1,317 results on '"Kutz, J. Nathan"'
Search Results
2. Robust State Estimation from Partial Out-Core Measurements with Shallow Recurrent Decoder for Nuclear Reactors
- Author
-
Riva, Stefano, Introini, Carolina, Cammi, Antonio, and Kutz, J. Nathan
- Subjects
Physics - Instrumentation and Detectors ,Mathematics - Numerical Analysis ,Physics - Computational Physics - Abstract
Reliable, real-time state estimation in nuclear reactors is of critical importance for monitoring, control and safety. It further empowers the development of digital twins that are sufficiently accurate for real-world deployment. As nuclear engineering systems are typically characterised by extreme environments, their in-core sensing is a challenging task, even more so in Generation-IV reactor concepts, which feature molten salt or liquid metals as thermal carriers. The emergence of data-driven methods allows for new techniques for accurate and robust estimation of the full state space vector characterising the reactor (mainly composed by neutron fluxes and the thermal-hydraulics fields). These techniques can combine different sources of information, including computational proxy models and local noisy measurements on the system, in order to robustly estimate the state. This work leverages the Shallow Recurrent Decoder (SHRED) architecture to estimate the entire state vector of a reactor from three, out-of-core time-series neutron flux measurements alone. Specifically, the Molten Salt Fast Reactor, in the EVOL geometry (Evaluation and Viability of Liquid Fuel Fast Reactor System project), is demonstrated as a test case, with neutron flux measurements alone allowing for reconstruction of the 20 coupled field variables of the dynamics. This approach can further quantify the uncertainty associated with the state estimation due to its considerably low training cost on compressed data. The accurate reconstruction of every characteristic field in real-time makes this approach suitable for monitoring and control purposes in the framework of a reactor digital twin.
- Published
- 2024
3. Automating the Practice of Science -- Opportunities, Challenges, and Implications
- Author
-
Musslick, Sebastian, Bartlett, Laura K., Chandramouli, Suyog H., Dubova, Marina, Gobet, Fernand, Griffiths, Thomas L., Hullman, Jessica, King, Ross D., Kutz, J. Nathan, Lucas, Christopher G., Mahesh, Suhas, Pestilli, Franco, Sloman, Sabina J., and Holmes, William R.
- Subjects
Computer Science - Computers and Society ,Physics - Physics and Society - Abstract
Automation transformed various aspects of our human civilization, revolutionizing industries and streamlining processes. In the domain of scientific inquiry, automated approaches emerged as powerful tools, holding promise for accelerating discovery, enhancing reproducibility, and overcoming the traditional impediments to scientific progress. This article evaluates the scope of automation within scientific practice and assesses recent approaches. Furthermore, it discusses different perspectives to the following questions: Where do the greatest opportunities lie for automation in scientific practice?; What are the current bottlenecks of automating scientific practice?; and What are significant ethical and practical consequences of automating scientific practice? By discussing the motivations behind automated science, analyzing the hurdles encountered, and examining its implications, this article invites researchers, policymakers, and stakeholders to navigate the rapidly evolving frontier of automated scientific practice.
- Published
- 2024
4. Long Sequence Decoder Network for Mobile Sensing
- Author
-
Mei, Jiazhong and Kutz, J. Nathan
- Subjects
Mathematics - Dynamical Systems - Abstract
The reconstruction and estimation of spatio-temporal patterns poses significant challenges when sensor measurements are limited. The use of mobile sensors adds additional complexity due to the change in sensor locations over time. In such cases, historical measurement and sensor information are useful for better performance, including models such as Kalman filters, recurrent neural networks (RNNs) or transformer models. However, many of these approaches often fail to efficiently handle long sequences of data in such scenarios and are sensitive to noise. In this paper, we consider a model-free approach using the {\em structured state space sequence} (S4D) model as a deep learning layer in traditional sequence models to learn a better representation of historical sensor data. Specifically, it is integrated with a shallow decoder network for reconstruction of the high-dimensional state space. We also introduce a novel initialization of the S4D model using a Butterworth filter design to reduce noise in the inputs. Consequently, we construct a robust S4D (rS4D) model by appending the filtering S4D layer before the original S4D structure. This robust variant enhances the capability to accurately reconstruct spatio-temporal patterns with noisy mobile sensor measurements in long sequence. Numerical experiments demonstrate that our model achieves better performance compared with previous approaches. Our results underscore the efficacy of leveraging state space models within the context of spatio-temporal data reconstruction and estimation using limited mobile sensor resources, particularly in terms of long-sequence dependency and robustness to noise., Comment: 18 pages, 11 figures
- Published
- 2024
5. VENI, VINDy, VICI: a variational reduced-order modeling framework with uncertainty quantification
- Author
-
Conti, Paolo, Kneifl, Jonas, Manzoni, Andrea, Frangi, Attilio, Fehr, Jörg, Brunton, Steven L., and Kutz, J. Nathan
- Subjects
Computer Science - Machine Learning ,Computer Science - Computational Engineering, Finance, and Science ,Mathematics - Dynamical Systems - Abstract
The simulation of many complex phenomena in engineering and science requires solving expensive, high-dimensional systems of partial differential equations (PDEs). To circumvent this, reduced-order models (ROMs) have been developed to speed up computations. However, when governing equations are unknown or partially known, typically ROMs lack interpretability and reliability of the predicted solutions. In this work we present a data-driven, non-intrusive framework for building ROMs where the latent variables and dynamics are identified in an interpretable manner and uncertainty is quantified. Starting from a limited amount of high-dimensional, noisy data the proposed framework constructs an efficient ROM by leveraging variational autoencoders for dimensionality reduction along with a newly introduced, variational version of sparse identification of nonlinear dynamics (SINDy), which we refer to as Variational Identification of Nonlinear Dynamics (VINDy). In detail, the method consists of Variational Encoding of Noisy Inputs (VENI) to identify the distribution of reduced coordinates. Simultaneously, we learn the distribution of the coefficients of a pre-determined set of candidate functions by VINDy. Once trained offline, the identified model can be queried for new parameter instances and new initial conditions to compute the corresponding full-time solutions. The probabilistic setup enables uncertainty quantification as the online testing consists of Variational Inference naturally providing Certainty Intervals (VICI). In this work we showcase the effectiveness of the newly proposed VINDy method in identifying interpretable and accurate dynamical system for the R\"ossler system with different noise intensities and sources. Then the performance of the overall method - named VENI, VINDy, VICI - is tested on PDE benchmarks including structural mechanics and fluid dynamics.
- Published
- 2024
6. Shallow Recurrent Decoder for Reduced Order Modeling of Plasma Dynamics
- Author
-
Kutz, J. Nathan, Reza, Maryam, Faraji, Farbod, and Knoll, Aaron
- Subjects
Physics - Plasma Physics ,Computer Science - Machine Learning ,Nonlinear Sciences - Pattern Formation and Solitons ,Physics - Computational Physics - Abstract
Reduced order models are becoming increasingly important for rendering complex and multiscale spatio-temporal dynamics computationally tractable. The computational efficiency of such surrogate models is especially important for design, exhaustive exploration and physical understanding. Plasma simulations, in particular those applied to the study of ${\bf E}\times {\bf B}$ plasma discharges and technologies, such as Hall thrusters, require substantial computational resources in order to resolve the multidimentional dynamics that span across wide spatial and temporal scales. Although high-fidelity computational tools are available to simulate such systems over limited conditions and in highly simplified geometries, simulations of full-size systems and/or extensive parametric studies over many geometric configurations and under different physical conditions are computationally intractable with conventional numerical tools. Thus, scientific studies and industrially oriented modeling of plasma systems, including the important ${\bf E}\times {\bf B}$ technologies, stand to significantly benefit from reduced order modeling algorithms. We develop a model reduction scheme based upon a {\em Shallow REcurrent Decoder} (SHRED) architecture. The scheme uses a neural network for encoding limited sensor measurements in time (sequence-to-sequence encoding) to full state-space reconstructions via a decoder network. Based upon the theory of separation of variables, the SHRED architecture is capable of (i) reconstructing full spatio-temporal fields with as little as three point sensors, even the fields that are not measured with sensor feeds but that are in dynamic coupling with the measured field, and (ii) forecasting the future state of the system using neural network roll-outs from the trained time encoding model., Comment: 12 pages, 7 figures
- Published
- 2024
7. Machine Learning in Viscoelastic Fluids via Energy-Based Kernel Embedding
- Author
-
Otto, Samuel E., Oishi, Cassio M., Amaral, Fabio, Brunton, Steven L., and Kutz, J. Nathan
- Subjects
Physics - Fluid Dynamics ,Physics - Computational Physics - Abstract
The ability to measure differences in collected data is of fundamental importance for quantitative science and machine learning, motivating the establishment of metrics grounded in physical principles. In this study, we focus on the development of such metrics for viscoelastic fluid flows governed by a large class of linear and nonlinear stress models. To do this, we introduce a kernel function corresponding to a given viscoelastic stress model that implicitly embeds flowfield snapshots into a Reproducing Kernel Hilbert Space (RKHS) whose squared norm equals the total mechanical energy. Working implicitly with lifted representations in the RKHS via the kernel function provides natural and unambiguous metrics for distances and angles between flowfields without the need for hyperparameter tuning. Additionally, we present a solution to the preimage problem for our kernels, enabling accurate reconstruction of flowfields from their RKHS representations. Through numerical experiments on an unsteady viscoelastic lid-driven cavity flow, we demonstrate the utility of our kernels for extracting energetically-dominant coherent structures in viscoelastic flows across a range of Reynolds and Weissenberg numbers. Specifically, the features extracted by Kernel Principal Component Analysis (KPCA) of flowfield snapshots using our kernel functions yield reconstructions with superior accuracy in terms of mechanical energy compared to conventional methods such as ordinary Principal Component Analysis (PCA) with na\"ively-defined state vectors or KPCA with ad-hoc choices of kernel functions. Our findings underscore the importance of principled choices of metrics in both scientific and machine learning investigations of complex fluid systems., Comment: 33 pages, 10 figures, Revised version of the publication
- Published
- 2024
- Full Text
- View/download PDF
8. Optimized Dynamic Mode Decomposition for Reconstruction and Forecasting of Atmospheric Chemistry Data
- Author
-
Velegar, Meghana, Keller, Christoph, and Kutz, J. Nathan
- Subjects
Computer Science - Machine Learning ,Mathematics - Dynamical Systems ,Physics - Atmospheric and Oceanic Physics ,Statistics - Applications ,Statistics - Machine Learning - Abstract
We introduce the optimized dynamic mode decomposition algorithm for constructing an adaptive and computationally efficient reduced order model and forecasting tool for global atmospheric chemistry dynamics. By exploiting a low-dimensional set of global spatio-temporal modes, interpretable characterizations of the underlying spatial and temporal scales can be computed. Forecasting is also achieved with a linear model that uses a linear superposition of the dominant spatio-temporal features. The DMD method is demonstrated on three months of global chemistry dynamics data, showing its significant performance in computational speed and interpretability. We show that the presented decomposition method successfully extracts known major features of atmospheric chemistry, such as summertime surface pollution and biomass burning activities. Moreover, the DMD algorithm allows for rapid reconstruction of the underlying linear model, which can then easily accommodate non-stationary data and changes in the dynamics., Comment: 13 pages, 16 figures
- Published
- 2024
9. SINDy-RL: Interpretable and Efficient Model-Based Reinforcement Learning
- Author
-
Zolman, Nicholas, Fasel, Urban, Kutz, J. Nathan, and Brunton, Steven L.
- Subjects
Computer Science - Machine Learning ,Electrical Engineering and Systems Science - Systems and Control ,Mathematics - Dynamical Systems ,Mathematics - Optimization and Control - Abstract
Deep reinforcement learning (DRL) has shown significant promise for uncovering sophisticated control policies that interact in environments with complicated dynamics, such as stabilizing the magnetohydrodynamics of a tokamak fusion reactor or minimizing the drag force exerted on an object in a fluid flow. However, these algorithms require an abundance of training examples and may become prohibitively expensive for many applications. In addition, the reliance on deep neural networks often results in an uninterpretable, black-box policy that may be too computationally expensive to use with certain embedded systems. Recent advances in sparse dictionary learning, such as the sparse identification of nonlinear dynamics (SINDy), have shown promise for creating efficient and interpretable data-driven models in the low-data regime. In this work we introduce SINDy-RL, a unifying framework for combining SINDy and DRL to create efficient, interpretable, and trustworthy representations of the dynamics model, reward function, and control policy. We demonstrate the effectiveness of our approaches on benchmark control environments and challenging fluids problems. SINDy-RL achieves comparable performance to state-of-the-art DRL algorithms using significantly fewer interactions in the environment and results in an interpretable control policy orders of magnitude smaller than a deep neural network policy., Comment: 24 pages + 14 appendices (45 pages total). 25 figures, 7 tables. For code, see https://github.com/nzolman/sindy-rl
- Published
- 2024
10. Statistical Mechanics of Dynamical System Identification
- Author
-
Klishin, Andrei A., Bakarji, Joseph, Kutz, J. Nathan, and Manohar, Krithika
- Subjects
Condensed Matter - Statistical Mechanics ,Computer Science - Machine Learning ,Mathematics - Optimization and Control ,Physics - Computational Physics - Abstract
Recovering dynamical equations from observed noisy data is the central challenge of system identification. We develop a statistical mechanical approach to analyze sparse equation discovery algorithms, which typically balance data fit and parsimony through a trial-and-error selection of hyperparameters. In this framework, statistical mechanics offers tools to analyze the interplay between complexity and fitness, in analogy to that done between entropy and energy. To establish this analogy, we define the optimization procedure as a two-level Bayesian inference problem that separates variable selection from coefficient values and enables the computation of the posterior parameter distribution in closed form. A key advantage of employing statistical mechanical concepts, such as free energy and the partition function, is in the quantification of uncertainty, especially in in the low-data limit; frequently encountered in real-world applications. As the data volume increases, our approach mirrors the thermodynamic limit, leading to distinct sparsity- and noise-induced phase transitions that delineate correct from incorrect identification. This perspective of sparse equation discovery, is versatile and can be adapted to various other equation discovery algorithms., Comment: 21 RevTeX page, 9 figures
- Published
- 2024
11. Data-driven local operator finding for reduced-order modelling of plasma systems: II. Application to parametric dynamics
- Author
-
Faraji, Farbod, Reza, Maryam, Knoll, Aaron, and Kutz, J. Nathan
- Subjects
Physics - Plasma Physics ,Computer Science - Machine Learning ,Physics - Computational Physics - Abstract
Real-world systems often exhibit dynamics influenced by various parameters, either inherent or externally controllable, necessitating models capable of reliably capturing these parametric behaviors. Plasma technologies exemplify such systems. For example, phenomena governing global dynamics in Hall thrusters (a spacecraft propulsion technology) vary with various parameters, such as the "self-sustained electric field". In this Part II, following on the introduction of our novel data-driven local operator finding algorithm, Phi Method, in Part I, we showcase the method's effectiveness in learning parametric dynamics to predict system behavior across unseen parameter spaces. We present two adaptations: the "parametric Phi Method" and the "ensemble Phi Method", which are demonstrated through 2D fluid-flow-past-a-cylinder and 1D Hall-thruster-plasma-discharge problems. Comparative evaluation against parametric OPT-DMD in the fluid case demonstrates superior predictive performance of the parametric Phi Method. Across both test cases, parametric and ensemble Phi Method reliably recover governing parametric PDEs and offer accurate predictions over test parameters. Ensemble ROM analysis underscores Phi Method's robust learning of dominant dynamic coefficients with high confidence., Comment: 24 pages, 17 figures
- Published
- 2024
12. Data-driven local operator finding for reduced-order modelling of plasma systems: I. Concept and verifications
- Author
-
Faraji, Farbod, Reza, Maryam, Knoll, Aaron, and Kutz, J. Nathan
- Subjects
Physics - Plasma Physics ,Computer Science - Machine Learning ,Physics - Computational Physics - Abstract
Reduced-order plasma models that can efficiently predict plasma behavior across various settings and configurations are highly sought after yet elusive. The demand for such models has surged in the past decade due to their potential to facilitate scientific research and expedite the development of plasma technologies. In line with the advancements in computational power and data-driven methods, we introduce the "Phi Method" in this two-part article. Part I presents this novel algorithm, which employs constrained regression on a candidate term library informed by numerical discretization schemes to discover discretized systems of differential equations. We demonstrate Phi Method's efficacy in deriving reliable and robust reduced-order models (ROMs) for three test cases: the Lorenz attractor, flow past a cylinder, and a 1D Hall-thruster-representative plasma. Part II will delve into the method's application for parametric dynamics discovery. Our results show that ROMs derived from the Phi Method provide remarkably accurate predictions of systems' behavior, whether derived from steady-state or transient-state data. This underscores the method's potential for transforming plasma system modeling., Comment: 27 pages, 18 figures
- Published
- 2024
13. Motif distribution and function of sparse deep neural networks
- Author
-
Zahn, Olivia T., Daniel, Thomas L., and Kutz, J. Nathan
- Subjects
Computer Science - Machine Learning - Abstract
We characterize the connectivity structure of feed-forward, deep neural networks (DNNs) using network motif theory. To address whether a particular motif distribution is characteristic of the training task, or function of the DNN, we compare the connectivity structure of 350 DNNs trained to simulate a bio-mechanical flight control system with different randomly initialized parameters. We develop and implement algorithms for counting second- and third-order motifs and calculate their significance using their Z-score. The DNNs are trained to solve the inverse problem of the flight dynamics model in Bustamante, et al. (2022) (i.e., predict the controls necessary for controlled flight from the initial and final state-space inputs) and are sparsified through an iterative pruning and retraining algorithm Zahn, et al. (2022). We show that, despite random initialization of network parameters, enforced sparsity causes DNNs to converge to similar connectivity patterns as characterized by their motif distributions. The results suggest how neural network function can be encoded in motif distributions, suggesting a variety of experiments for informing function and control.
- Published
- 2024
14. Multi-Hierarchical Surrogate Learning for Structural Dynamical Crash Simulations Using Graph Convolutional Neural Networks
- Author
-
Kneifl, Jonas, Fehr, Jörg, Brunton, Steven L., and Kutz, J. Nathan
- Subjects
Computer Science - Machine Learning ,Mathematics - Dynamical Systems - Abstract
Crash simulations play an essential role in improving vehicle safety, design optimization, and injury risk estimation. Unfortunately, numerical solutions of such problems using state-of-the-art high-fidelity models require significant computational effort. Conventional data-driven surrogate modeling approaches create low-dimensional embeddings for evolving the dynamics in order to circumvent this computational effort. Most approaches directly operate on high-resolution data obtained from numerical discretization, which is both costly and complicated for mapping the flow of information over large spatial distances. Furthermore, working with a fixed resolution prevents the adaptation of surrogate models to environments with variable computing capacities, different visualization resolutions, and different accuracy requirements. We thus propose a multi-hierarchical framework for structurally creating a series of surrogate models for a kart frame, which is a good proxy for industrial-relevant crash simulations, at different levels of resolution. For multiscale phenomena, macroscale features are captured on a coarse surrogate, whereas microscale effects are resolved by finer ones. The learned behavior of the individual surrogates is passed from coarse to finer levels through transfer learning. In detail, we perform a mesh simplification on the kart model to obtain multi-resolution representations of it. We then train a graph-convolutional neural network-based surrogate that learns parameter-dependent low-dimensional latent dynamics on the coarsest representation. Subsequently, another, similarly structured surrogate is trained on the residual of the first surrogate using a finer resolution. This step can be repeated multiple times. By doing so, we construct multiple surrogates for the same system with varying hardware requirements and increasing accuracy.
- Published
- 2024
15. PyDMD: A Python package for robust dynamic mode decomposition
- Author
-
Ichinaga, Sara M., Andreuzzi, Francesco, Demo, Nicola, Tezzele, Marco, Lapo, Karl, Rozza, Gianluigi, Brunton, Steven L., and Kutz, J. Nathan
- Subjects
Statistics - Computation ,Electrical Engineering and Systems Science - Systems and Control ,Mathematics - Dynamical Systems ,Physics - Computational Physics - Abstract
The dynamic mode decomposition (DMD) is a simple and powerful data-driven modeling technique that is capable of revealing coherent spatiotemporal patterns from data. The method's linear algebra-based formulation additionally allows for a variety of optimizations and extensions that make the algorithm practical and viable for real-world data analysis. As a result, DMD has grown to become a leading method for dynamical system analysis across multiple scientific disciplines. PyDMD is a Python package that implements DMD and several of its major variants. In this work, we expand the PyDMD package to include a number of cutting-edge DMD methods and tools specifically designed to handle dynamics that are noisy, multiscale, parameterized, prohibitively high-dimensional, or even strongly nonlinear. We provide a complete overview of the features available in PyDMD as of version 1.0, along with a brief overview of the theory behind the DMD algorithm, information for developers, tips regarding practical DMD usage, and introductory coding examples. All code is available at https://github.com/PyDMD/PyDMD .
- Published
- 2024
16. Attention for Causal Relationship Discovery from Biological Neural Dynamics
- Author
-
Lu, Ziyu, Tabassum, Anika, Kulkarni, Shruti, Mi, Lu, Kutz, J. Nathan, Shea-Brown, Eric, and Lim, Seung-Hwan
- Subjects
Computer Science - Machine Learning ,Statistics - Methodology - Abstract
This paper explores the potential of the transformer models for learning Granger causality in networks with complex nonlinear dynamics at every node, as in neurobiological and biophysical networks. Our study primarily focuses on a proof-of-concept investigation based on simulated neural dynamics, for which the ground-truth causality is known through the underlying connectivity matrix. For transformer models trained to forecast neuronal population dynamics, we show that the cross attention module effectively captures the causal relationship among neurons, with an accuracy equal or superior to that for the most popular Granger causality analysis method. While we acknowledge that real-world neurobiology data will bring further challenges, including dynamic connectivity and unobserved variability, this research offers an encouraging preliminary glimpse into the utility of the transformer model for causal representation learning in neuroscience., Comment: Accepted to the NeurIPS 2023 Workshop on Causal Representation Learning
- Published
- 2023
17. Ensemble Principal Component Analysis
- Author
-
Dorabiala, Olga, Aravkin, Aleksandr, and Kutz, J. Nathan
- Subjects
Statistics - Computation ,62F40, 62H30 ,I.5.3 ,I.5.4 - Abstract
Efficient representations of data are essential for processing, exploration, and human understanding, and Principal Component Analysis (PCA) is one of the most common dimensionality reduction techniques used for the analysis of large, multivariate datasets today. Two well-known limitations of the method include sensitivity to outliers and noise and no clear methodology for the uncertainty quantification of the principle components or their associated explained variances. Whereas previous work has focused on each of these problems individually, we propose a scalable method called Ensemble PCA (EPCA) that addresses them simultaneously for data which has an inherently low-rank structure. EPCA combines boostrapped PCA with k-means cluster analysis to handle challenges associated with sign-ambiguity and the re-ordering of components in the PCA subsamples. EPCA provides a noise-resistant extension of PCA that lends itself naturally to uncertainty quantification. We test EPCA on data corrupted with white noise, sparse noise, and outliers against both classical PCA and Robust PCA (RPCA) and show that EPCA performs competitively across different noise scenarios, with a clear advantage on datasets containing outliers and orders of magnitude reduction in computational cost compared to RPCA., Comment: 20 pages, 8 Figures
- Published
- 2023
18. Promising directions of machine learning for partial differential equations
- Author
-
Brunton, Steven L. and Kutz, J. Nathan
- Published
- 2024
- Full Text
- View/download PDF
19. A Unified Framework to Enforce, Discover, and Promote Symmetry in Machine Learning
- Author
-
Otto, Samuel E., Zolman, Nicholas, Kutz, J. Nathan, and Brunton, Steven L.
- Subjects
Computer Science - Machine Learning ,Mathematics - Differential Geometry ,Mathematics - Numerical Analysis ,15B30, 22E15, 22E70, 47D03, 54H15, 57S99, 5808, 58D19, 58K70, 65F55, 68Q32, 68T07, 70G65, 70H33, 90C25 - Abstract
Symmetry is present throughout nature and continues to play an increasingly central role in physics and machine learning. Fundamental symmetries, such as Poincar\'{e} invariance, allow physical laws discovered in laboratories on Earth to be extrapolated to the farthest reaches of the universe. Symmetry is essential to achieving this extrapolatory power in machine learning applications. For example, translation invariance in image classification allows models with fewer parameters, such as convolutional neural networks, to be trained on smaller data sets and achieve state-of-the-art performance. In this paper, we provide a unifying theoretical and methodological framework for incorporating symmetry into machine learning models in three ways: 1. enforcing known symmetry when training a model; 2. discovering unknown symmetries of a given model or data set; and 3. promoting symmetry during training by learning a model that breaks symmetries within a user-specified group of candidates when there is sufficient evidence in the data. We show that these tasks can be cast within a common mathematical framework whose central object is the Lie derivative associated with fiber-linear Lie group actions on vector bundles. We extend and unify several existing results by showing that enforcing and discovering symmetry are linear-algebraic tasks that are dual with respect to the bilinear structure of the Lie derivative. We also propose a novel way to promote symmetry by introducing a class of convex regularization functions based on the Lie derivative and nuclear norm relaxation to penalize symmetry breaking during training of machine learning models. We explain how these ideas can be applied to a wide range of machine learning models including basis function regression, dynamical systems discovery, neural networks, and neural operators acting on fields.
- Published
- 2023
20. HyperSINDy: Deep Generative Modeling of Nonlinear Stochastic Governing Equations
- Author
-
Jacobs, Mozes, Brunton, Bingni W., Brunton, Steven L., Kutz, J. Nathan, and Raut, Ryan V.
- Subjects
Computer Science - Machine Learning ,68T07 (Primary) 37H10, 60H10 (Secondary) ,I.2 ,J.2 - Abstract
The discovery of governing differential equations from data is an open frontier in machine learning. The sparse identification of nonlinear dynamics (SINDy) \citep{brunton_discovering_2016} framework enables data-driven discovery of interpretable models in the form of sparse, deterministic governing laws. Recent works have sought to adapt this approach to the stochastic setting, though these adaptations are severely hampered by the curse of dimensionality. On the other hand, Bayesian-inspired deep learning methods have achieved widespread success in high-dimensional probabilistic modeling via computationally efficient approximate inference techniques, suggesting the use of these techniques for efficient stochastic equation discovery. Here, we introduce HyperSINDy, a framework for modeling stochastic dynamics via a deep generative model of sparse governing equations whose parametric form is discovered from data. HyperSINDy employs a variational encoder to approximate the distribution of observed states and derivatives. A hypernetwork \citep{ha_hypernetworks_2016} transforms samples from this distribution into the coefficients of a differential equation whose sparse form is learned simultaneously using a trainable binary mask \citep{louizos_learning_2018}. Once trained, HyperSINDy generates stochastic dynamics via a differential equation whose coefficients are driven by a Gaussian white noise. In experiments, HyperSINDy accurately recovers ground truth stochastic governing equations, with learned stochasticity scaling to match that of the data. Finally, HyperSINDy provides uncertainty quantification that scales to high-dimensional systems. Taken together, HyperSINDy offers a promising framework for model discovery and uncertainty quantification in real-world systems, integrating sparse equation discovery methods with advances in statistical machine learning and deep generative modeling., Comment: 19 pages, 4 figures (main text), 4 figures (appendix)
- Published
- 2023
21. Extremum seeking control of quantum gates
- Author
-
Abbasgholinejad, Erfan, Deng, Haoqin, Gamble, John, Kutz, J. Nathan, Nielsen, Erik, Pisenti, Neal, and Xie, Ningzhi
- Subjects
Quantum Physics - Abstract
To be useful for quantum computation, gate operations must be maintained at high fidelities over long periods of time. In addition to decoherence, slow drifts in control hardware leads to inaccurate gates, causing the quality of operation of as-built quantum computers to vary over time. Here, we demonstrate a data-driven approach to stabilized control, combining extremum-seeking control (ESC) with direct randomized benchmarking (DRB) to stabilize two-qubit gates under unknown control parameter fluctuations. As a case study, we consider these control strategies in the context of a trapped ion quantum computer using physically-realistic simulation. We then experimentally demonstrate this control strategy on a state-of-the-art, commercial trapped-ion quantum computer., Comment: 5 pages, 6 figures
- Published
- 2023
22. Multi-fidelity reduced-order surrogate modeling
- Author
-
Conti, Paolo, Guo, Mengwu, Manzoni, Andrea, Frangi, Attilio, Brunton, Steven L., and Kutz, J. Nathan
- Subjects
Computer Science - Machine Learning ,Mathematics - Numerical Analysis - Abstract
High-fidelity numerical simulations of partial differential equations (PDEs) given a restricted computational budget can significantly limit the number of parameter configurations considered and/or time window evaluated for modeling a given system. Multi-fidelity surrogate modeling aims to leverage less accurate, lower-fidelity models that are computationally inexpensive in order to enhance predictive accuracy when high-fidelity data are limited or scarce. However, low-fidelity models, while often displaying important qualitative spatio-temporal features, fail to accurately capture the onset of instability and critical transients observed in the high-fidelity models, making them impractical as surrogate models. To address this shortcoming, we present a new data-driven strategy that combines dimensionality reduction with multi-fidelity neural network surrogates. The key idea is to generate a spatial basis by applying the classical proper orthogonal decomposition (POD) to high-fidelity solution snapshots, and approximate the dynamics of the reduced states - time-parameter-dependent expansion coefficients of the POD basis - using a multi-fidelity long-short term memory (LSTM) network. By mapping low-fidelity reduced states to their high-fidelity counterpart, the proposed reduced-order surrogate model enables the efficient recovery of full solution fields over time and parameter variations in a non-intrusive manner. The generality and robustness of this method is demonstrated by a collection of parametrized, time-dependent PDE problems where the low-fidelity model can be defined by coarser meshes and/or time stepping, as well as by misspecified physical features. Importantly, the onset of instabilities and transients are well captured by this surrogate modeling technique.
- Published
- 2023
23. Dynamic Mode Decomposition for data-driven analysis and reduced-order modelling of ExB plasmas: II. dynamics forecasting
- Author
-
Faraji, Farbod, Reza, Maryam, Knoll, Aaron, and Kutz, J. Nathan
- Subjects
Physics - Plasma Physics ,Computer Science - Machine Learning ,Physics - Computational Physics - Abstract
In part I of the article, we demonstrated that a variant of the Dynamic Mode Decomposition (DMD) algorithm based on variable projection optimization, called Optimized DMD (OPT-DMD), enables a robust identification of the dominant spatiotemporally coherent modes underlying the data across various test cases representing different physical parameters in an ExB simulation configuration. As the OPT-DMD can be constrained to produce stable reduced-order models (ROMs) by construction, in this paper, we extend the application of the OPT-DMD and investigate the capabilities of the linear ROM from this algorithm toward forecasting in time of the plasma dynamics in configurations representative of the radial-azimuthal and axial-azimuthal cross-sections of a Hall thruster and over a range of simulation parameters in each test case. The predictive capacity of the OPT-DMD ROM is assessed primarily in terms of short-term dynamics forecast or, in other words, for large ratios of training-to-test data. However, the utility of the ROM for long-term dynamics forecasting is also presented for an example case in the radial-azimuthal configuration. The model's predictive performance is heterogeneous across various test cases. Nonetheless, a remarkable predictiveness is observed in the test cases that do not exhibit highly transient behaviors. Moreover, in all investigated cases, the error between the ground-truth and the reconstructed data from the OPT-DMD ROM remains bounded over time within both the training and the test window. As a result, despite its limitation in terms of generalized applicability to all plasma conditions, the OPT-DMD is proven as a reliable method to develop low computational cost and highly predictive data-driven reduced-order models in systems with a quasi-periodic global evolution of the plasma state., Comment: 14 pages, 14 figures
- Published
- 2023
24. Dynamic Mode Decomposition for data-driven analysis and reduced-order modelling of ExB plasmas: I. Extraction of spatiotemporally coherent patterns
- Author
-
Faraji, Farbod, Reza, Maryam, Knoll, Aaron, and Kutz, J. Nathan
- Subjects
Physics - Plasma Physics ,Computer Science - Machine Learning ,Physics - Computational Physics - Abstract
In this two-part article, we evaluate the utility and the generalizability of the Dynamic Mode Decomposition (DMD) algorithm for data-driven analysis and reduced-order modelling of plasma dynamics in cross-field ExB configurations. The DMD algorithm is an interpretable data-driven method that finds a best-fit linear model describing the time evolution of spatiotemporally coherent structures (patterns) in data. We have applied the DMD to extensive high-fidelity datasets generated using a particle-in-cell (PIC) code based on a cost-efficient reduced-order PIC scheme. In this part, we first provide an overview of the concept of DMD and its underpinning Proper Orthogonal and Singular Value Decomposition methods. Two of the main DMD variants are next introduced. We then present and discuss the results of the DMD application in terms of the identification and extraction of the dominant spatiotemporal modes from high-fidelity data over a range of simulation conditions. We demonstrate that the DMD variant based on variable projection optimization (OPT-DMD) outperforms the basic DMD method in identification of the modes underlying the data, leading to notably more reliable reconstruction of the ground-truth. Furthermore, we show in multiple test cases that the discrete frequency spectrum of OPT-DMD-extracted modes is consistent with the temporal spectrum from the Fast Fourier Transform of the data. This observation implies that the OPT-DMD augments the conventional spectral analyses by being able to uniquely reveal the spatial structure of the dominant modes in the frequency spectra, thus, yielding more accessible, comprehensive information on the spatiotemporal characteristics of the plasma phenomena., Comment: 21 pages, 16 figues
- Published
- 2023
25. Nonlinear parametric models of viscoelastic fluid flows
- Author
-
Oishi, Cassio M., Kaptanoglu, Alan A., Kutz, J. Nathan, and Brunton, Steven L.
- Subjects
Physics - Fluid Dynamics ,Mathematics - Numerical Analysis ,Physics - Computational Physics - Abstract
Reduced-order models have been widely adopted in fluid mechanics, particularly in the context of Newtonian fluid flows. These models offer the ability to predict complex dynamics, such as instabilities and oscillations, at a considerably reduced computational cost. In contrast, the reduced-order modeling of non-Newtonian viscoelastic fluid flows remains relatively unexplored. This work leverages the sparse identification of nonlinear dynamics algorithm to develop interpretable reduced-order models for viscoelastic flows. In particular, we explore a benchmark oscillatory viscoelastic flow on the four-roll mill geometry using the classical Oldroyd-B fluid. This flow exemplifies many canonical challenges associated with non-Newtonian flows, including transitions, asymmetries, instabilities, and bifurcations arising from the interplay of viscous and elastic forces, all of which require expensive computations in order to resolve the fast timescales and long transients characteristic of such flows. First, we demonstrate the effectiveness of our data-driven surrogate model to predict the transient evolution and accurately reconstruct the spatial flow field for fixed flow parameters. We then develop a fully parametric, nonlinear model capable of capturing the dynamic variations as a function of the Weissenberg number. While the training data is predominantly concentrated on a limit cycle regime for moderate Wi, we show that the parameterized model can be used to extrapolate, accurately predicting the dominant dynamics in the case of high Weissenberg numbers. The proposed methodology represents an initial step in the field of reduced-order modeling for viscoelastic flows with the potential to be further refined and enhanced for the design, optimization, and control of a wide range of non-Newtonian fluid flows using machine learning and reduced-order modeling techniques.
- Published
- 2023
26. Data-Induced Interactions of Sparse Sensors
- Author
-
Klishin, Andrei A., Kutz, J. Nathan, and Manohar, Krithika
- Subjects
Condensed Matter - Statistical Mechanics ,Computer Science - Machine Learning ,Electrical Engineering and Systems Science - Signal Processing ,Mathematics - Optimization and Control ,Physics - Computational Physics - Abstract
Large-dimensional empirical data in science and engineering frequently has low-rank structure and can be represented as a combination of just a few eigenmodes. Because of this structure, we can use just a few spatially localized sensor measurements to reconstruct the full state of a complex system. The quality of this reconstruction, especially in the presence of sensor noise, depends significantly on the spatial configuration of the sensors. Multiple algorithms based on gappy interpolation and QR factorization have been proposed to optimize sensor placement. Here, instead of an algorithm that outputs a singular "optimal" sensor configuration, we take a thermodynamic view to compute the full landscape of sensor interactions induced by the training data. The landscape takes the form of the Ising model in statistical physics, and accounts for both the data variance captured at each sensor location and the crosstalk between sensors. Mapping out these data-induced sensor interactions allows combining them with external selection criteria and anticipating sensor replacement impacts., Comment: 17 RevTeX pages, 10 figures
- Published
- 2023
27. Leveraging arbitrary mobile sensor trajectories with shallow recurrent decoder networks for full-state reconstruction
- Author
-
Ebers, Megan R., Williams, Jan P., Steele, Katherine M., and Kutz, J. Nathan
- Subjects
Computer Science - Machine Learning ,Mathematics - Dynamical Systems - Abstract
Sensing is one of the most fundamental tasks for the monitoring, forecasting and control of complex, spatio-temporal systems. In many applications, a limited number of sensors are mobile and move with the dynamics, with examples including wearable technology, ocean monitoring buoys, and weather balloons. In these dynamic systems (without regions of statistical-independence), the measurement time history encodes a significant amount of information that can be extracted for critical tasks. Most model-free sensing paradigms aim to map current sparse sensor measurements to the high-dimensional state space, ignoring the time-history all together. Using modern deep learning architectures, we show that a sequence-to-vector model, such as an LSTM (long, short-term memory) network, with a decoder network, dynamic trajectory information can be mapped to full state-space estimates. Indeed, we demonstrate that by leveraging mobile sensor trajectories with shallow recurrent decoder networks, we can train the network (i) to accurately reconstruct the full state space using arbitrary dynamical trajectories of the sensors, (ii) the architecture reduces the variance of the mean-square error of the reconstruction error in comparison with immobile sensors, and (iii) the architecture also allows for rapid generalization (parameterization of dynamics) for data outside the training set. Moreover, the path of the sensor can be chosen arbitrarily, provided training data for the spatial trajectory of the sensor is available. The exceptional performance of the network architecture is demonstrated on three applications: turbulent flows, global sea-surface temperature data, and human movement biomechanics., Comment: 11 pages, 5 figures, 2 tables
- Published
- 2023
28. PyKoopman: A Python Package for Data-Driven Approximation of the Koopman Operator
- Author
-
Pan, Shaowu, Kaiser, Eurika, de Silva, Brian M., Kutz, J. Nathan, and Brunton, Steven L.
- Subjects
Electrical Engineering and Systems Science - Systems and Control ,Computer Science - Machine Learning ,Mathematics - Dynamical Systems ,Physics - Computational Physics - Abstract
PyKoopman is a Python package for the data-driven approximation of the Koopman operator associated with a dynamical system. The Koopman operator is a principled linear embedding of nonlinear dynamics and facilitates the prediction, estimation, and control of strongly nonlinear dynamics using linear systems theory. In particular, PyKoopman provides tools for data-driven system identification for unforced and actuated systems that build on the equation-free dynamic mode decomposition (DMD) and its variants. In this work, we provide a brief description of the mathematical underpinnings of the Koopman operator, an overview and demonstration of the features implemented in PyKoopman (with code examples), practical advice for users, and a list of potential extensions to PyKoopman. Software is available at http://github.com/dynamicslab/pykoopman, Comment: 16 pages
- Published
- 2023
29. Machine Learning for Partial Differential Equations
- Author
-
Brunton, Steven L. and Kutz, J. Nathan
- Subjects
Computer Science - Machine Learning ,Mathematics - Analysis of PDEs ,Mathematics - Dynamical Systems ,Mathematics - Numerical Analysis ,Physics - Fluid Dynamics - Abstract
Partial differential equations (PDEs) are among the most universal and parsimonious descriptions of natural physical laws, capturing a rich variety of phenomenology and multi-scale physics in a compact and symbolic representation. This review will examine several promising avenues of PDE research that are being advanced by machine learning, including: 1) the discovery of new governing PDEs and coarse-grained approximations for complex natural and engineered systems, 2) learning effective coordinate systems and reduced-order models to make PDEs more amenable to analysis, and 3) representing solution operators and improving traditional numerical algorithms. In each of these fields, we summarize key advances, ongoing challenges, and opportunities for further development., Comment: 16 pages, 6 figures
- Published
- 2023
30. Convergence of uncertainty estimates in Ensemble and Bayesian sparse model discovery
- Author
-
Gao, L. Mars, Fasel, Urban, Brunton, Steven L., and Kutz, J. Nathan
- Subjects
Computer Science - Machine Learning ,Mathematics - Dynamical Systems ,Statistics - Methodology - Abstract
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, we perform a theoretical study on ensemble sparse model discovery, which shows empirical success in terms of accuracy and robustness to noise. In particular, we analyse the bootstrapping-based sequential thresholding least-squares estimator. We show that this bootstrapping-based ensembling technique can perform a provably correct variable selection procedure with an exponential convergence rate of the error rate. In addition, we show that the ensemble sparse model discovery method can perform computationally efficient uncertainty estimation, compared to expensive Bayesian uncertainty quantification methods via MCMC. We demonstrate the convergence properties and connection to uncertainty quantification in various numerical studies on synthetic sparse linear regression and sparse model discovery. The experiments on sparse linear regression support that the bootstrapping-based sequential thresholding least-squares method has better performance for sparse variable selection compared to LASSO, thresholding least-squares, and bootstrapping-based LASSO. In the sparse model discovery experiment, we show that the bootstrapping-based sequential thresholding least-squares method can provide valid uncertainty quantification, converging to a delta measure centered around the true value with increased sample sizes. Finally, we highlight the improved robustness to hyperparameter selection under shifting noise and sparsity levels of the bootstrapping-based sequential thresholding least-squares method compared to other sparse regression methods., Comment: 32 pages, 7 figures
- Published
- 2023
31. Deep Learning Based Object Tracking in Walking Droplet and Granular Intruder Experiments
- Author
-
Kara, Erdi, Zhang, George, Williams, Joseph J., Ferrandez-Quinto, Gonzalo, Rhoden, Leviticus J., Kim, Maximilian, Kutz, J. Nathan, and Rahman, Aminur
- Subjects
Computer Science - Computer Vision and Pattern Recognition - Abstract
We present a deep-learning based tracking objects of interest in walking droplet and granular intruder experiments. In a typical walking droplet experiment, a liquid droplet, known as \textit{walker}, propels itself laterally on the free surface of a vibrating bath of the same liquid. This motion is the result of the interaction between the droplets and the surface waves generated by the droplet itself after each successive bounce. A walker can exhibit a highly irregular trajectory over the course of its motion, including rapid acceleration and complex interactions with the other walkers present in the same bath. In analogy with the hydrodynamic experiments, the granular matter experiments consist of a vibrating bath of very small solid particles and a larger solid \textit{intruder}. Like the fluid droplets, the intruder interacts with and travels the domain due to the waves of the bath but tends to move much slower and much less smoothly than the droplets. When multiple intruders are introduced, they also exhibit complex interactions with each other. We leverage the state-of-art object detection model YOLO and the Hungarian Algorithm to accurately extract the trajectory of a walker or intruder in real-time. Our proposed methodology is capable of tracking individual walker(s) or intruder(s) in digital images acquired from a broad spectrum of experimental settings and does not suffer from any identity-switch issues. Thus, the deep learning approach developed in this work could be used to automatize the efficient, fast and accurate extraction of observables of interests in walking droplet and granular flow experiments. Such extraction capabilities are critically enabling for downstream tasks such as building data-driven dynamical models for the coarse-grained dynamics and interactions of the objects of interest.
- Published
- 2023
32. Sensing with shallow recurrent decoder networks
- Author
-
Williams, Jan P., Zahn, Olivia, and Kutz, J. Nathan
- Subjects
Mathematics - Dynamical Systems - Abstract
Sensing is a universal task in science and engineering. Downstream tasks from sensing include inferring full state estimates of a system (system identification), control decisions, and forecasting. These tasks are exceptionally challenging to achieve with limited sensors, noisy measurements, and corrupt or missing data. We propose a SHallow REcurrent Decoder (SHRED) neural network structure for sensing which incorporates (i) a recurrent neural network (LSTM) to learn a latent representation of the temporal dynamics of the sensors, and (ii) a shallow decoder that learns a mapping between this latent representation and the high-dimensional state space. By explicitly accounting for the time-history, or trajectory, of the sensor measurements, SHRED enables accurate reconstructions with far fewer sensors, outperforms existing techniques when more measurements are available, and is agnostic towards sensor placement. In addition, a compressed representation of the high-dimensional state is directly obtained from sensor measurements, which provides an on-the-fly compression for modeling physical and engineering systems. Forecasting is also achieved from the sensor time-series data alone, producing an efficient paradigm for predicting temporal evolution with an exceptionally limited number of sensors. In the example cases explored, including turbulent flows, complex spatio-temporal dynamics can be characterized with exceedingly limited sensors that can be randomly placed with minimal loss of performance., Comment: 12 pages, 7 figures
- Published
- 2023
33. Data-driven discovery and extrapolation of parameterized pattern-forming dynamics
- Author
-
Nicolaou, Zachary G., Huo, Guanyu, Chen, Yihui, Brunton, Steven L., and Kutz, J. Nathan
- Subjects
Nonlinear Sciences - Pattern Formation and Solitons ,Condensed Matter - Disordered Systems and Neural Networks - Abstract
Pattern-forming systems can exhibit a diverse array of complex behaviors as external parameters are varied, enabling a variety of useful functions in biological and engineered systems. First-principles derivations of the underlying transitions can be characterized using bifurcation theory on model systems whose governing equations are known. In contrast, data-driven methods for more complicated and realistic systems whose governing evolution dynamics are unknown have only recently been developed. Here we develop a data-driven approach, the {\em sparse identification for nonlinear dynamics with control parameters} (SINDyCP), to discover dynamics for systems with adjustable control parameters, such as an external driving strength. We demonstrate the method on systems of varying complexity, ranging from discrete maps to systems of partial differential equations. To mitigate the impact of measurement noise, we also develop a weak formulation of SINDyCP and assess its performance on noisy data. We demonstrate applications including the discovery of universal pattern-formation equations, and their bifurcation dependencies, directly from data accessible from experiments and the extrapolation of predictions beyond the weakly nonlinear regime near the onset of an instability., Comment: 6 pages, 4 figures, plus supplement
- Published
- 2023
- Full Text
- View/download PDF
34. Mobile Sensor Path Planning for Kalman Filter Spatiotemporal Estimation
- Author
-
Mei, Jiazhong, Brunton, Steven L., and Kutz, J. Nathan
- Subjects
Mathematics - Optimization and Control - Abstract
The estimation of spatiotemporal data from limited sensor measurements is a required task across many scientific disciplines. The sensor selection problem, which aims to optimize the placement of sensors, leverages innovations in greedy algorithms and low-rank subspace projection to provide model-free, data-driven estimates. Alternatively, Kalman filter estimation balances model-based information and sparsely observed measurements to collectively make an estimation, with many related optimization algorithms developed for selecting optimal sensors. The majority of methods have been developed for stationary sensors, with relatively limited work estimating spatiotemporal data using mobile sensors that leverage both Kalman filtering and low-rank features. We show that mobile sensing along dynamic trajectories can achieve the equivalent performance of a larger number of stationary sensors, with performance gains related to three distinct timescales: (i) the timescale of the spatio-temporal dynamics, (ii) the velocity of the sensors, and (iii) the rate of sampling. Taken together, these timescales strongly influence how well-conditioned the estimation task is. Mobile sensing is particularly effective for spatio-temporal data that contain spatially localized structures, whose features are captured along dynamic trajectories. We draw connections between the Kalman filter performance and the observability of the state space model, and propose a greedy path planning algorithm based on minimizing the condition number of the observability matrix. Through a series of examples of increasing complexity, we show that mobile sensing improves Kalman filter performance in terms of better limiting estimation and faster convergence., Comment: 19 pages, 10 figures
- Published
- 2022
35. Universal Dynamics of Damped-Driven Systems: The Logistic Map as a Normal Form for Energy Balance
- Author
-
Kutz, J. Nathan, Rahman, Aminur, Ebers, Megan R., Koch, James, and Bramburger, Jason J.
- Subjects
Nonlinear Sciences - Adaptation and Self-Organizing Systems ,Mathematics - Dynamical Systems ,Nonlinear Sciences - Chaotic Dynamics ,Physics - Data Analysis, Statistics and Probability ,Physics - Popular Physics - Abstract
Damped-driven systems are ubiquitous in engineering and science. Despite the diversity of physical processes observed in a broad range of applications, the underlying instabilities observed in practice have a universal characterization which is determined by the overall gain and loss curves of a given system. The universal behavior of damped-driven systems can be understood from a geometrical description of the energy balance with a minimal number of assumptions. The assumptions on the energy dynamics are as follows: the energy increases monotonically as a function of increasing gain, and the losses become increasingly larger with increasing energy, i.e. there are many routes for dissipation in the system for large input energy. The intersection of the gain and loss curves define an energy balanced solution. By constructing an iterative map between the loss and gain curves, the dynamics can be shown to be homeomorphic to the logistic map, which exhibits a period doubling cascade to chaos. Indeed, the loss and gain curves allow for a geometrical description of the dynamics through a simple Verhulst diagram (cobweb plot). Thus irrespective of the physics and its complexities, this simple geometrical description dictates the universal set of logistic map instabilities that arise in complex damped-driven systems. More broadly, damped-driven systems are a class of non-equilibrium pattern forming systems which have a canonical set of instabilities that are manifest in practice., Comment: 26 pages, 31 figures
- Published
- 2022
36. Bayesian autoencoders for data-driven discovery of coordinates, governing equations and fundamental constants
- Author
-
Gao, L. Mars and Kutz, J. Nathan
- Subjects
Computer Science - Machine Learning ,Computer Science - Artificial Intelligence ,Statistics - Machine Learning - Abstract
Recent progress in autoencoder-based sparse identification of nonlinear dynamics (SINDy) under $\ell_1$ constraints allows joint discoveries of governing equations and latent coordinate systems from spatio-temporal data, including simulated video frames. However, it is challenging for $\ell_1$-based sparse inference to perform correct identification for real data due to the noisy measurements and often limited sample sizes. To address the data-driven discovery of physics in the low-data and high-noise regimes, we propose Bayesian SINDy autoencoders, which incorporate a hierarchical Bayesian sparsifying prior: Spike-and-slab Gaussian Lasso. Bayesian SINDy autoencoder enables the joint discovery of governing equations and coordinate systems with a theoretically guaranteed uncertainty estimate. To resolve the challenging computational tractability of the Bayesian hierarchical setting, we adapt an adaptive empirical Bayesian method with Stochatic gradient Langevin dynamics (SGLD) which gives a computationally tractable way of Bayesian posterior sampling within our framework. Bayesian SINDy autoencoder achieves better physics discovery with lower data and fewer training epochs, along with valid uncertainty quantification suggested by the experimental studies. The Bayesian SINDy autoencoder can be applied to real video data, with accurate physics discovery which correctly identifies the governing equation and provides a close estimate for standard physics constants like gravity $g$, for example, in videos of a pendulum., Comment: 28 pages, 11 figures
- Published
- 2022
37. Pilot-Wave Dynamics: Using Dynamic Mode Decomposition to characterize Bifurcations, Routes to Chaos and Emergent Statistics
- Author
-
Kutz, J. Nathan, Nachbin, Andre, Baddoo, Peter J., and Bush, John W. M.
- Subjects
Physics - Fluid Dynamics ,Mathematics - Dynamical Systems ,Nonlinear Sciences - Pattern Formation and Solitons - Abstract
We develop a data-driven characterization of the pilot-wave hydrodynamic system in which a bouncing droplet self-propels along the surface of a vibrating bath. We consider drop motion in a confined one-dimensional geometry, and apply the {\em Dynamic mode decomposition} (DMD) in order to characterize the evolution of the wave field as the bath's vibrational acceleration is increased progressively. DMD provides a regression framework for adaptively learning a best-fit linear dynamics model over snapshots of spatio-temporal data. The DMD characterization of the wave field yields a fresh perspective on the bouncing-droplet problem that forges valuable new links with the mathematical machinery of quantum mechanics. Moreover, it provides a low-rank characterization of the bifurcation structure of the pilot wave physics. Specifically, the analysis shows that as the vibrational acceleration is increased, the pilot-wave field undergoes a series of Hopf bifurcations that ultimately lead to a chaotic wave field. The established relation between the mean pilot-wave field and the droplet statistics allows us to characterize the evolution of the emergent statistics with increased vibrational forcing from the evolution of the pilot-wave field. We thus develop a numerical framework with the same basic structure as quantum mechanics, specifically a wave theory that predicts particle statistics., Comment: 12 pages, 10 figures
- Published
- 2022
38. Saddle Transport and Chaos in the Double Pendulum
- Author
-
Kaheman, Kadierdan, Bramburger, Jason J., Kutz, J. Nathan, and Brunton, Steven L.
- Subjects
Mathematics - Dynamical Systems ,37J46, 65P99 - Abstract
Pendulums are simple mechanical systems that have been studied for centuries and exhibit many aspects of modern dynamical systems theory. In particular, the double pendulum is a prototypical chaotic system that is frequently used to illustrate a variety of phenomena in nonlinear dynamics. In this work, we explore the existence and implications of codimension-1 invariant manifolds in the double pendulum, which originate from unstable periodic orbits around saddle equilibria and act as separatrices that mediate the global phase space transport. Motivated in part by similar studies on the three-body problem, we are able to draw a direct comparison between the dynamics of the double pendulum and transport in the solar system, which exist on vastly different scales. Thus, the double pendulum may be viewed as a table-top benchmark for chaotic, saddle-mediated transport, with direct relevance to energy-efficient space mission design. The analytical results of this work provide an existence result, concerning arbitrarily long itineraries in phase space, that is applicable to a wide class of two degree of freedom Hamiltonian systems, including the three-body problem and the double pendulum. This manuscript details a variety of periodic orbits corresponding to acrobatic motions of the double pendulum that can be identified and controlled in a laboratory setting., Comment: 47 pages, 17 figures Version 2 made minor changes based on reviewers comments
- Published
- 2022
39. Robust, High-Rate Trajectory Tracking on Insect-Scale Soft-Actuated Aerial Robots with Deep-Learned Tube MPC
- Author
-
Tagliabue, Andrea, Hsiao, Yi-Hsuan, Fasel, Urban, Kutz, J. Nathan, Brunton, Steven L., Chen, YuFeng, and How, Jonathan P.
- Subjects
Computer Science - Robotics ,Computer Science - Machine Learning - Abstract
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 computational constraints prevent the deployment of computationally expensive strategies. In this work, we present an approach for agile and computationally efficient trajectory tracking on the MIT SoftFly, a sub-gram MAV (0.7 grams). Our strategy employs a cascaded control scheme, where an adaptive attitude controller is combined with a neural network policy trained to imitate a trajectory tracking robust tube model predictive controller (RTMPC). The neural network policy is obtained using our recent work, which enables the policy to preserve the robustness of RTMPC, but at a fraction of its computational cost. We experimentally evaluate our approach, achieving position Root Mean Square Errors lower than 1.8 cm even in the more challenging maneuvers, obtaining a 60% reduction in maximum position error compared to our previous work, and demonstrating robustness to large external disturbances, Comment: Submitted to ICRA 2023. Andrea Tagliabue and Yi-Hsuan Hsiao equally contributed. Video: https://youtu.be/Seupy1bSkY4
- Published
- 2022
40. Koopman-theoretic Approach for Identification of Exogenous Anomalies in Nonstationary Time-series Data
- Author
-
Mallen, Alex, Keller, Christoph A., and Kutz, J. Nathan
- Subjects
Computer Science - Machine Learning ,I.6.0 ,I.5.0 ,J.2 - Abstract
In many scenarios, it is necessary to monitor a complex system via a time-series of observations and determine when anomalous exogenous events have occurred so that relevant actions can be taken. Determining whether current observations are abnormal is challenging. It requires learning an extrapolative probabilistic model of the dynamics from historical data, and using a limited number of current observations to make a classification. We leverage recent advances in long-term probabilistic forecasting, namely {\em Deep Probabilistic Koopman}, to build a general method for classifying anomalies in multi-dimensional time-series data. We also show how to utilize models with domain knowledge of the dynamics to reduce type I and type II error. We demonstrate our proposed method on the important real-world task of global atmospheric pollution monitoring, integrating it with NASA's Global Earth System Model. The system successfully detects localized anomalies in air quality due to events such as COVID-19 lockdowns and wildfires., Comment: 10 pages, 8 figures
- Published
- 2022
41. Solving nonlinear ordinary differential equations using the invariant manifolds and Koopman eigenfunctions
- Author
-
Morrison, Megan and Kutz, J. Nathan
- Subjects
Mathematics - Dynamical Systems ,Nonlinear Sciences - Exactly Solvable and Integrable Systems ,34A25 (Primary) 34A05, 34A34 (Secondary) - Abstract
Nonlinear ordinary differential equations can rarely be solved analytically. Koopman operator theory provides a way to solve nonlinear systems by mapping nonlinear dynamics to a linear space using eigenfunctions. Unfortunately, finding such eigenfunctions is difficult. We introduce a method for constructing eigenfunctions from a nonlinear ODE's invariant manifolds. This method, when successful, allows us to find analytical solutions for constant coefficient nonlinear systems. Previous data-driven methods have used Koopman theory to construct local Koopman eigenfunction approximations valid in different regions of phase space; our method finds analytic Koopman eigenfunctions that are exact and globally valid. We demonstrate our Koopman method of solving nonlinear systems on 1-dimensional and 2-dimensional ODEs. The nonlinear examples considered have simple expressions for their invariant manifolds which produce tractable analytical solutions. Thus our method allows for the construction of analytical solutions for previously unsolved ordinary differential equations. It also highlights the connection between invariant manifolds and eigenfunctions in nonlinear ordinary differential equations and presents avenues for extending this method to solve more nonlinear systems., Comment: 28 pages, 9 figures
- Published
- 2022
42. Data-driven discovery of governing equations for coarse-grained heterogeneous network dynamics
- Author
-
Owens, Katherine and Kutz, J. Nathan
- Subjects
Mathematics - Dynamical Systems ,34, 37 - Abstract
We leverage data-driven model discovery methods to determine the governing equations for the emergent behavior of heterogeneous networked dynamical systems. Specifically, we consider networks of coupled nonlinear oscillators whose collective behaviour approaches a limit cycle. Stable limit-cycles are of interest in many biological applications as they model self-sustained oscillations (e.g. heart beats, chemical oscillations, neurons firing, circadian rhythm). For systems that display relaxation oscillations, our method automatically detects boundary (time) layer structures in the dynamics, fitting inner and outer solutions and matching them in a data-driven manner. We demonstrate the method on well-studied systems: the Rayleigh Oscillator and the Van der Pol Oscillator. We then apply the mathematical framework to discovering low-dimensional dynamics in networks of semi-synchronized Kuramoto, Rayleigh, Rossler, and Fitzhugh-Nagumo oscillators, as well as heterogeneous combinations thereof. We also provide a numerical exploration of the dimension of collective network dynamics as a function of several network parameters, showing that the discovery of coarse-grained variables and dynamics can be accomplished with the proposed architecture.
- Published
- 2022
43. Effcient magnetometer sensor array selection for signal reconstruction and brain source localization
- Author
-
Yeo, Wan-Jin, Taulu, Samu, and Kutz, J. Nathan
- Subjects
Physics - Medical Physics - Abstract
Magnetoencephalography (MEG) is a noninvasive method for measuring magnetic flux signals caused by brain activity using sensor arrays located on or above the scalp. A common strategy for monitoring brain activity is to place sensors on a nearly uniform grid, or sensor array, around the head. By increasing the total number of sensors, higher spatial-frequency components of brain activity can be resolved as dictated by Nyquist sampling theory. Currently, there are few principled mathematical architectures for sensor placement aside from Nyquist considerations. However, global brain activity often exhibits low-dimensional patterns of spatio-temporal dynamics. The low-dimensional global patterns can be computed from the singular value decomposition and can be leveraged to select a small number of sensors optimized for reconstructing brain signals and localizing brain sources. Moreover, a smaller number of sensors which are systematically chosen can outperform the entire sensor array when considering noisy measurements. We propose a greedy selection algorithm based upon the QR decomposition that is computationally efficient to implement for MEG. We demonstrate the performance of the sensor selection algorithm for the tasks of signal reconstruction and localization. The performance is dependent upon source localization, with shallow sources easily identified and reconstructed, and deep sources more difficult to locate. Our findings suggest that principled methods for sensor selection can improve MEG capabilities and potentially add cost savings for monitoring brain-wide activity.
- Published
- 2022
44. The Experimental Multi-Arm Pendulum on a Cart: A Benchmark System for Chaos, Learning, and Control
- Author
-
Kaheman, Kadierdan, Fasel, Urban, Bramburger, Jason J., Strom, Benjamin, Kutz, J. Nathan, and Brunton, Steven L.
- Subjects
Nonlinear Sciences - Chaotic Dynamics ,Computer Science - Robotics ,Mathematics - Dynamical Systems ,Physics - Physics Education ,B.0 ,D.0 ,E.0 - Abstract
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, from simple harmonic motion in the single pendulum to chaotic dynamics in multi-arm pendulums. Under forcing, even the single pendulum may exhibit chaos, providing a simple example of a damped-driven system. All multi-armed pendulums are characterized by the existence of index-one saddle points, which mediate the transport of trajectories in the system, providing a simple mechanical analog of various complex transport phenomena, from biolocomotion to transport within the solar system. Further, pendulum systems have long been used to design and test both linear and nonlinear control strategies, with the addition of more arms making the problem more challenging. In this work, we provide extensive designs for the construction and operation of a high-performance, multi-link pendulum on a cart system. Although many experimental setups have been built to study the behavior of pendulum systems, such an extensive documentation on the design, construction, and operation is missing from the literature. The resulting experimental system is highly flexible, enabling a wide range of benchmark problems in dynamical systems modeling, system identification and learning, and control. To promote reproducible research, we have made our entire system open-source, including 3D CAD drawings, basic tutorial code, and data. Moreover, we discuss the possibility of extending our system capability to be operated remotely to enable researchers all around the world to use it, thus increasing access., Comment: 72 pages, 39 figures, 9 tables
- Published
- 2022
45. Neural Implicit Flow: a mesh-agnostic dimensionality reduction paradigm of spatio-temporal data
- Author
-
Pan, Shaowu, Brunton, Steven L., and Kutz, J. Nathan
- Subjects
Computer Science - Machine Learning ,Computer Science - Computational Engineering, Finance, and Science - Abstract
High-dimensional spatio-temporal dynamics can often be encoded in a low-dimensional subspace. Engineering applications for modeling, characterization, design, and control of such large-scale systems often rely on dimensionality reduction to make solutions computationally tractable in real-time. Common existing paradigms for dimensionality reduction include linear methods, such as the singular value decomposition (SVD), and nonlinear methods, such as variants of convolutional autoencoders (CAE). However, these encoding techniques lack the ability to efficiently represent the complexity associated with spatio-temporal data, which often requires variable geometry, non-uniform grid resolution, adaptive meshing, and/or parametric dependencies. To resolve these practical engineering challenges, we propose a general framework called Neural Implicit Flow (NIF) that enables a mesh-agnostic, low-rank representation of large-scale, parametric, spatial-temporal data. NIF consists of two modified multilayer perceptrons (MLPs): (i) ShapeNet, which isolates and represents the spatial complexity, and (ii) ParameterNet, which accounts for any other input complexity, including parametric dependencies, time, and sensor measurements. We demonstrate the utility of NIF for parametric surrogate modeling, enabling the interpretable representation and compression of complex spatio-temporal dynamics, efficient many-spatial-query tasks, and improved generalization performance for sparse reconstruction., Comment: 60 pages
- Published
- 2022
46. Walking droplets as a damped-driven system
- Author
-
Rahman, Aminur and Kutz, J. Nathan
- Subjects
Mathematics - Dynamical Systems ,Nonlinear Sciences - Chaotic Dynamics - Abstract
We consider the dynamics of a droplet on a vibrating fluid bath. This hydrodynamic quantum analog system is shown to elicit the canonical behavior of damped-driven systems, including a period doubling route to chaos. By approximating the system as a compositional map between the gain and loss dynamics, the underlying nonlinear dynamics can be shown to be driven by energy balances in the systems. The gain-loss iterative mapping is similar to a normal form encoding for the pattern forming instabilities generated in such spatially-extended system. Similar to mode-locked lasers and rotating detonation engines, the underlying bifurcations persist for general forms of the loss and gain, both of which admit explicit representations in our approximation. Moreover, the resulting geometrical description of the particle-wave interaction completely characterizes the instabilities observed in experiments., Comment: 20 pages, 7 figures
- Published
- 2022
47. Discrepancy Modeling Framework: Learning missing physics, modeling systematic residuals, and disambiguating between deterministic and random effects
- Author
-
Ebers, Megan R., Steele, Katherine M., and Kutz, J. Nathan
- Subjects
Statistics - Machine Learning ,Mathematics - Dynamical Systems - Abstract
Physics-based and first-principles models pervade the engineering and physical sciences, allowing for the ability to model the dynamics of complex systems with a prescribed accuracy. The approximations used in deriving governing equations often result in discrepancies between the model and sensor-based measurements of the system, revealing the approximate nature of the equations and/or the signal-to-noise ratio of the sensor itself. In modern dynamical systems, such discrepancies between model and measurement can lead to poor quantification, often undermining the ability to produce accurate and precise control algorithms. We introduce a discrepancy modeling framework to identify the missing physics and resolve the model-measurement mismatch with two distinct approaches: (i) by learning a model for the evolution of systematic state-space residual, and (ii) by discovering a model for the deterministic dynamical error. Regardless of approach, a common suite of data-driven model discovery methods can be used. The choice of method depends on one's intent (e.g., mechanistic interpretability) for discrepancy modeling, sensor measurement characteristics (e.g., quantity, quality, resolution), and constraints imposed by practical applications (e.g., modeling approaches using the suite of data-driven modeling methods on three continuous dynamical systems under varying signal-to-noise ratios. Finally, we emphasize structural shortcomings of each discrepancy modeling approach depending on error type. In summary, if the true dynamics are unknown (i.e., an imperfect model), one should learn a discrepancy model of the missing physics in the dynamical space. Yet, if the true dynamics are known yet model-measurement mismatch still exists, one should learn a discrepancy model in the state space., Comment: 27 pages, 13 figures
- Published
- 2022
48. Transitions between peace and systemic war as bifurcations in a signed network dynamical system
- Author
-
Morrison, Megan, Kutz, J. Nathan, and Gabbay, Michael
- Subjects
Computer Science - Social and Information Networks ,Physics - Physics and Society ,91D30, 37G99, 37N99, 91C20, 34H20 ,J.4 - Abstract
We investigate structural features and processes associated with the onset of systemic conflict using an approach which integrates complex systems theory with network modeling and analysis. We present a signed network model of cooperation and conflict dynamics in the context of international relations between states. The model evolves ties between nodes under the influence of a structural balance force and a dyad-specific force. Model simulations exhibit a sharp bifurcation from peace to systemic war as structural balance pressures increase, a bistable regime in which both peace and war stable equilibria exist, and a hysteretic reverse bifurcation from war to peace. We show how the analytical expression we derive for the peace-to-war bifurcation condition implies that polarized network structure increases susceptibility to systemic war. We develop a framework for identifying patterns of relationship perturbations that are most destabilizing and apply it to the network of European great powers before World War I. We also show that the model exhibits critical slowing down, in which perturbations to the peace equilibrium take longer to decay as the system draws closer to the bifurcation. We discuss how our results relate to international relations theories on the causes and catalysts of systemic war.
- Published
- 2022
49. The Adaptive Spectral Koopman Method for Dynamical Systems
- Author
-
Li, Bian, Ma, Yi-An, Kutz, J. Nathan, and Yang, Xiu
- Subjects
Mathematics - Dynamical Systems ,37L65 (primary) 65L60 (secondary) - Abstract
Dynamical systems have a wide range of applications in mechanics, electrical engineering, chemistry, and so on. In this work, we propose the adaptive spectral Koopman (ASK) method to solve nonlinear autonomous dynamical systems. This novel numerical method leverages the spectral-collocation (i.e., pseudo-spectral) method and properties of the Koopman operator to obtain the solution of a dynamical system. Specifically, this solution is represented as a linear combination of the multiplication of Koopman operator's eigenfunctions and eigenvalues, and these eigenpairs are approximated by the spectral method. Unlike conventional time evolution algorithms such as Euler's scheme and the Runge-Kutta scheme, ASK is mesh-free, and hence is more flexible when evaluating the solution. Numerical experiments demonstrate high accuracy of ASK for solving one-, two- and three-dimensional dynamical systems., Comment: 31 pages, 13 figures
- Published
- 2022
50. Data-driven sensor placement with shallow decoder networks
- Author
-
Williams, Jan, Zahn, Olivia, and Kutz, J. Nathan
- Subjects
Mathematics - Dynamical Systems - Abstract
Sensor placement is an important and ubiquitous problem across the engineering and physical sciences for tasks such as reconstruction, forecasting and control. Surprisingly, there are few principled mathematical techniques developed to date for optimizing sensor locations, with the leading sensor placement algorithms often based upon the discovery of linear, low-rank sub-spaces and the QR algorithm. QR is a computationally efficient greedy search algorithm which selects sensor locations from candidate positions with maximal variance exhibited in a training data set. More recently, neural networks, specifically shallow decoder networks (SDNs), have been shown to be very successful in mapping sensor measurements to the original high-dimensional state space. SDNs outperform linear subspace representations in reconstruction accuracy, noise tolerance, and robustness to sensor locations. However, SDNs lack principled mathematical techniques for determining sensor placement. In this work, we develop two algorithms for optimizing sensor locations for use with SDNs: one which is a linear selection algorithm based upon QR (Q-SDN), and one which is a nonlinear selection algorithm based upon neural network pruning (P-SDN). Such sensor placement algorithms promise to enhance the already impressive reconstruction capabilities of SDNs. We demonstrate our sensor selection algorithms on two example data sets from fluid dynamics. Moreover, we provide a detailed comparison between our linear (Q-SDN) and nonlinear (P-SDN) algorithms with traditional linear embedding techniques (proper orthogonal decomposition) and QR greedy selection. We show that QR selection with SDNs enhances performance. QR even out-performs our nonlinear selection method that uses magnitude-based pruning. Thus, the combination of a greedy linear selection (QR) with nonlinear encoding (SDN) provides a synergistic combination., Comment: 10 pages, 8 figures, to be submitted to IEEE Sensors Journal
- Published
- 2022
Catalog
Discovery Service for Jio Institute Digital Library
For full access to our library's resources, please sign in.