The high dimensionality and variability of Computational Fluid Dynamics (CFD) data pose a significant challenge for Machine Learning (ML) models. The only solutions in the literature address- ing inference from CFD flow fields are based on expert-driven features, which consist of fluid dynamic quantities averaged on specific regions of the entire computational domain. However, using handcrafted features can limit the scalability and portability of existing methods, and result in the loss of critical flow field information that might be essential for capturing non-linear patterns inherent in the CFD data. We propose a method to replace handcrafted features with features defined on regions obtained by clustering. Our approach combines: i) physics-based cluster- ing, to identify meaningful regions within the flow field, ii) cluster-based feature extraction, to capture localized fluid dynamics properties, and iii) set-learning models to process the extracted information. Our solu- tion allows integrating physics-based modeling with ML, and provides a portable and flexible pipeline capable of effectively dealing with the vari- ability and dimensionality of CFD flow fields. We validate our method on publicly available CFD datasets (from the aerospace domain) and apply it to a realistic scenario, that is, the classification of pathologies in real 3D human upper airways extracted from CT scans, acquired in collaboration with a medical hospital. Experimental results demonstrate the accuracy and scalability of our method, and highlight its potential for leveraging CFD data in ML frameworks for other scientific and engi- neering applications.

Physics-Based Region Clustering to Boost Inference on Computational Fluid Dynamics Flow Fields / Margheritti, Riccardo; Semeraro, Onofrio; Quadrio, Maurizio; Boracchi, Giacomo. - (In corso di stampa). (Intervento presentato al convegno European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases - ECML PKDD tenutosi a Porto nel 15-19 Settembre 2025).

Physics-Based Region Clustering to Boost Inference on Computational Fluid Dynamics Flow Fields

Margheritti, Riccardo;
In corso di stampa

Abstract

The high dimensionality and variability of Computational Fluid Dynamics (CFD) data pose a significant challenge for Machine Learning (ML) models. The only solutions in the literature address- ing inference from CFD flow fields are based on expert-driven features, which consist of fluid dynamic quantities averaged on specific regions of the entire computational domain. However, using handcrafted features can limit the scalability and portability of existing methods, and result in the loss of critical flow field information that might be essential for capturing non-linear patterns inherent in the CFD data. We propose a method to replace handcrafted features with features defined on regions obtained by clustering. Our approach combines: i) physics-based cluster- ing, to identify meaningful regions within the flow field, ii) cluster-based feature extraction, to capture localized fluid dynamics properties, and iii) set-learning models to process the extracted information. Our solu- tion allows integrating physics-based modeling with ML, and provides a portable and flexible pipeline capable of effectively dealing with the vari- ability and dimensionality of CFD flow fields. We validate our method on publicly available CFD datasets (from the aerospace domain) and apply it to a realistic scenario, that is, the classification of pathologies in real 3D human upper airways extracted from CT scans, acquired in collaboration with a medical hospital. Experimental results demonstrate the accuracy and scalability of our method, and highlight its potential for leveraging CFD data in ML frameworks for other scientific and engi- neering applications.
In corso di stampa
File in questo prodotto:
File Dimensione Formato  
preprint_ecml_pkdd_2025_ads_653.pdf

accesso riservato

Tipologia: 1. Preprint / submitted version [pre- review]
Licenza: Non Pubblico - Accesso privato/ristretto
Dimensione 5.69 MB
Formato Adobe PDF
5.69 MB Adobe PDF   Visualizza/Apri   Richiedi una copia
Pubblicazioni consigliate

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11583/3003231