Search Results for author: Luca Magri

Found 38 papers, 7 papers with code

On the Usage of the Trifocal Tensor in Motion Segmentation

1 code implementation ECCV 2020 Federica Arrigoni, Luca Magri, Tomas Pajdla

Motion segmentation, i. e., the problem of clustering data in multiple images based on different 3D motions, is an important task for reconstructing and understanding dynamic scenes.

Clustering Motion Segmentation +1

Manifold-augmented Eikonal Equations: Geodesic Distances and Flows on Differentiable Manifolds

1 code implementation9 Oct 2023 Daniel Kelshaw, Luca Magri

Manifolds discovered by machine learning models provide a compact representation of the underlying data.

Control-aware echo state networks (Ca-ESN) for the suppression of extreme events

no code implementations6 Aug 2023 Alberto Racca, Luca Magri

Extreme event are sudden large-amplitude changes in the state or observables of chaotic nonlinear systems, which characterize many scientific phenomena.

Model Predictive Control

Super-resolving sparse observations in partial differential equations: A physics-constrained convolutional neural network approach

no code implementations19 Jun 2023 Daniel Kelshaw, Luca Magri

We propose the physics-constrained convolutional neural network (PC-CNN) to infer the high-resolution solution from sparse observations of spatiotemporal and nonlinear partial differential equations.

Super-Resolution

Uncovering solutions from data corrupted by systematic errors: A physics-constrained convolutional neural network approach

no code implementations7 Jun 2023 Daniel Kelshaw, Luca Magri

We show that the solutions inferred from the PC-CNN are physical, in contrast to the data corrupted by systematic errors that does not fulfil the governing equations.

A machine learning approach to the prediction of heat-transfer coefficients in micro-channels

no code implementations28 May 2023 Tullio Traverso, Francesco Coletti, Luca Magri, Tassos G. Karayiannis, Omar K. Matar

The accurate prediction of the two-phase heat transfer coefficient (HTC) as a function of working fluids, channel geometries and process conditions is key to the optimal design and operation of compact heat exchangers.

GPR regression

Short and Straight: Geodesics on Differentiable Manifolds

no code implementations24 May 2023 Daniel Kelshaw, Luca Magri

Geodesics on these manifolds define locally length-minimising curves and provide a notion of distance, which are key for reduced-order modelling, statistical inference, and interpolation.

valid

Reconstruction, forecasting, and stability of chaotic dynamics from partial data

no code implementations24 May 2023 Elise Özalp, Georgios Margazoglou, Luca Magri

The forecasting and computation of the stability of chaotic systems from partial observations are tasks for which traditional equation-based methods may not be suitable.

Physics-Informed Long Short-Term Memory for Forecasting and Reconstruction of Chaos

no code implementations3 Feb 2023 Elise Özalp, Georgios Margazoglou, Luca Magri

We present the Physics-Informed Long Short-Term Memory (PI-LSTM) network to reconstruct and predict the evolution of unmeasured variables in a chaotic system.

Convolutional autoencoder for the spatiotemporal latent representation of turbulence

no code implementations31 Jan 2023 Nguyen Anh Khoa Doan, Alberto Racca, Luca Magri

The goal of this paper is to obtain an efficient and accurate reduced-order latent representation of a turbulent flow that exhibits extreme events.

Multi-body Depth and Camera Pose Estimation from Multiple Views

no code implementations ICCV 2023 Andrea Porfiri Dal Cin, Giacomo Boracchi, Luca Magri

Traditional and deep Structure-from-Motion (SfM) methods typically operate under the assumption that the scene is rigid, i. e., the environment is static or consists of a single moving object.

Depth Estimation Pose Estimation

Modelling spatiotemporal turbulent dynamics with the convolutional autoencoder echo state network

no code implementations21 Nov 2022 Alberto Racca, Nguyen Anh Khoa Doan, Luca Magri

The overarching objective of this paper is to propose a nonlinear decomposition of the turbulent state for a reduced-order representation of the dynamics.

On interpretability and proper latent decomposition of autoencoders

no code implementations15 Nov 2022 Luca Magri, Anh Khoa Doan

This decomposition finds the dominant directions in the curved latent space.

Physics-Informed CNNs for Super-Resolution of Sparse Observations on Dynamical Systems

1 code implementation31 Oct 2022 Daniel Kelshaw, Georgios Rigas, Luca Magri

In the absence of high-resolution samples, super-resolution of sparse observations on dynamical systems is a challenging problem with wide-reaching applications in experimental settings.

Super-Resolution

Physics-Informed Convolutional Neural Networks for Corruption Removal on Dynamical Systems

1 code implementation28 Oct 2022 Daniel Kelshaw, Luca Magri

Measurements on dynamical systems, experimental or otherwise, are often subjected to inaccuracies capable of introducing corruption; removal of which is a problem of fundamental importance in the physical sciences.

A physics-based domain adaptation framework for modelling and forecasting building energy systems

no code implementations19 Aug 2022 Zack Xuereb Conti, Ruchi Choudhary, Luca Magri

In this initial exploration, we evaluate the physics-based SDA framework on a demonstrative heat conduction scenario by varying the thermophysical properties of the source and target systems to demonstrate the transferability of mechanistic models from a physics-based domain to a data domain.

Domain Adaptation energy management +2

Data-driven prediction and control of extreme events in a chaotic flow

no code implementations25 Apr 2022 Alberto Racca, Luca Magri

We show that echo state networks are able to predict extreme events well beyond the predictability time, i. e., up to more than five Lyapunov times.

Binary Classification Time Series Analysis

Statistical prediction of extreme events from small datasets

1 code implementation20 Jan 2022 Alberto Racca, Luca Magri

We asses whether the networks are able to extrapolate from the small imperfect datasets and predict the heavy-tail statistics that describe the events.

Gradient-free optimization of chaotic acoustics with reservoir computing

no code implementations17 Jun 2021 Francisco Huhn, Luca Magri

Third, we find the set of flame parameters that minimize the time-averaged acoustic energy of chaotic oscillations, which are caused by the positive feedback with a heat source, such as a flame in gas turbines or rocket motors.

Short- and long-term prediction of a chaotic flow: A physics-constrained reservoir computing approach

no code implementations15 Feb 2021 Nguyen Anh Khoa Doan, Wolfgang Polifke, Luca Magri

We propose a physics-constrained machine learning method-based on reservoir computing- to time-accurately predict extreme events and long-term velocity statistics in a model of turbulent shear flow.

BIG-bench Machine Learning

Robust Optimization and Validation of Echo State Networks for learning chaotic dynamics

no code implementations9 Feb 2021 Alberto Racca, Luca Magri

The proposed validation strategies, which are based on the dynamical systems properties of chaotic time series, are shown to outperform the state-of-the-art validation strategies.

Bayesian Optimization Robust Design +1

Synchronization of Group-Labelled Multi-Graphs

no code implementations ICCV 2021 Andrea Porfiri Dal Cin, Luca Magri, Federica Arrigoni, Andrea Fusiello, Giacomo Boracchi

MultiSynch is a general solution that can cope with any linear group and we show to be profitably usable both on synthetic and real problems.

Automatic-differentiated Physics-Informed Echo State Network (API-ESN)

no code implementations28 Dec 2020 Alberto Racca, Luca Magri

The network is showcased in the reconstruction of unmeasured (hidden) states of a chaotic system.

Auto-Encoded Reservoir Computing for Turbulence Learning

no code implementations20 Dec 2020 Nguyen Anh Khoa Doan, Wolfgang Polifke, Luca Magri

We present an Auto-Encoded Reservoir-Computing (AE-RC) approach to learn the dynamics of a 2D turbulent flow.

BIG-bench Machine Learning

Physics-Informed Echo State Networks

no code implementations31 Oct 2020 Nguyen Anh Khoa Doan, Wolfgang Polifke, Luca Magri

This approach is demonstrated on a chaotic Lorenz system and a truncation of the Charney-DeVore system.

First-principles machine learning modelling of COVID-19

1 code implementation20 Apr 2020 Luca Magri, Nguyen Anh Khoa Doan

The coronavirus disease 2019 (COVID-19) has changed the world since the World Health Organization declared its outbreak on 30th January 2020, recognizing the outbreak as a pandemic on 11th March 2020.

Populations and Evolution

Learning ergodic averages in chaotic systems

no code implementations9 Jan 2020 Francisco Huhn, Luca Magri

We propose a physics-informed machine learning method to predict the time average of a chaotic attractor.

BIG-bench Machine Learning Physics-informed machine learning

Learning Hidden States in a Chaotic System: A Physics-Informed Echo State Network Approach

no code implementations6 Jan 2020 Nguyen Anh Khoa Doan, Wolfgang Polifke, Luca Magri

We extend the Physics-Informed Echo State Network (PI-ESN) framework to reconstruct the evolution of an unmeasured state (hidden state) in a chaotic system.

A physics-aware machine to predict extreme events in turbulence

no code implementations23 Dec 2019 Nguyen Anh Khoa Doan, Wolfgang Polifke, Luca Magri

We propose a physics-aware machine learning method to time-accurately predict extreme events in a turbulent flow.

Fitting Multiple Heterogeneous Models by Multi-Class Cascaded T-Linkage

no code implementations CVPR 2019 Luca Magri, Andrea Fusiello

This paper addresses the problem of multiple models fitting in the general context where the sought structures can be described by a mixture of heterogeneous parametric models drawn from different classes.

Model Selection

Physics-Informed Echo State Networks for Chaotic Systems Forecasting

no code implementations9 Apr 2019 Nguyen Anh Khoa Doan, Wolfgang Polifke, Luca Magri

We propose a physics-informed Echo State Network (ESN) to predict the evolution of chaotic systems.

Data assimilation in a nonlinear time-delayed dynamical system

no code implementations9 Apr 2019 Tullio Traverso, Luca Magri

Reduced-order thermoacoustic models, which are nonlinear and time-delayed, can only qualitatively predict thermoacoustic oscillations.

Combined State and Parameter Estimation in Level-Set Methods

no code implementations1 Mar 2019 Hans Yu, Matthew P. Juniper, Luca Magri

Reduced-order models based on level-set methods are widely used tools to qualitatively capture and track the nonlinear dynamics of an interface.

Uncertainty Quantification

Multiple Model Fitting as a Set Coverage Problem

no code implementations CVPR 2016 Luca Magri, Andrea Fusiello

This paper deals with the extraction of multiple models from noisy or outlier-contaminated data.

Clustering

T-Linkage: A Continuous Relaxation of J-Linkage for Multi-Model Fitting

no code implementations CVPR 2014 Luca Magri, Andrea Fusiello

This paper presents an improvement of the J-linkage algorithm for fitting multiple instances of a model to noisy data corrupted by outliers.

Cannot find the paper you are looking for? You can Submit a new open access paper.