Hybrid Cold-Start Recommender System for Closure Model Selection in Multiphase Flow Simulations
2026-04-10 • Information Retrieval
Information Retrieval
AI summaryⓘ
The authors address the challenge of choosing the best physical models to simulate fluid flows involving multiple phases, which is usually hard and costly. They treat this choice as a recommendation problem and develop a system that uses both case details and past results from similar scenarios to suggest good model combinations for new simulations. Tested on a large dataset of simulations, their system outperforms simpler methods and saves time and effort by avoiding poor model choices. Their work shows that recommendation techniques can help make smarter decisions in complex scientific simulations with limited data.
multiphase CFDclosure modelsrecommendation systemsmatrix completionmetadata-driven similaritycross-validationmodel selectionregret measurecomputational fluid dynamicssimulation optimization
Authors
S. Hänsch, A. Sajdoková, A. Rębowski, F. Miškařík, K. Ramakrishna, F. Schlegel, V. Rybář, R. Alves, P. Kordík
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.