Recent works & publication list

Parameterized VAE-transformer ROM diagram

Efficient adaptation of ROMs for unsteady flows using data assimilation

This paper proposes an efficient retraining strategy for parameterized reduced-order models, which adapts a variational autoencoder and transformer architecture to out-of-sample flow regimes from sparse observations.

Latent attention on masked patches for flow reconstruction (LAMP)

This paper introduces LAMP, an interpretable regression-based vision transformer that reconstructs full flow fields from heavily masked and noisy inputs, and yields optimal sensor-placement maps.

Real-time forecasting of chaotic dynamics from sparse data and autoencoders

This paper introduces DA-MIRL, a novel framework that integrates sequential DA with off-policy RL to estimate and control high-dimensional, spatio-temporal chaos using only partial and noisy observations..

Data-assimilated model-informed reinforcement learning (DA-MIRL)

A real-time digital twin of azimuthal thermoacoustic instabilities

This paper develops novel methods to infer unknown unknowns in complex dynamical systems using data assimilation techniques.

Inferring unknown unknowns

This paper develops novel methods to infer unknown unknowns in complex dynamical systems using data assimilation techniques.

Complete list of publications

Year	Publication	Journal
2026	A wall-based, interpretable reduced-order model for real-time estimation of near-wall turbulence _{Pérez Cuadrado, Cavallazzi, Nóvoa and Pinelli}	Under review
2026	Transferable inference of turbulence models for urban flows with the Parameter-Regularised Ensemble Kalman Filter _{Bombardi, Nóvoa, Magri and Parente}	Under review
2026	Latent attention on masked patches for flow reconstruction _{Eze, Magri and Nóvoa}	ICCS Lecture Notes in Computer Science _{Workshops, pp. 181–188}
2026	Efficient adaptation of ROMs for unsteady flows using data assimilation _{Zighed, Nóvoa, Magri and Sayadi}	Computers & Fluids ₁₀₇₂₅₀
2026	Real-time forecasting of chaotic dynamics from sparse data and autoencoders _{Özalp, Nóvoa and Magri}	Computer Methods in Applied Mechanics and Engineering _{450, 118600}
2025	Data-assimilated model-informed reinforcement learning _{Ozan, Nóvoa, Rigas and Magri}	Proc. of the Royal Society A _{481(2327): 20250476}
2025	Online model learning with data-assimilated reservoir computers _{Nóvoa and Magri}	ICCS Lecture Notes in Computer Science _{Vol. 15910, pp. 57–64}
2025	Data-assimilated model-based reinforcement learning for partially observed chaotic flows _{Ozan, Nóvoa and Magri}	ICCS Lecture Notes in Computer Science _{Vol. 15910, pp. 65–72}
2024	Real-time digital twins of multiphysics and turbulent flows _{Nóvoa and Magri}	Proceedings of the Center for Turbulence Research Summer Program _{pp. 207-216}
2024	A real-time digital twin of azimuthal thermoacoustic instabilities _{Nóvoa, Noiray, Dawson and Magri}	Journal of Fluid Mechanics _{1001, A49}
2024	Prediction of chaotic dynamics from data: An introduction _{Magri, Nóvoa and Özalp}	Book chapter in: Machine Learning for Fluid Mechanics _{Ed. by M. A. Mendez and A. Parente, von Karman Institute for Fluid Dynamics, 2025}
2023	Inferring unknown unknowns: regularized bias-aware ensemble Kalman filter _{Nóvoa, Racca and Magri}	Computer Methods in Applied Mechanics and Engineering _{418, 116502}
2022	Real-time thermoacoustic data assimilation _{Nóvoa and Magri}	Journal of Fluid Mechanics _{948, A35}
2022	Bias-aware thermoacoustic data assimilation _{Nóvoa, Racca and Magri}	Proceedings of the 51st InterNoise Conference _{pp. 1924-1931(8)}
2021	Fully automated methodology for the delineation of railway lanes and the generation of IFC alignment models using 3D point cloud data _{Soilán, Nóvoa, Sánchez-Rodríguez, Justo and Riveiro}	Automation in Construction _{126, 103684}
2020	Semantic segmentation of point clouds with PointNet and KPConv architectures applied to railway tunnels _{Soilán, Nóvoa, Sánchez-Rodríguez, Riveiro and Arias}	The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences _{V-2-2020, pp. 281-288}