neural networks (CNNs), have been recently designed to tackle this problem. However, these solutions were limited to approximating one field over the domain (e.g. velocity field). In this manuscript, we present a novel deep learning approach that incorporates both temporal and spatial information to predict the future states of the dissolution process at a fixed time-step horizon, given a sequence of input states. The overall performance, in terms of speed and prediction accuracy, is demonstrated on a numerical simulation dataset, comparing its prediction results against state-of-the-art approaches, also achieving a speedup around $10^4$ over traditional numerical simulators.

Problem

• Predict reactive dissolution in porous media efficiently
• Overcome computational expense of traditional numerical simulators
• Incorporate temporal and spatial data for accurate predictions

Innovation

• Deep-learning iterative stacked approach
• Incorporates temporal and spatial information
• Achieves 10^4 speedup over traditional simulators