Urban Fasel
YOU?
Author Swipe
View article: Data-driven discovery and model reduction methods for the atmospheric effects of high altitude emissions
Data-driven discovery and model reduction methods for the atmospheric effects of high altitude emissions Open
Chemistry transport models play a crucial role in the evaluation of the effect of anthropogenic emissions on the atmosphere and climate, but they come with high computational costs and require specialized know-how. This renders them imprac…
View article: HypeMARL: Multi-Agent Reinforcement Learning For High-Dimensional, Parametric, and Distributed Systems
HypeMARL: Multi-Agent Reinforcement Learning For High-Dimensional, Parametric, and Distributed Systems Open
Deep reinforcement learning has recently emerged as a promising feedback control strategy for complex dynamical systems governed by partial differential equations (PDEs). When dealing with distributed, high-dimensional problems in state an…
View article: Sparse Identification of Nonlinear Dynamics with Conformal Prediction
Sparse Identification of Nonlinear Dynamics with Conformal Prediction Open
The Sparse Identification of Nonlinear Dynamics (SINDy) is a method for discovering nonlinear dynamical system models from data. Quantifying uncertainty in SINDy models is essential for assessing their reliability, particularly in safety-c…
View article: SINDy on slow manifolds
SINDy on slow manifolds Open
The sparse identification of nonlinear dynamics (SINDy) has been established as an effective method to learn interpretable models of dynamical systems from data. However, for high-dimensional slow-fast dynamical systems, the regression pro…
View article: Rapid Bayesian identification of sparse nonlinear dynamics from scarce and noisy data
Rapid Bayesian identification of sparse nonlinear dynamics from scarce and noisy data Open
We propose a fast probabilistic framework for identifying differential equations governing the dynamics of observed data. We recast the sparse identification of nonlinear dynamics (SINDy) method within a Bayesian framework and use Gaussian…
View article: Machine Learning for Sparse Nonlinear Modeling and Control
Machine Learning for Sparse Nonlinear Modeling and Control Open
Machine learning is rapidly advancing nearly every field of science and engineering, and control theory is no exception. In particular, it has shown incredible promise for handling several of the main challenges facing modern dynamics and …
View article: Interpretable and efficient data-driven discovery and control of distributed systems
Interpretable and efficient data-driven discovery and control of distributed systems Open
Effectively controlling systems governed by partial differential equations (PDEs) is crucial in several fields of applied sciences and engineering. These systems usually yield significant challenges to conventional control schemes due to t…
View article: Interpretable low-order representation of eigenmode deformation in parameterized dynamical systems
Interpretable low-order representation of eigenmode deformation in parameterized dynamical systems Open
Modal analysis has long been consolidated as a basic tool to interpret dynamics and build low-order models of mechanical, thermal, and fluid systems. Eigenmodes arising from the spectral decomposition of the underlying linearized dynamics …
View article: Interpretable and Efficient Data-driven Discovery and Control of Distributed Systems
Interpretable and Efficient Data-driven Discovery and Control of Distributed Systems Open
Effectively controlling systems governed by Partial Differential Equations (PDEs) is crucial in several fields of Applied Sciences and Engineering. These systems usually yield significant challenges to conventional control schemes due to t…
View article: Sparsifying Parametric Models with L0 Regularization
Sparsifying Parametric Models with L0 Regularization Open
This document contains an educational introduction to the problem of sparsifying parametric models with L0 regularization. We utilize this approach together with dictionary learning to learn sparse polynomial policies for deep reinforcemen…
View article: Parametric PDE Control with Deep Reinforcement Learning and Differentiable L0-Sparse Polynomial Policies
Parametric PDE Control with Deep Reinforcement Learning and Differentiable L0-Sparse Polynomial Policies Open
Optimal control of parametric partial differential equations (PDEs) is crucial in many applications in engineering and science. In recent years, the progress in scientific machine learning has opened up new frontiers for the control of par…
View article: SINDy-RL: Interpretable and Efficient Model-Based Reinforcement Learning
SINDy-RL: Interpretable and Efficient Model-Based Reinforcement Learning Open
Deep reinforcement learning (DRL) has shown significant promise for uncovering sophisticated control policies that interact in complex environments, such as stabilizing a tokamak fusion reactor or minimizing the drag force on an object in …
View article: Rapid Bayesian identification of sparse nonlinear dynamics from scarce and noisy data
Rapid Bayesian identification of sparse nonlinear dynamics from scarce and noisy data Open
We propose a fast probabilistic framework for identifying differential equations governing the dynamics of observed data. We recast the SINDy method within a Bayesian framework and use Gaussian approximations for the prior and likelihood t…
View article: Data-Driven Modeling for Transonic Aeroelastic Analysis
Data-Driven Modeling for Transonic Aeroelastic Analysis Open
Aeroelasticity in the transonic regime is challenging because of the strongly nonlinear phenomena involved in the formation of shock waves and flow separation. In this work, we introduce a computationally efficient framework for accurate t…
View article: Data-Driven Modeling for Transonic Aeroelastic Analysis
Data-Driven Modeling for Transonic Aeroelastic Analysis Open
Aeroelasticity in the transonic regime is challenging because of the strongly nonlinear phenomena involved in the formation of shock waves and flow separation. In this work, we introduce a computationally efficient framework for accurate t…
View article: Benchmarking sparse system identification with low-dimensional chaos
Benchmarking sparse system identification with low-dimensional chaos Open
Sparse system identification is the data-driven process of obtaining parsimonious differential equations that describe the evolution of a dynamical system, balancing model complexity and accuracy. There has been rapid innovation in system …
View article: Convergence of uncertainty estimates in Ensemble and Bayesian sparse model discovery
Convergence of uncertainty estimates in Ensemble and Bayesian sparse model discovery Open
Sparse model identification enables nonlinear dynamical system discovery from data. However, the control of false discoveries for sparse model identification is challenging, especially in the low-data and high-noise limit. In this paper, w…
View article: FlexWing-ROM: A matlab framework for data-drivenreduced-order modeling of flexible wings
FlexWing-ROM: A matlab framework for data-drivenreduced-order modeling of flexible wings Open
Flexible wings pose a considerable modeling challenge, as they involve highly coupled and nonlinear interactions between the aerodynamic and structural dynamics. In this work, we provide an open source code framework, unifying recent data-…
View article: Robust, High-Rate Trajectory Tracking on Insect-Scale Soft-Actuated Aerial Robots with Deep-Learned Tube MPC
Robust, High-Rate Trajectory Tracking on Insect-Scale Soft-Actuated Aerial Robots with Deep-Learned Tube MPC Open
Accurate and agile trajectory tracking in sub-gram Micro Aerial Vehicles (MAVs) is challenging, as the small scale of the robot induces large model uncertainties, demanding robust feedback controllers, while the fast dynamics and computati…
View article: The Experimental Multi-Arm Pendulum on a Cart: A Benchmark System for Chaos, Learning, and Control
The Experimental Multi-Arm Pendulum on a Cart: A Benchmark System for Chaos, Learning, and Control Open
The single, double, and triple pendulum has served as an illustrative experimental benchmark system for scientists to study dynamical behavior for more than four centuries. The pendulum system exhibits a wide range of interesting behaviors…
View article: The Experimental Multi-Arm Pendulum on a Cart: A Benchmark System for Chaos, Learning, and Control
The Experimental Multi-Arm Pendulum on a Cart: A Benchmark System for Chaos, Learning, and Control Open
The single, double, and triple pendulum has served as an illustrative experimental benchmark system for scientists to study dynamical behavior for more than four centuries. The pendulum system exhibits a wide range of interesting behaviors…
View article: The Experimental Multi-Arm Pendulum on a Cart: A Benchmark System for Chaos, Learning, and Control
The Experimental Multi-Arm Pendulum on a Cart: A Benchmark System for Chaos, Learning, and Control Open
The single, double, and triple pendulum has served as an illustrative experimental benchmark system for scientists to study dynamical behavior for more than four centuries. The pendulum system exhibits a wide range of interesting behaviors…
View article: Ensemble-SINDy: Robust sparse model discovery in the low-data, high-noise limit, with active learning and control
Ensemble-SINDy: Robust sparse model discovery in the low-data, high-noise limit, with active learning and control Open
Sparse model identification enables the discovery of nonlinear dynamical systems purely from data; however, this approach is sensitive to noise, especially in the low-data limit. In this work, we leverage the statistical approach of bootst…
View article: PySINDy: A comprehensive Python package for robust sparse system identification
PySINDy: A comprehensive Python package for robust sparse system identification Open
Automated data-driven modeling, the process of directly discovering the\ngoverning equations of a system from data, is increasingly being used across\nthe scientific community. PySINDy is a Python package that provides tools for\napplying …
View article: Data-driven unsteady aeroelastic modeling for control
Data-driven unsteady aeroelastic modeling for control Open
Aeroelastic structures, from insect wings to wind turbine blades, experience transient unsteady aerodynamic loads that are coupled to their motion. Effective real-time control of flexible structures relies on accurate and efficient predict…
View article: Ensemble-SINDy: Robust sparse model discovery in the low-data, high-noise limit, with active learning and control
Ensemble-SINDy: Robust sparse model discovery in the low-data, high-noise limit, with active learning and control Open
Sparse model identification enables the discovery of nonlinear dynamical systems purely from data; however, this approach is sensitive to noise, especially in the low-data limit. In this work, we leverage the statistical approach of bootst…
View article: SINDy with Control: A Tutorial
SINDy with Control: A Tutorial Open
Many dynamical systems of interest are nonlinear, with examples in turbulence, epidemiology, neuroscience, and finance, making them difficult to control using linear approaches. Model predictive control (MPC) is a powerful model-based opti…
View article: A Balanced Mode Decomposition Approach for Equation-Free Reduced-Order Modeling of LPV Aeroservoelastic Systems
A Balanced Mode Decomposition Approach for Equation-Free Reduced-Order Modeling of LPV Aeroservoelastic Systems Open
The paper proposes a novel approach to data-driven reduced-order modeling which combines the Dynamic Mode Decomposition technique with the concept of balanced realization. The information on the system comes from input, state, and output t…