Towards Fast GNN Surrogates for CO2 Migration in Complex Geological Formations

• URL: http://arxiv.org/abs/2606.17180v1
• Date: Mon, 15 Jun 2026 18:19:17 GMT
• Title: Towards Fast GNN Surrogates for CO2 Migration in Complex Geological Formations
• Abstract summary: We propose an end-to-end graph neural surrogate tailored to CO$$ibility plume migration forecasting in geological storage.<n>The method is evaluated on the SPE11A benchmark, a well-known industry test case designed to assess CO$$ storage scenarios.<n>The proposed model produces competitive forecasts of gas saturation and liquid-phase density, with cumulative errors that remain moderate over extended forecasting horizons.
• Score: 58.079925240809644
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: This chapter discusses how a data-driven machine learning approach can reproduce key aspects of the physical behavior of multiphase flows in complex geological formations. We propose an end-to-end graph neural surrogate tailored to CO$_2$ plume migration forecasting in geological storage. The method is evaluated on the SPE11A benchmark, a well-known industry test case designed to assess CO$_2$ storage scenarios and characterized by sharp gas-water interfaces, strong advective transport, and rapid convective mixing with fingering development. The benchmark is reformulated as a graph in which nodes represent computational cells and edges encode transmissibility-based interactions enriched with geometric attributes. Directional transport arising from grid geometry, permeability contrasts, and geological heterogeneity is captured through an anisotropic message-passing mechanism, where interaction weights are computed via geometry-conditioned edge embeddings, biasing message aggregation toward physically relevant transport directions. Temporal evolution is modeled in latent space using an autoregressive residual formulation trained with multi-step supervision. The proposed model produces competitive forecasts of gas saturation and liquid-phase density, which are key indicators for CO$_2$ storage monitoring, with cumulative errors that remain moderate over extended forecasting horizons.

Related papers

• DyG$^2$T: Modeling Object Dynamics with 3D Gaussian Temporal-Spatial Particle Graph Transformer [86.4618122245946]
  DyG$2$T is a dynamics modeling framework that infers object motion trajectories by spatially completing and temporally discriminating Key Point representations.<n>Experiments on both synthetic and real-world datasets demonstrate that DyG$2$T achieves accurate dynamics modeling and reasoning.
  arXiv  Detail & Related papers  (2026-08-19T03:44:28Z)
• A Unified Geometric Framework for Developmental Analysis of Spatial Transcriptomic Data [38.40052829128497]
  High-resolution single-cell and transcriptomic technologies provide snapshots of heterogeneous cellular states.<n> temporal and spatial dynamics must be inferred from independently sampled, unaligned cell populations.<n>We introduce a geometric framework for analyzing thetemporal evolution of gene expression networks through embeddings in Gromov--Wasserstein (GW) space.
  arXiv  Detail & Related papers  (2026-08-15T16:19:58Z)
• Deep Gaussian Processes on Directed Acyclic Graphs [11.74273181198187]
  Many real-world processes can be represented as compositions of functions along a directed acyclic graph (DAG)<n>These functions are partially observed across the DAG, with noisy and heterogeneously sampled measurements.<n>We theoretically study their prior-collapse behaviour, and the effect of graph topology and intermediate observations on information preservation.<n>We offer a structured variational approximation that retains graph dependencies, preserves compositional uncertainty, and captures the explaining-away behaviour of colliders.
  arXiv  Detail & Related papers  (2026-07-10T17:41:11Z)
• Embedded Polygon Symbolic Transfer Entropy (EPSTE): A Geometric Token and Deep Learning Approach to Estimating Transfer Entropy in Neuroimaging Time Series [2.1575136240463597]
  This work introduces Embedded Polygon Transfer Entropy (EPSTE), a framework that reframes TE estimation as a learnable problem.<n>A recurrent neural network with attention-based multiple-instance learning is trained to predict surrogate-validated TE values from bags of symbolic temporal windows.<n>The results demonstrate that while local window-level predictions are noisy, aggregation across trials and channel pairs yields stable directed dependencies.
  arXiv  Detail & Related papers  (2026-06-19T21:13:56Z)
• Physics-Guided Dual-Stream Heterogeneous Graph Neural Network for Predicting Full-Field Structural Response of Stiffened Panels [0.0]
  Iterative design and optimization of large, complex structures require fast and accurate prediction of stress, displacement, and other fields.<n>Existing neural network surrogates often struggle with varying topologies and complex boundary conditions.<n>This study proposes the novel DualStream Heterogeneous Graph Neural Network (DS-HGNN) for full-field stress and displacement prediction in thin-walled structures.
  arXiv  Detail & Related papers  (2026-06-18T20:12:18Z)
• Topological Flow Matching [56.16372813551555]
  Flow matching is a powerful generative modeling framework, valued for its simplicity and strong empirical performance.<n>We introduce topological flow matching, a topology-aware generalization of flow matching.<n>We demonstrate its effectiveness on diverse structured datasets, including brain fMRIs, ocean currents, seismic events, and traffic flows.
  arXiv  Detail & Related papers  (2026-06-14T16:29:33Z)
• Crash Assessment via Mesh-Based Graph Neural Networks and Physics-Aware Attention [0.0]
  We evaluate whether neural surrogates can reproduce full-field crash kinematics with sufficient accuracy, spatial regularity, and structural plausibility for engineering interpretation.<n>The proposed architectures combine local mesh message passing, geometry-aware global attention, and sparse contact-aware correction for autoregressive crash rollout.
  arXiv  Detail & Related papers  (2026-05-12T08:50:49Z)
• Beyond Distance: Quantifying Point Cloud Dynamics with Persistent Homology and Dynamic Optimal Transport [29.979662030541146]
  We introduce a framework for analyzing topological tipping in time-evolutionary point clouds by extending the recently proposed Topological Optimal Transport (TpOT) distance.<n>To overcome this limitation, we present a hierarchical dynamic evaluation framework driven by a novel topological and hypergraph reconstruction strategy.<n>Along this geodesic, we introduce a set of multi-scale indicators: macroscopic metrics (Topological Distortion and Persistence Entropy) to capture global shifts, and a novel mesoscopic dual-perspective Hypergraph Entropy to detect highly sensitive, asynchronous local rewirings.
  arXiv  Detail & Related papers  (2026-03-15T07:56:56Z)
• GeodesicNVS: Probability Density Geodesic Flow Matching for Novel View Synthesis [54.39598154430305]
  We propose a Data-to-Data Flow Matching framework that learns deterministic transformations directly between paired views.<n>PDG-FM constrains flow trajectories using geodesic interpolants derived from probability density metrics of pretrained diffusion models.<n>These results highlight the advantages of incorporating data-dependent geometric regularization into deterministic flow matching for consistent novel view generation.
  arXiv  Detail & Related papers  (2026-03-01T09:30:11Z)
• GeoGNN: Quantifying and Mitigating Semantic Drift in Text-Attributed Graphs [59.61242815508687]
  Graph neural networks (GNNs) on text--attributed graphs (TAGs) encode node texts using pretrained language models (PLMs) and propagate these embeddings through linear neighborhood aggregation.<n>This work introduces a local PCA-based metric that measures the degree of semantic drift and provides the first quantitative framework to analyze how different aggregation mechanisms affect manifold structure.
  arXiv  Detail & Related papers  (2025-11-12T06:48:43Z)
• EHGCN: Hierarchical Euclidean-Hyperbolic Fusion via Motion-Aware GCN for Hybrid Event Stream Perception [57.54227977352417]
  Event cameras emit high-speed event stream for perception tasks.<n>We propose a novel approach named EHGCN to perceive event stream in both Euclidean and hyperbolic spaces.
  arXiv  Detail & Related papers  (2025-04-23T11:01:03Z)
• Diffusion-based subsurface CO$_2$ multiphysics monitoring and forecasting [4.2193475197905705]
  We propose a novel subsurface multiphysics monitoring and forecasting framework utilizing video diffusion models.<n>This approach can generate high-quality representations of CO$2$ evolution and associated changes in subsurface elastic properties.<n>Tests based on the Compass model show that the proposed method successfully captured the inherently complex physical phenomena associated with CO$$ monitoring.
  arXiv  Detail & Related papers  (2024-07-25T23:04:37Z)
• Physical-Virtual Collaboration Modeling for Intra-and Inter-Station Metro Ridership Prediction [116.66657468425645]
  We propose a unified Physical-Virtual Collaboration Graph Network (PVCGN), which can effectively learn the complex ridership patterns from the tailor-designed graphs. Specifically, a physical graph is directly built based on the realistic topology of the studied metro system. A similarity graph and a correlation graph are built with virtual topologies under the guidance of the inter-station passenger flow similarity and correlation.
  arXiv  Detail & Related papers  (2020-01-14T16:47:54Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.