A Multimodal Vision Transformer-based Modeling Framework for Prediction of Fluid Flows in Energy Systems

Kiran Yalamanchi; Shivam Barwey; Ibrahim Jarrah; Pinaki Pal

physics.flu-dynApr 2, 2026

A Multimodal Vision Transformer-based Modeling Framework for Prediction of Fluid Flows in Energy Systems

Authors: Kiran Yalamanchi, Shivam Barwey, Ibrahim Jarrah, Pinaki Pal

Organizations: Transportation and Power Systems Division, Argonne National Laboratory, Lemont, IL, USA

Abstract

Computational fluid dynamics (CFD) simulations of complex fluid flows in energy systems are prohibitively expensive due to strong nonlinearities and multiscale-multiphysics interactions. In this work, we present a transformer-based modeling framework for prediction of fluid flows, and demonstrate it for high-pressure gas injection phenomena relevant to reciprocating engines. The approach employs a hierarchical Vision Transformer (SwinV2-UNet) architecture that processes multimodal flow datasets from multi-fidelity simulations. The model architecture is conditioned on auxiliary tokens explicitly encoding the data modality and time increment. Model performance is assessed on two different tasks: (1) spatiotemporal rollouts, where the model autoregressively predicts the flow state at future times; and (2) feature transformation, where the model infers unobserved fields/views from observed fields/views. We train separate models on multimodal datasets generated from in-house CFD simulations of argon jet injection into a nitrogen environment, encompassing multiple grid resolutions, turbulence models, and equations of state. The resulting data-driven models learn to generalize across resolutions and modalities, accurately forecasting the flow evolution and reconstructing missing flow-field information from limited views. This work demonstrates how large vision transformer-based models can be adapted to advance predictive modeling of complex fluid flow systems.

Figures & tables

ID	Grid	Turbulence	Equation of State	$Sc$
C–LES–RG	Coarse	LES	Real gas	–
C–RANS–RG	Coarse	RANS	Real gas	–
C–RANS–RG–0.5	Coarse	RANS	Real gas	0.50
F–LES–IG	Fine	LES	Ideal gas	–
F–RANS–IG	Fine	RANS	Ideal gas	–
F–RANS–RG	Fine	RANS	Real gas	–

Table 1: Curated simulation datasets for argon (

35\text{\,}\mathrm{b}\mathrm{a}\mathrm{r}

) injection into nitrogen (

5\text{\,}\mathrm{b}\mathrm{a}\mathrm{r}

). Each case label encodes grid resolution (C/F), turbulence model, equation of state, and Schmidt number (if applicable).

Figure 1: Schematic of the SwinV2-UNet architecture used for spatiotemporal prediction.

Figure 2: Spatiotemporal prediction results for longitudinal projected flow variables. Each row corresponds to a physical variable ( $\rho$ , $u$ , $v$ , $w$ ). Columns show: input at $t=1.00$ s, ground-truth target at $t=1.01$ s, baseline model (trained with single-step rollout) prediction at $t=1.01$ s, and local prediction error at $t=1.01$ s.

Figure 3: Spatiotemporal prediction results for longitudinal slice variables. Layout as in Figure 2 , with rows for density and velocity components ( $u$ , $v$ , $w$ ) on planar slices.

Figure 4: Spatiotemporal prediction results for density on transverse planes at $z=2$ mm and $z=10$ mm. Columns show input, target, baseline model prediction, and local prediction error.

Figure 5: Feature transformation results for Case 1: longitudinal projected density to velocity components ( $u$ , $v$ , $w$ ) using Euclidean loss.

Figure 6: Feature transformation results for Case 1: longitudinal slice density to velocity components ( $u$ , $v$ , $w$ ) using Euclidean loss.

Figure 7: Feature transformation results for Case 2: longitudinal projected density to transverse slice density reconstruction.

Figure 8: Feature transformation results for Case 3: longitudinal projected density + velocity components to longitudinal slice density + velocity components.

Figure 9: Feature transformation results for Case 4: longitudinal slice density + velocity components to longitudinal projected density + velocity components in longitudinal direction.

Figure 10: Feature transformation results for Case 5: transverse slice density at $z=2$ mm to transverse slice density at $z=10$ mm.

Computational Fluid Dynamics

Computational fluid dynamics numerically models fluid motion, turbulence, heat and mass transport, and fluid–structure interactions.

See all 275 papers

FluidFlow: a flow-matching generative model for fluid dynamics surrogates on unstructured meshes
Mar 30, 2026David Ramos, Lucas Lacasa, Fermín Gutiérrez +2PDE Surrogate Modeling Computational Fluid Dynamics
ETSIAE-UPM-School of Aeronautics, Universidad Politécnica de Madrid, Plaza Cardenal Cisneros 3, E-28040 Madrid, Spain · Institute for Cross-Disciplinary Physics and Complex Systems (IFISC, CSIC-UIB), 07122 Palma de Mallorca (Spain) · Center for Computational Simulation, Universidad Politécnica de Madrid, Campus de Montegancedo, Boadilla del Monte, 28660 Madrid, Spain
A Physics-Informed Fourier-Wavelet Transformer for Multiscale Computational Fluid Dynamics Surrogate Modeling
Jun 23, 2026Somyajit Chakraborty, Ming Pan, Xizhong ChenSurrogate Modeling PDE Surrogate Modeling
Shanghai Jiao Tong University, Department of Chemistry and Chemical Engineering 800 Dongchuan Road, Minhang District, Shanghai, 200240, China
Physics and Data Driven Transformer-Mamba Framework for Flow Field
Sep 24, 2026Zhuo Zhang, Shun Zou, Canqun Yang +1PDE Surrogate Modeling PDE Operator Learning
College of Computer Science and Technology, National University of Defense Technology, Changsha, China · College of Artificial Intelligence, Nanjing Agricultural University, NanJing, China · National SuperComputer Center in Tianjin, Binhai New Area, Tianjin, China +1

Mar 30, 2026J/K move · Enter open · S save

FluidFlow: a flow-matching generative model for fluid dynamics surrogates on unstructured meshes

David Ramos, Lucas Lacasa, Fermín Gutiérrez, Eusebio Valero+1

ETSIAE-UPM-School of Aeronautics, Universidad Politécnica de Madrid, Plaza Cardenal Cisneros 3, E-28040 Madrid, Spain · Institute for Cross-Disciplinary Physics and Complex Systems (IFISC, CSIC-UIB), 07122 Palma de Mallorca (Spain) · Center for Computational Simulation, Universidad Politécnica de Madrid, Campus de Montegancedo, Boadilla del Monte, 28660 Madrid, Spain

PDE Surrogate Modeling Computational Fluid Dynamics Conditional Generative Modeling

Open paper AskPDF arXiv

Computational fluid dynamics (CFD) provides high-fidelity simulations of fluid flows but remains computationally expensive for many-query applications. In recent years deep learning (DL) has been used to construct data-driven fluid-dynamic surrogate models. In this work we consider a different learning paradigm and embrace generative modelling as a framework for constructing scalable fluid-dynamics surrogate models. We introduce FluidFlow, a generative model based on conditional flow-matching, a recent alternative to diffusion models that learns deterministic transport maps between noise and data distributions. FluidFlow is specifically designed to operate directly on CFD data defined on both structured and unstructured meshes alike, without the needs to perform any mesh interpolation pre-processing and preserving geometric fidelity. We assess the capabilities of FluidFlow using two different core neural network architectures, a U-Net and diffusion transformer (DiT), and condition their learning on physically meaningful parameters. The methodology is validated on two benchmark problems of increasing complexity: prediction of pressure coefficients along an airfoil boundary across different operating conditions, and prediction of pressure and friction coefficients over a full three-dimensional aircraft geometry discretized on a large unstructured mesh. In both cases, FluidFlow outperform strong multilayer perceptron baselines, achieving significantly lower error metrics and improved generalisation across operating conditions. Notably, the transformer-based architecture enables scalable learning on large unstructured datasets while maintaining high predictive accuracy. These results demonstrate that flow-matching generative models provide an effective and flexible framework for surrogate modelling in fluid dynamics, with potential for realistic engineering and scientific applications.

Abstract

Computational Fluid Dynamics

Explore similar work

FluidFlow: a flow-matching generative model for fluid dynamics surrogates on unstructured meshes

A Physics-Informed Fourier-Wavelet Transformer for Multiscale Computational Fluid Dynamics Surrogate Modeling

Physics and Data Driven Transformer-Mamba Framework for Flow Field