Data Driven Computational Mechanics at EXascale

Información del proyecto

DComEX

Identificador del acuerdo de subvención: 956201

DOI

10.3030/956201

Proyecto cerrado

Fecha de la firma de la CE 3 Diciembre 2020

Fecha de inicio 1 Abril 2021

Fecha de finalización 30 Septiembre 2024

Financiado con arreglo a

• INDUSTRIAL LEADERSHIP - Leadership in enabling and industrial technologies - Information and Communication Technologies (ICT)

Coste total

€ 2 981 250,00

Aportación de la UE

€ 1 359 375,00

Coordinado por

ETHNICON METSOVION POLYTECHNION
Greece

CORDIS proporciona enlaces a los documentos públicos y las publicaciones de los proyectos de los programas marco HORIZONTE.

Los enlaces a los documentos y las publicaciones de los proyectos del Séptimo Programa Marco, así como los enlaces a algunos tipos de resultados específicos, como conjuntos de datos y «software», se obtienen dinámicamente de OpenAIRE .

Resultado final

Documents, reports (12)

AI-Solve library prototype (report)
Communication, dissemination and exploitation report (report)
DMAPand CAE surrogate model Report

DMAP and CAE surrogate model Report

Communication, dissemination and exploitation report and plan (report)
Performance evaluation of DCoMEX-BIO prototype (report)
Communication, dissemination and exploitation plan (report)
System requirements, design and architecture (report)
Performance evaluation of DCoMEX-MAT prototype (report)
Data processing software final evaluation and documentation (report)Data processing software final evaluation and documentation (report)

Data processing software final evaluation and documentation (report)

Collaboration plan with definition of common objectives and activities including Milestones (report)

Collaboration plan with definition of common objectives and activities including Milestones. Updated versions will be delivered at the end of each reporting period (report)

AI-Solve performance evaluation (report)
DCoMEX codes baseline prototype (report)

Other (6)

UQ aware image segmentation final software (software module)
Optimal material composition for CNT reinforced concrete applications
Post-processing final software (software module)
DCoMEX codes baseline prototype (software module)
UQ aware image segmentation prototype (software module)
DMAP algorithm prototype

Open Research Data Pilot (1)

Data management plan (report)

Websites, patent fillings, videos etc. (1)

DCoMEX website

Publicaciones

Peer reviewed articles (22)

AI‐enhanced iterative solvers for accelerating the solution of large‐scale parametrized systems

Autores: Stefanos Nikolopoulos, Ioannis Kalogeris, George Stavroulakis, Vissarion Papadopoulos
Publicado en: International Journal for Numerical Methods in Engineering, Edición 125, 2023, ISSN 0029-5981
Editor: John Wiley & Sons Inc.
DOI: 10.1002/nme.7372

Solving inverse problems in physics by optimizing a discrete loss: Fast and accurate learning without neural networks

Autores: Petr Karnakov, Sergey Litvinov, Petros Koumoutsakos
Publicado en: PNAS Nexus, Edición 3, 2024, ISSN 2752-6542
Editor: Oxford University Press
DOI: 10.1093/pnasnexus/pgae005

A computational framework for the indirect estimation of the interface thermal resistance of composite materials using XPINNs

Autores: L. Papadopoulos, S. Bakalakos, S. Nikolopoulos, I. Kalogeris, V. Papadopoulos
Publicado en: International Journal of Heat and Mass Transfer, Edición 2023, 2023, ISSN 0017-9310
Editor: Pergamon Press Ltd.
DOI: 10.1016/j.ijheatmasstransfer.2022.123420

Quantitative 3D histochemistry reveals region-specific amyloid-β reduction by the antidiabetic drug netoglitazone

Autores: Francesca Catto, Ehsan Dadgar-Kiani, Daniel Kirschenbaum, Athena E. Economides, Anna Maria Reuss, Chiara Trevisan, Davide Caredio, Delic Mirzet, Lukas Frick, Ulrike Weber-Stadlbauer, Sergey Litvinov, Petros Koumoutsakos, Jin Hyung Lee, Adriano Aguzzi
Publicado en: biorxiv, 2024, ISSN 1559-6095
Editor: Cold Spring Harbor Laboratory Press
DOI: 10.1101/2024.08.15.608042

Personalized in silico model for radiation-induced pulmonary fibrosis

Autores: E. Ioannou, M. Hadjicharalambous, A. Malai, E. Papageorgiou, A. Peraticou, N. Katodritis, D. Vomvas, V. Vavourakis
Publicado en: Journal of the Royal Society Interface, 2024, ISSN 1742-5662
Editor: Zenodo
DOI: 10.5281/zenodo.13766990

Closure Discovery for Coarse-grained Partial Differential Equations with Grid-based Reinforcement Learning

Autores: JP. von Bassewitz, S. Kaltenbach, P. Koumoutsakos
Publicado en: arxiv, 2025, ISSN 2331-8422
Editor: Cornell University
DOI: 10.48550/arxiv.2402.00972

Interpretable learning of effective dynamics for multiscale systems

Autores: E. Menier, S. Kaltenback, M. Yagoubi, M. Schoenauer, P. Koumoutsakos
Publicado en: arXiv, 2025, ISSN 2331-8422
Editor: Cornell University
DOI: 10.48550/arxiv.2309.05812

Machine learning accelerated transient analysis of stochastic nonlinear structures

Autores: S. Nikolopoulos, I. Kalogeris, V. Papadopoulos
Publicado en: Engineering Structures, Edición Volume 257, 2022, 2022, ISSN 0141-0296
Editor: Pergamon Press Ltd.
DOI: 10.1016/j.engstruct.2022.114020

Toward image-based personalization of glioblastoma therapy: A clinical and biological validation study of a novel, deep learning-driven tumor growth model

Autores: Marie-Christin Metz, Ivan Ezhov, Jan C Peeken, Josef A Buchner, Jana Lipkova, Florian Kofler, Diana Waldmannstetter, Claire Delbridge, Christian Diehl, Denise Bernhardt, Friederike Schmidt-Graf, Jens Gempt, Stephanie E Combs, Claus Zimmer, Bjoern Menze, Benedikt Wiestler
Publicado en: Neuro-Oncology Advances, Edición 6, 2024, ISSN 2632-2498
Editor: Oxford University Press
DOI: 10.1093/noajnl/vdad171

Multiscale analysis of nonlinear systems using a hierarchy of deep neural networks

Autores: Stefanos Pyrialakos, Ioannis Kalogeris, Vissarion Papadopoulos
Publicado en: International Journal of Solids and Structures, Edición 271-272, 2024, Página(s) 112261, ISSN 0020-7683
Editor: Pergamon Press Ltd.
DOI: 10.1016/j.ijsolstr.2023.112261

Domain decomposition methods for 3D crack propagation problems using XFEM

Autores: S. Bakalakos, M. Georgioudakis, M. Papadrakakis
Publicado en: Computer Methods in Applied Mechanics and Engineering, Edición 00457825, 2022, ISSN 0045-7825
Editor: Elsevier BV
DOI: 10.1016/j.cma.2022.115390

Fusing nonlinear solvers with transformers for accelerating the solution of parametric transient problems

Autores: Leonidas Papadopoulos, Konstantinos Atzarakis, Gerasimos Sotiropoulos, Ioannis Kalogeris, Vissarion Papadopoulos
Publicado en: Computer Methods in Applied Mechanics and Engineering, Edición 428, 2024, Página(s) 117074, ISSN 0045-7825
Editor: Elsevier BV
DOI: 10.1016/j.cma.2024.117074

An efficient hierarchical Bayesian framework for multiscale material modeling

Autores: Stefanos Pyrialakos, Ioannis Kalogeris, Vissarion Papadopoulos
Publicado en: Composite Structures, Edición 351, 2024, Página(s) 118570, ISSN 0263-8223
Editor: Elsevier BV
DOI: 10.1016/j.compstruct.2024.118570

Generative Learning of the Solution of Parametric Partial Differential Equations using Guided Diffusion Models and Virtual Observations

Autores: H. Gao, S. Kaltenbach, P. Koumoutsakos
Publicado en: arXiv, 2025, ISSN 2331-8422
Editor: Cornell University
DOI: 10.48550/arxiv.2408.00157

Predictive surrogates for Aerodynamic Performance of Wind Propulsion System Configurations

Autores: M. Reche-Vilanova, S. Kaltenbach, P. Koumoutsakos, H.B. Bingham, M. Fluck, D. Morris, H.N. Psaraftis
Publicado en: Applied Ocean Research, 2025, ISSN 0141-1187
Editor: Pergamon Press Ltd.

Learn-Morph-Infer: A new way of solving the inverse problem for brain tumor modeling

Autores: Ivan Ezhov, Kevin Scibilia, Katharina Franitza, Felix Steinbauer, Suprosanna Shit, Lucas Zimmer, Jana Lipkova, Florian Kofler, Johannes C. Paetzold, Luca Canalini, Diana Waldmannstetter, Martin J. Menten, Marie Metz, Benedikt Wiestler, Bjoern Menze
Publicado en: Medical Image Analysis, Edición 83, 2024, Página(s) 102672, ISSN 1361-8415
Editor: Elsevier BV
DOI: 10.1016/j.media.2022.102672

Generative Learning for the Effective Dynamics of Complex High-dimensional Systems

Autores: H. Gao, S. Kaltenbach, P. Koumoutsakos
Publicado en: Nature Communications, 2025, ISSN 2041-1723
Editor: Nature Publishing Group
DOI: 10.48550/arxiv.2402.17157

Individualizing Glioma Radiotherapy planning by Optimization of a Data and Physics-Informed Discrete Loss

Autores: M. Balcerak, J. Weidner, P. Karnakov, I. Ezhov, S. Litvinov, P. Koumoutsakos, R.Z. Zhang, J.S. Lowengrub, I. Yakushev, B. Wiestler, B. Menze
Publicado en: arXiv, 2025, ISSN 2331-8422
Editor: Cornell University

The stress-free state of human erythrocytes: Data-driven inference of a transferable RBC model

Autores: Lucas Amoudruz, Athena Economides, Georgios Arampatzis, Petros Koumoutsakos
Publicado en: Biophysical Journal, Edición 122, 2024, Página(s) 1517-1525, ISSN 0006-3495
Editor: Biophysical Society
DOI: 10.1016/j.bpj.2023.03.019

Interpretable reduced-order modeling with time-scale separation

Autores: S. Kaltenbach, P.S. Koutsourelakis, P. Koumoutsakos
Publicado en: arXiv, 2025, ISSN 2331-8422
Editor: Cornell University
DOI: 10.48550/arxiv.2303.02189

A learnable prior improves inverse tumor growth modeling

Autores: J. Weidner, I. Ezhov, M. Metz, S. Litvinov, S. Kaltenbach, M. Balcerak, L. Feiner, L. Lux, F. Kofler, J. Lipkova, J. latz, D. Rueckert, B. Menze, B. Wiestler
Publicado en: arxiv, 2025, ISSN 2331-8422
Editor: Cornell University
DOI: 10.48550/arxiv.2403.04500

An adaptive semi‐implicit finite element solver for brain cancer progression modeling

Autores: Konstantinos Tzirakis, Christos Panagiotis Papanikas, Vangelis Sakkalis, Eleftheria Tzamali, Yannis Papaharilaou, Alfonso Caiazzo, Triantafyllos Stylianopoulos, Vasileios Vavourakis
Publicado en: International Journal for Numerical Methods in Biomedical Engineering, Edición 39, 2023, ISSN 2040-7939
Editor: John Wiley & Sons Ltd.
DOI: 10.1002/cnm.3734

Conference proceedings (2)

Improving the accuracy of Coarse-grained Partial Differential Equations with Grid-based Reinforcement Learning

Autores: JP. von Bassewitz, S. Kaltenbach, P. Koumoutsakos
Publicado en: 2024
Editor: ICML-AI4Science

A for-loop is all you need. For solving the inverse problem in the case of personalized tumor growth modeling

Autores: I. Ezhov, M. Rosier, L. Zimmer, F. Kofler, S. Shit, J.C. Paetzold, K. Scibilia, F. Steinbauer, L. Maechler, K. Franitza, T. Amiranashvili, M.J. Menten, M. Metz, S. Conjeti, B. Wiestler, B. Menze
Publicado en: Proceedings of Machine Learning Research, Edición 193, 2022, Página(s) 566-577
Editor: Machine Learning for Health