Educational Background

• 2016 Ph.D. in Mathematics, cum laude, University of Trento, Italy
• 2013 M.S. in Mathematics, University of Trento, Italy
• 2010 B.S. in Mathematics, University of Milano-Bicocca, Italy

Employment History

• 2026 - Present: Assistant Professor, Department of Civil and Environmental Engineering, Louisiana State University
• 2025 - 2026: Senior Adjunct Researcher, Trento Institute for Fundamental Physics and Applications (TIFPA), Italian National Institute for Nuclear Physics (INFN)
• 2024 - 2026: Associate Professor, Department of Civil, Environmental and Mechanical Engineering, University of Trento, Italy
• 2021 - 2024: Assistant Professor, Department of Civil, Environmental and Mechanical Engineering, University of Trento, Italy

Research Interests

My research focuses on mathematical and computational modeling of complex physical and biological systems, combining stochastic processes, mechanistic models, numerical simulations, and artificial intelligence. I am particularly interested in understanding how microscopic interactions and stochastic dynamics determine the macroscopic behavior of complex systems, with applications ranging from biological materials to mechanical and engineering systems.

A central direction of my research is scientific machine learning (SciML), integrating mathematical models with modern AI techniques to develop fast, accurate, and physically grounded predictive tools. My work includes multiscale and stochastic partial differential equations, agent-based models, neural operators, generative AI, and physics-informed learning. These approaches aim to accelerate computationally demanding simulations while preserving essential physical mechanisms, enabling uncertainty quantification, model discovery, and optimization.

My research also includes stochastic dynamical systems, stochastic port-Hamiltonian systems, and optimal control, with applications to mechanical systems, robotics, and interconnected physical processes. In biological applications, I develop multiscale models of radiation-induced damage and cellular response, connecting microscopic physical and chemical processes to tissue-level outcomes. The underlying mathematical and AI-based approaches are broadly applicable to material damage and degradation, predictive digital twins, and complex engineering systems.

Research Areas

• Stochastic differential equations and multiscale mathematical modeling
• Scientific machine learning and physics-informed artificial intelligence
• Neural operators, generative models, and AI-based surrogate modeling
• Agent-based modeling and stochastic interacting particle systems
• Stochastic mechanics, port-Hamiltonian systems, and optimal control
• High-dimensional and stiff partial differential equations
• Mathematical modeling of biological materials and radiation-induced damage
• Uncertainty quantification, model discovery, and predictive digital twins

Selected Research Projects

Stochastic Particle-Based Anomalous Reaction-Diffusion Models with Heterogeneous Interaction for Radiation Therapy

Principal Investigator - PRIN 2022 PNRR
Total funding: €222,591

Development of stochastic and multiscale mathematical models to investigate interacting particle systems, reaction-diffusion processes, and their applications to radiation-induced biological effects.

Towards Genomic Adjusted Particle Therapy

Principal Investigator - Italian National Institute for Nuclear Physics (INFN)
Total funding: €200,000

Integration of mathematical modeling, radiation biophysics, and biological data to investigate radiation-induced damage and support the development of more personalized particle therapy approaches.

Sex Differences in Chromosomal Aberrations in Peripheral Blood Lymphocytes Exposed to Galactic Cosmic Radiation: A Microdosimetric and Mathematical Mechanistic Approach

Principal Investigator - European Space Agency (ESA-IBPER)

Development of mechanistic and microdosimetric models to investigate the biological effects of galactic cosmic radiation, supported by experimental irradiation studies.

Selected Publications

Stochastic Mechanics and Port-Hamiltonian Systems

• F. G. Cordoni, L. Di Persio, and R. Muradore. Stochastic Port-Hamiltonian Systems. Journal of Nonlinear Science, 32, 91 (2022).
• F. G. Cordoni, L. Di Persio, and R. Muradore. Weak energy shaping for stochastic port-Hamiltonian systems. SIAM Journal on Control and Optimization, 61(5), 2902–2926 (2023).
• F. G. Cordoni, L. Di Persio, and R. Muradore. Discrete stochastic port-Hamiltonian systems. Automatica, 137, 110122 (2022).
• F. G. Cordoni, L. Di Persio, and R. Muradore. On the relationship between stochastic and deterministic energy shaping techniques for stochastic port-Hamiltonian systems via invariant measure characterization. Automatica, 179, 112385 (2025).

Multiscale Modeling and Radiation Biophysics

• F. G. Cordoni et al. The Generalized Stochastic Microdosimetric Model: The Main Formulation. Physical Review E, 103 (2021).
• F. G. Cordoni. A spatial measure-valued model for radiation-induced DNA damage kinetics and repair under protracted irradiation condition. Journal of Mathematical Biology, 88, 21 (2024).
• M. Battestini et al., F. G. Cordoni (corresponding author), and E. Scifoni. A multiscale radiation biophysical stochastic model describing the cell survival response at ultra-high dose rate over a broad LET, particle type and oxygenation range. Radiotherapy and Oncology, 207, 110895 (2025).
• G. Bordieri et al., F. G. Cordoni (corresponding author). Integrating nano- and micrometer-scale energy deposition models for mechanistic prediction of radiation-induced DNA damage and cell survival. Computers in Biology and Medicine, 199, 111330 (2025).

Artificial Intelligence and Scientific Machine Learning

• F. G. Cordoni et al. An Artificial Intelligence-based model for cell killing prediction: development, validation and explainability analysis of the ANAKIN model. Physics in Medicine & Biology, 68, 085017 (2023).
• F. G. Cordoni et al. A multi-modal unsupervised fault detection system based on power signals and thermal imaging via deep AutoEncoder neural network. Engineering Applications of Artificial Intelligence, 110, 104729 (2022).
• G. Bordieri et al., F. G. Cordoni. One scale to rule them all: interpretable multi-scale Deep Learning for predicting cell survival after proton and carbon ion irradiation. Frontiers in Artificial Intelligence, 9, 1807677 (2026).
• F. G. Cordoni, G. Bacchiega, G. Bondani, R. Radu, and R. Muradore. A deep learning approach for fault detection and fault diagnosis in household appliances. IFAC-PapersOnLine, 53(2), 10749–10754 (2020).

Stochastic Differential Equations and Mathematical Modeling

• F. G. Cordoni, L. Di Persio, L. Maticiuc, and A. Zălinescu. A stochastic approach for path-dependent nonlinear Kolmogorov equations via BSDEs with time-delayed generators. Stochastic Processes and Their Applications, 130(3), 1669–1712 (2020).
• F. G. Cordoni, L. Di Persio, and I. Oliva. A nonlinear Kolmogorov equation for stochastic functional delay differential equations with jumps. Nonlinear Differential Equations and Applications, 24, 16 (2017).
• D. Banos, F. G. Cordoni, G. Di Nunno, L. Di Persio, and E. Rose. Stochastic system with memory and jumps. Journal of Differential Equations (2019).
• F. G. Cordoni and L. Di Persio. Optimal control of the FitzHugh–Nagumo stochastic model with nonlinear diffusion. Applied Mathematics & Optimization (2021).

Additional Professional Experience

Cordoni co-founded HPA s.r.l., an AI and predictive analytics startup that developed machine learning solutions for industrial and commercial applications. His work included probabilistic forecasting for energy markets, predictive maintenance, fault detection, and AI-based modeling of industrial systems.

His research has involved collaborations with academic institutions, research laboratories, medical centers, and industrial partners across Europe and the United States, combining mathematical theory, computational methods, and experimental data to address complex scientific and engineering challenges.