Hybrid Cold-Start Recommender System for Closure Model Selection in Multiphase Flow Simulations

TL;DR

This paper introduces a hybrid recommender system for selecting physical models in multiphase CFD simulations, improving decision accuracy with limited data and leveraging both case similarity and collaborative inference.

Contribution

It formulates closure model selection as a cold-start recommender problem and proposes a hybrid framework combining metadata similarity and matrix completion for scientific decision support.

Findings

The hybrid recommender outperforms baseline models in simulation ranking accuracy.

It reduces decision regret across various data sparsity levels.

The approach effectively supports complex scientific model choices with limited prior data.

Abstract

Selecting appropriate physical models is a critical yet difficult step in many areas of computational science and engineering. In multiphase Computational Fluid Dynamics (CFD), practitioners must choose among numerous closure model combinations whose performance varies strongly across flow conditions. Sub-optimal choices can lead to inaccurate predictions, simulation failures, and wasted computational resources, making model selection a prime candidate for data-driven decision support. This work formulates closure model selection as a cold-start recommender system problem in a high-cost scientific domain. We propose a hybrid recommendation framework that combines (i) metadata-driven case similarity and (ii) collaborative inference via matrix completion. The approach enables case-specific model recommendations for entirely new CFD cases using their descriptive features, while leveraging historical simulation results from similar cases. The methodology is evaluated on 13,600 simulations across 136 validation cases and 100 model combinations. A nested cross-validation protocol with experiment-level holdout is employed to rigorously assess generalisation to unseen flow scenarios under varying levels of data sparsity. Recommendation quality is measured using ranking-based metrics and a domain-specific regret measure capturing performance loss relative to the per-case optimum. Results show that the proposed hybrid recommender consistently outperforms popularity-based and expert-designed reference models and reduces regret across the investigated sparsities. These findings demonstrate that recommender system methodology can effectively support complex scientific decision-making tasks characterised by expensive evaluations, structured metadata, and limited prior observations.