a project to join

I coordinate a research group focusing on designing and implementing software tools for the automated analysis and development of digital twins. We exercised our tools in many disparate domains: aerospace, systems biology, healthcare, medicine, and critical infrastructures. We can provide expertise in software engineering, AI-based optimization, AI-based search for worst-case scenarios, model identification, and parameter estimation (e.g., linking models to experimental data), development of (physics-informed) data-driven models (e.g. using Machine Learning techniques), development of Surrogate Models (e.g., to speed-up simulation).

Publications (full list on Google Scholar)

- M. Esposito, T. Mancini, E. Tronci, Optimizing Fault-Tolerant Quality-Guaranteed Sensor Deployments for UAV Localization in Critical Areas via Computational Geometry. IEEE Trans. on Systems, Man, and Cybernetics: Systems, 2023.

- T. Mancini, I. Melatti and E. Tronci. Optimizing Highly-Parallel Simulation-Based Verification of Cyber-Physical Systems. IEEE Trans. on Software Engineering, 2023.

- S Sinisi, V Alimguzhin, T Mancini, E Tronci, B Leeners, Complete populations of virtual patients for in silico clinical trials, Bioinformatics, 2020.

- F Maggioli, T Mancini, E Tronci, SBML2Modelica: integrating biochemical models within open-standard simulation ecosystems, Bioinformatics, 2020.

List of research projects available at: mclab.di.uniroma1.it

PA1 - Digital Twins of the Oceans (DTO) at regional sub basin scale
PA2 - Blue economy sectors, development of marine multi-use infrastructures
PA3 - Planning and managing sea-uses at the regional level
PA4 - Blue Bioresources

As a project partner, we can:
1) Work with domain experts in the development of digital twins by providing know-how on mathematics, computer science, Artificial Intelligence (AI), Machine Learning (ML).
2) Work with domain experts in developing Physics-Informed data-driven models (e.g., through AI and ML).
3) Carry out parameter estimation for large-scale models, possibly using High-Performance Computing (HPC).
4) Carry out simulation-based optimization with respect to given KPI (Key Performance Indicators).
5) Carry out a search for worst-case scenarios through AI-driven simulation.
6) Development of simulation-based software tools.

digital twin, simulation, physics-informed data-driven models, artificial intelligence, machine learning, surrogate models, optimization, worst-case analysis, software engineering, parameter estimation.

Just send an email to tronci@di.uniroma1.it