aiqbench analysis
This article introduces Neptuna, a specialized benchmarking framework designed to evaluate machine learning surrogates for complex compressible multiphase flows involving shocks and material interfaces. By providing 2.4 TB of high-fidelity datasets alongside diverse model evaluations—including transformer-based architectures and physics-informed losses—it addresses critical gaps in simulating nonlinear fluid dynamics where traditional methods struggle with discontinuities. The findings highlight that composite loss functions, particularly those using adaptive weighting strategies like SoftAdapt, offer significant improvements in interface preservation without substantial computational overhead.
Neptuna: A Comprehensive Machine Learning Framework for Benchmarking Complex Multiphase Flows
arXiv:2607.22280v1 Announce Type: cross Abstract: Compressible multiphase flows involving shocks and material interfaces arise in applications such as bubble collapse and droplet breakup, where strong nonlinear interactions produce complex interface deformation, mixing, and multiscale dynamics. Developing reliable machine learning surrogates for these flows remains challenging due to the simultaneous presence of compressibility, sharp discontinuities, and multiphase effects. In this work, we introduce the first large-scale benchmark specifically designed for shock-driven compressible multiphase flows, comprising 2.4 TB of high-fidelity 2D and 3D datasets \footnote{Dataset repo: https://huggingface.co/FluidVerse. Dataset sample videos, metadata.json, inference rollout plots from autoregressive rollout of the trained baselines are provided in the supplementary\_material.zip } featuring shock-induced bubble collapse and droplet breakup. We evaluate diverse surrogate model families on our benchmarking framework: Neptuna \footnote{Benchmarking repo: https://anonymous.4open.science/r/neptuna-A4E3}, including convolutional, spectral, transformer-based, and pre-trained PDE foundation models. Beyond standard MSE training, we investigate composite losses combining MSE with Sobolev, interface-aware, and structure-aware terms, together with adaptive loss balancing using SoftAdapt and GradNorm. Evaluation includes pointwise, spectral, feature-focused, structural, and physics-informed metrics. Results show that no single model performs best across all datasets and metrics, while composite losses significantly improve interface preservation and spectral fidelity. Among adaptive weighting strategies, SoftAdapt provides the most consistent improvements with almost no overhead compared to MSE-only training.
Abstract:Compressible multiphase flows involving shocks and material interfaces arise in applications such as bubble collapse and droplet breakup, where strong nonlinear interactions produce complex interface deformation, mixing, and multiscale dynamics. Developing reliable machine learning surrogates for these flows remains challenging due to the simultaneous presence of compressibility, sharp discontinuities, and multiphase effects. In this work, we introduce the first large-scale benchmark specifically designed for shock-driven compressible multiphase flows, comprising 2.4 TB of high-fidelity 2D and 3D datasets \footnote{Dataset repo: this https URL. Dataset sample videos, this http URL, inference rollout plots from autoregressive rollout of the trained baselines are provided in the supplementary\this http URL } featuring shock-induced bubble collapse and droplet breakup. We evaluate diverse surrogate model families on our benchmarking framework: Neptuna \footnote{Benchmarking repo: this https URL}, including convolutional, spectral, transformer-based, and pre-trained PDE foundation models. Beyond standard MSE training, we investigate composite losses combining MSE with Sobolev, interface-aware, and structure-aware terms, together with adaptive loss balancing using SoftAdapt and GradNorm. Evaluation includes pointwise, spectral, feature-focused, structural, and physics-informed metrics. Results show that no single model performs best across all datasets and metrics, while composite losses significantly improve interface preservation and spectral fidelity. Among adaptive weighting strategies, SoftAdapt provides the most consistent improvements with almost no overhead compared to MSE-only training.
Fluid Dynamics (physics.flu-dyn); Artificial Intelligence (cs.AI)
arXiv:2607.22280 [physics.flu-dyn]
(or arXiv:2607.22280v1 [physics.flu-dyn] for this version)
https://doi.org/10.48550/arXiv.2607.22280 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 310 words
