Filippo Aglietti is a Machine learning Technical Leader at Dumarey Automotive Italia SpA
Filippo Aglietti graduated in Automotive Engineering from Politecnico di Torino in 2017. He joined Dumarey Automotive Italia (formerly General Motors), where he has worked as an Analysis Engineer focusing on 1D-CFD engine performance simulations. In 2022, he started an industrial PhD centered on scientific machine-learning for diesel engine emissions prediction. Since 2025, he is Technical Leader for the development of machine-learning models applied to physical systems.
What is your motivation to join DT-HATS?
The DT-HATS project plays a key role in advancing next-generation propulsion technologies by combining high-fidelity simulation with data-driven modelling. Working on a digital twin for NH₃–H₂ combustion contributes concretely to the development of low-carbon mobility solutions. I was motivated to join this research to help shape innovative digital-twin architectures, integrating real data and reduced-order models to support robust engineering decisions and the design of sustainable combustion systems.
Aglietti, F., Della Santa, F., Piano, A., Aglietti, V. “Gradient-Informed Neural Networks: Embedding Prior Beliefs for Learning in Low-Data Scenarios”. Neural Networks, 2026, Article 108681. https://doi.org/10.1016/j.neunet.2026.108681
Aglietti, F., Piano, A., Della Santa, F., Capra, A., Centini, M. P., Rimondi, M., Millo, F. “A Novel Prior-Informed Machine Learning Model for Diesel Engine Emission Estimation”. Fuel, 2026, Article 137435. https://doi.org/10.1016/j.fuel.2025.137435
Sapio, F., Aglietti, F., Ferreri, P., Savuca, A. “Neural-Network-Based Modeling of SCR Systems for Emission Simulation: A Comprehensive Approach”. SAE International Journal of Advances and Current Practices in Mobility, 7(3):1437–1452, 2025. https://doi.org/10.4271/2024-24-0042
Credo, G., Taddeo, V., Aglietti, F. “Artificial Neural Network for Airborne Noise Prediction of a Diesel Engine”. SAE Technical Paper, 2024-01-2929, 2024. https://doi.org/10.4271/2024-01-2929