Close

Anna Ivagnes

PhD Student

  • About Me

    I'm a PhD student in the SISSA mathLab group, based in Trieste (Italy). My advisor is Prof. Gianluigi Rozza and I'm working on machine learning techniques to enhance Reduced Order Models (ROMs), with applications in CFD. Photo

    Education

    SISSA - Trieste (Italy)

    PhD in Mathematical Analysis, Modeling and Applications

    Working on stabilization/closure approaches for reduced order modeling under the supervision of Prof. Gianluigi Rozza (SISSA) and Dr. Giovanni Stabile (University of Urbino and Scuola Superiore Sant'Anna, Pisa).

    SISSA - Trieste (Italy)

    Research fellowship

    Research activity in cooperation with FINCANTIERI S.P.A. on the development of a shape optimization pipeline for marine propellers using reduced order models. The project was under the supervision of Nicola Demo and Prof. Gianluigi Rozza.

    PoliTo - Torino (Italy)

    Master degree in Mathematical Engineering

    Master thesis: "Data Enhanced Reduced Order Models for turbulent flows" under the supervision of Dr. Giovanni Stabile, Dr. Andrea Mola, Prof. Traian Iliescu, and Prof. Gianluigi Rozza, and Prof. Claudio Canuto.

    Final mark: 110/110 with honors

    University of Salento - Lecce (Italy)

    Bachelor degree in Industrial Engineering

    Bachelor thesis: "Self-healing materials: study of a cohesive zone model using a thermodynamic approach", under the supervision of Dr. Marco Trullo and Prof. Rossana Dimitri.

    Final mark: 110/110 with honors

    - Liceo Quinto Ennio, Gallipoli - Lecce (Italy)

    Scientific High School

    Final mark: 100/100 with honors

    Publications

    Preprint

    Enhancing non-intrusive Reduced Order Models with space-dependent aggregation methods

    A. Ivagnes, N. Tonicello, P. Cinnella, G. Rozza

    arXiv bibTex

    IJNME, 2024

    A shape optimization pipeline for marine propellers by means of reduced order modeling techniques

    A. Ivagnes, N. Demo, G. Rozza

    arXiv doi bibTex

    JOSS, 2023

    Physics-informed neural networks for advanced modeling

    D. Coscia, A. Ivagnes, N. Demo, G. Rozza

    doi bibTex

    AMC, 2023

    Hybrid data-driven closure strategies for reduced order modeling

    A. Ivagnes, G. Stabile, A. Mola, T. Iliescu, G. Rozza

    arXiv doi bibTex

    JCP, 2023

    Pressure data-driven variational multiscale reduced order models

    A. Ivagnes, G. Stabile, A. Mola, T. Iliescu, G. Rozza

    arXiv doi bibTex

    JSC, 2023

    Towards a machine learning pipeline in reduced order modelling for inverse problems: neural networks for boundary parametrization, dimensionality reduction and solution manifold approximation

    A. Ivagnes, N. Demo, G. Rozza

    arXiv doi bibTex

    Research Projects

    Enhance intrusive ROMs with data-driven correction terms

    This project focuses on the introduction of data-driven "correction" terms into POD-Galerkin ROMs in order to re-introduce the contribution of the neglected modes.

    This project is in collaboration with Prof. Traian Iliescu, from Virginia Tech.

    "Pressure data-driven variational multiscale reduced order models",
    "Hybrid data-driven closure strategies for reduced order modeling"

    by A.Ivagnes, G. Stabile, A. Mola, T. Iliescu, G. Rozza

    Accelerate shape optimization in marine propellers through ROMs

    This project focused on the development of a shape optimization pipeline for marine propellers using reduced order models.

    This project was in cooperation with FINCANTIERI S.P.A.

    "A shape optimization pipeline for marine propellers by means of reduced order modeling techniques"

    by A.Ivagnes, N. Demo, G. Rozza

    Enhance non-intrusive ROMs with aggregation methods

    The project is focused on creating a model mixture based on the combination of non-intrusive ROMs, which differs for the reduction and approximation technique considered.

    This project is in collaboration with Prof. Paola Cinnella, from Sorbonne university.

    "Enhancing non-intrusive Reduced Order Models with space-dependent aggregation methods"

    by A. Ivagnes, N. Tonicello, P. Cinnella, G. Rozza

    Get in Touch