As global environmental, urban, and computing challenges expand, traditional computational frameworks frequently hit structural limits. Simulating entire cityscapes, tracing microscale atmospheric pollution, or predicting the flash progression of a wildfire requires massive processing capacity. However, raw power is no longer enough; next-generation engineering demands scalability, transparency, and energy awareness.
As a premier EuroHPC Joint Undertaking Center of Excellence, HiDALGO2 bridges this gap. By co-designing next-generation numerical methods, workflow automation pipelines, and machine learning architectures, our global consortium is unlocking extreme-scale computing for open science.
To help researchers, developers, and policymakers navigate our project milestones, we have consolidated our latest 16 core publications, benchmarks, and open datasets into five interconnected scientific pillars.
Theme I: Urban Digital Twins & Sustainable Infrastructure
Developing viable mitigation plans for modern smart cities requires modeling physical infrastructure at an individual building resolution. HiDALGO2 accelerates this deployment by introducing automated cloud-native engineering into classic supercomputing environments, eliminating manual deployment friction.
1. Automated Building Orchestration: Discover the implementation of continuous integration and continuous deployment (CI/CD) pipelines engineered to push municipal infrastructure simulations directly onto HPC execution nodes.
Read the Chapter Ktirio Urban Building: A Computational Framework for City Energy Simulations Enhanced by CI/CD Innovations on EuroHPC Systems, by Luca Berti, Vincent Chabannes, Gwennolé Chappron, Javier Cladellas, Abdoulaye Diallo, Maryam Maslek Elayam, Philippe Pinçon & Christophe Prud’homme.
https://link.springer.com/chapter/10.1007/978-3-031-85703-4_2
2. Validation Engine Frameworks: Deep dive into the underlying structural configurations and code orchestration layers supporting next-gen urban digital twins.
Read the article “Open-source complex-geometry 3D fluid dynamics for applications with unpredictable heterogeneous dynamic high-performance-computing loads”, by J. Bakosi, Széchenyi Egyetem, University of Győr, Hungary
https://www.sciencedirect.com/science/article/pii/S0045782523007107
– Predicting Shading & Wildfire Behavior (AISYS 2024): Integrating Graph Neural Networks and HPDA to map building-to-building solar masks in Strasbourg and deploy real-time shape-matching algorithms for wildfire propagation front containment
Title: AI for Global Challenges: Case Studies in Urban Solar Exposure & Wildfire Management
Authors: Giorgos Filandrianos, Angeliki Dimitriou, Vasiliki Kostoula, Nikolaos Chalvantzis, David Caballero, Luis Torres, Michal Kulczewski, Javier Cladellas, Zoltán Horváth, Harald Köstler, Konstantinos Nikas, Dimitrios Tsoumakos, Giorgos Stamou
Link: https://www.thinkmind.org/articles/aisys_2024_1_20_88003.pdf
– Antwerp Field Validation (Part A): Microscale dispersion analytics and spatial tracking metrics under FAIRMODE standards.
Title: Estimating the air quality standard exceedance areas and the spatial representativeness of urban air quality stations applying microscale modelling
Authors: F. Martín, V. Rodrigues, J.L. Santiago, J. Sousa, J. Stocker, S. Janssen, R. Jackson, F. Russo, M.G. Villani, G. Tinarelli, D. Barbero, R. San José, J.L. Pérez-Camanyo, G. Sousa-Santos, L. Tarrason, J. Bartzis, I. Sakellaris, Z. Horváth, L. Környei, X. Jurado, P. Thunis
https://www.sciencedirect.com/science/article/pii/S0048969725014652?via%3Dihub
– Exceedance Mapping Profiles (Part B): Using high-resolution computing clusters to isolate city pollution hotspots.
Title: Using dispersion models at microscale to assess long-term air pollution in urban hot spots: A FAIRMODE joint intercomparison exercise for a case study in Antwerp
Authors: F. Martín, S. Janssen, V. Rodrigues, J.Sousa, J.L. Santiago, E.Rivas, J.Stocker, R.Jackson, F.Russo, M.G.Villani, G.Tinarelli, D.Barbero, R.San José, J.L.Pérez-Camanyo, G.Sousa Santos, J.Bartzis, I.Sakellaris, Z.Horváth, L.Környei, B.Liszkai, C.Cuvelier
https://www.sciencedirect.com/science/article/pii/S0048969724019041?via%3Dihub
Theme II: Next-Gen AI Convergence & Explainable Deep Learning Models
The modern computational landscape demands a tight coupling of classic HPC methods with AI workflows. Our consortium focuses on two major friction points: optimising massive Large Language Model execution speeds by bypassing thread execution boundaries and establishing semantic explanation metrics for deep neural visual networks to replace unreliable, traditional black-box analytics.
– LLM Pipeline Bottlenecks: Deconstructing matrix calculations (SpMM/SDDMM) and thread execution structures across multi-core systems.
Title: Breaking Down LLM Inference: A preliminary performance analysis of sparsified transformers
Authors: Ioanna Tasou; Petros Anastasiadis; Panagiotis Mpakos; Dimitrios Galanopoulos; Nectarios Koziris; Georgios Goumas
https://ieeexplore.ieee.org/document/11105852
– Explainable AI (XAI) Architecture: Bypassing graph comparison limitations via semantic explanation trees at ICML.
Title: Structure Your Data: Towards Semantic Graph Counterfactuals, Proceedings of the 41st International Conference on Machine Learning, PMLR 235:10897-10926, 2024.
Authors: Angeliki Dimitriou, Maria Lymperaiou, Georgios Filandrianos, Konstantinos Thomas, Giorgos Stamou
https://proceedings.mlr.press/v235/dimitriou24a.html
Theme III: Advanced CFD Scaling, Energy Optimisation & Asynchronous Run-times
At the centre of extreme computing lies code performance optimisation. HiDALGO2 addresses the real-world operational costs of large clusters by using analytical optimisation equations (like the CVOPTS optimisation metric) alongside task-parallel runtime execution frameworks (such as Xyst and mUQSA) to prevent processing waste across thousand-core infrastructures.
– Wildfire Simulations on EuroHPC Resources: A comprehensive look at the mathematical, computational, and infrastructure challenges of scaling wildfire and smoke propagation models on Europe’s grandest supercomputing clusters.
Title: Simulation of Wildfires Using EuroHPC Resources: Challenges and Opportunities
Authors: David Caballero, Leydi Laura Salazar, Ángela Rivera & Luis Torres
Link: https://link.springer.com/chapter/10.1007/978-3-031-85703-4_1
– Green HPC Modelling: Balancing performance metrics and energy footprints using the predictive CVOPTS tool.
Title: Prediction model of performance–energy trade-off for CFD codes on AMD-based cluster
Authors: Marcin Lawenda, Łukasz Szustak, László Környei
Link: https://www.sciencedirect.com/science/article/abs/pii/S0167739X25001050
– Mathematical Infrastructure Design: Advanced cross-platform parallel portability for multi-scale physical grids.
Title: Partition deactivation with load balancing for parallel flow simulations
Authors: J. Bakosi, Széchenyi Egyetem, University of Győr, Hungary
Link: https://www.sciencedirect.com/science/article/pii/S0021999124006351?via%3Dihub
– Xyst Fluid Dynamics Code: Multi-dimensional compressible flow simulations leveraging Charm++ runtime systems.
Title: Complex-Geometry 3D Computational Fluid Dynamics with Automatic Load Balancing
Authors: József Bakosi, Mátyás Constans, Zoltán Horváth, Ákos Kovács, László Környei, Marc Charest, Aditya Pandare, Paula Rutherford and Jacob Waltz
Link: https://www.mdpi.com/2311-5521/8/5/147
– mUQSA Uncertainty Toolkit: Web-accessible uncertainty quantification systems for complex distributed
architectures.
Title: Fostering Uncertainty Quantification in Global Challenges with mUQSA Toolkit
Authors: Michał Kulczewski, Bartosz Bosak, Piotr Kopta, Wojciech Szeliga & Tomasz Piontek
https://link.springer.com/chapter/10.1007/978-3-031-85703-4_3
– Distributed Simulation Pipelines: Managing validation limits across heterogeneous European supercomputers.
Title: Profiling and Optimisation of Multicard GPU Machine Learning Jobs
Authors: Marcin Lawenda, Kyrylo Khloponin, Krzesimir Samborski, Łukasz Szustak
https://onlinelibrary.wiley.com/doi/10.1002/cpe.70196
– Open Science Verification Hub (Zenodo): Open benchmark profiles and code execution blueprints.
Title: Efficient allocation of image recognition and LLM tasks on multi-GPU system
Authors: Marcin Lawenda, Krzesimir Samborski, Kyrylo Khloponin, Łukasz Szusta
https://zenodo.org/records/15055009
Title: Uncut-GEMMs : Communication-aware matrix multiplication on multi-GPU nodes
Authors: Petros Anastasiadis, Nikela Papadopoulou, Nectarios Koziris and Georgios Goumas
https://zenodo.org/records/14536176
