arXiv subjects

Patricio Clark Di Leoni

Publications and source records attributed to Patricio Clark Di Leoni.

7 recordsLinked to original sources

arXiv2026

Estimating bottom topography in shallow water flows

We present two methods to estimate bottom topography in a shallow water flow using only surface deformation measurements. One is based on Physics-Informed Neural Networks (PINNs) and the other on the Adjoint State Method. We test both methods using synthetic data in 1D and 2D cases. Both are able to successfully reconstruct not only the bottom topography but also the surface velocity. Both also show robustness against noise and data sparsity up to reasonable levels.

physics.flu-dyn↗

arXiv2023

Reconstructing Rayleigh-Benard flows out of temperature-only measurements using Physics-Informed Neural Networks

We investigate the capabilities of Physics-Informed Neural Networks (PINNs) to reconstruct turbulent Rayleigh-Benard flows using only temperature information. We perform a quantitative analysis of the quality of the reconstructions at various amounts of low-passed-filtered information and turbulent intensities. We compare our results with those obtained via nudging, a classical equation-informed data assimilation technique. At low Rayleigh numbers, PINNs are able to reconstruct with high precision, comparable to the one achieved with nudging. At high Rayleigh numbers, PINNs outperform nudging and are able to achieve satisfactory reconstruction of the velocity fields only when data for temperature is provided with high spatial and temporal density. When data becomes sparse, the PINNs performance worsens, not only in a point-to-point error sense but also, and contrary to nudging, in a statistical sense, as can be seen in the probability density functions and energy spectra.

physics.flu-dyn↗

arXiv2022

Reconstructing velocity and pressure from sparse noisy particle tracks using Physics-Informed Neural Networks

Volume-resolving imaging techniques are rapidly advancing progress in experimental fluid mechanics. However, reconstructing the full and structured Eulerian velocity and pressure fields from sparse and noisy particle tracks obtained experimentally remains a significant challenge. We introduce a new method for this reconstruction, based on Physics-Informed Neural Networks (PINNs). The method uses a Neural Network regularized by the Navier-Stokes equations to interpolate the velocity data and simultaneously determine the pressure field. We compare this approach to the state-of-the-art Constrained Cost Minimization method [1]. Using data from direct numerical simulations and various types of synthetically generated particle tracks, we show that PINNs are able to accurately reconstruct both velocity and pressure even in regions with low particle density and small accelerations. PINNs are also robust against increasing the distance between particles and the noise in the measurements, when studied under synthetic and experimental conditions.

physics.flu-dyn↗

arXiv2022

Generation of Turbulent States using Physics-Informed Neural Networks

When modelling turbulent flows, it is often the case that information on the forcing terms or the boundary conditions is either not available or overly complicated and expensive to implement. Instead, some flow features, such as the mean velocity profile or its statistical moments, may be accessible through experiments or observations. We present a method based on physics-informed neural networks to generate turbulent states subject to a set of given conditions. The physics-informed method ensures the final state approximates a valid flow. We show examples of different statistical conditions that can be used to prepare states, motivated by experimental and atmospheric problems. Lastly, we show two ways of scaling the resolution of the prepared states. One is through the use of multiple and parallel neural networks. The other uses nudging, a synchronization-based data assimilation technique that leverages the power of specialized numerical solvers.

physics.flu-dyn↗

arXiv2022

Reconstructing Rayleigh-Bénard flows out of temperature-only measurements using nudging

Nudging is a data assimilation technique that has proved to be capable of reconstructing several highly turbulent flows from a set of partial spatiotemporal measurements. In this study we apply the nudging protocol on the temperature field in a Rayleigh-Bénard Convection system at varying levels of turbulence. We assess the global, as well as scale by scale, success in reconstructing the flow and the transition to full synchronization while varying both the quantity and quality of the information provided by the sparse measurements either on the Eulerian or Lagrangian domain. We asses the statistical reproduction of the dynamic behaviour of the system by studying the spectra of the nudged fields as well as the correct prediction of the heat transfer properties as measured by the Nusselt number. Further, we analyze the results in terms of the complexity of the solutions at various Rayleigh numbers and discuss the more general problem of predicting all state variables of a system given partial or full measurements of only one subset of the fields, in particular temperature. This study sheds new light on the correlation between velocity and temperature in thermally driven flows and on the possibility to control them by acting on the temperature only.

physics.flu-dyn↗

arXiv2020

Physics-informed neural network for ultrasound nondestructive quantification of surface breaking cracks

We introduce an optimized physics-informed neural network (PINN) trained to solve the problem of identifying and characterizing a surface breaking crack in a metal plate. PINNs are neural networks that can combine data and physics in the learning process by adding the residuals of a system of Partial Differential Equations to the loss function. Our PINN is supervised with realistic ultrasonic surface acoustic wave data acquired at a frequency of 5 MHz. The ultrasonic surface wave data is represented as a surface deformation on the top surface of a metal plate, measured by using the method of laser vibrometry. The PINN is physically informed by the acoustic wave equation and its convergence is sped up using adaptive activation functions. The adaptive activation function uses a scalable hyperparameter in the activation function, which is optimized to achieve best performance of the network as it changes dynamically the topology of the loss function involved in the optimization process. The usage of adaptive activation function significantly improves the convergence, notably observed in the current study. We use PINNs to estimate the speed of sound of the metal plate, which we do with an error of 1\%, and then, by allowing the speed of sound to be space dependent, we identify and characterize the crack as the positions where the speed of sound has decreased. Our study also shows the effect of sub-sampling of the data on the sensitivity of sound speed estimates. More broadly, the resulting model shows a promising deep neural network model for ill-posed inverse problems.

cs.LG↗

arXiv2019

Zermelo's problem: Optimal point-to-point navigation in 2D turbulent flows using Reinforcement Learning

To find the path that minimizes the time to navigate between two given points in a fluid flow is known as Zermelo's problem. Here, we investigate it by using a Reinforcement Learning (RL) approach for the case of a vessel which has a slip velocity with fixed intensity, Vs , but variable direction and navigating in a 2D turbulent sea. We show that an Actor-Critic RL algorithm is able to find quasi-optimal solutions for both time-independent and chaotically evolving flow configurations. For the frozen case, we also compared the results with strategies obtained analytically from continuous Optimal Navigation (ON) protocols. We show that for our application, ON solutions are unstable for the typical duration of the navigation process, and are therefore not useful in practice. On the other hand, RL solutions are much more robust with respect to small changes in the initial conditions and to external noise, even when V s is much smaller than the maximum flow velocity. Furthermore, we show how the RL approach is able to take advantage of the flow properties in order to reach the target, especially when the steering speed is small.

nlin.CD↗