J. Nathan Kutz’s research while affiliated with University of Washington and other places

Identifying the governing equations of a dynamical system is one of the most important tasks for scientific modeling. However, this procedure often requires high-quality spatio-temporal data uniformly sampled on structured grids. In this paper, we propose mesh-free SINDy, a novel algorithm which leverages the power of neural network approximation as well as auto-differentiation to identify governing equations from arbitrary sensor placements and non-uniform temporal data sampling. We show that mesh-free SINDy is robust to high noise levels and limited data while remaining computationally efficient. In our implementation, the training procedure is straight-forward and nearly free of hyperparameter tuning, making mesh-free SINDy widely applicable to many scientific and engineering problems. In the experiments, we demonstrate its effectiveness on a series of PDEs including the Burgers' equation, the heat equation, the Korteweg-De Vries equation and the 2D advection-diffusion equation. We conduct detailed numerical experiments on all datasets, varying the noise levels and number of samples, and we also compare our approach to previous state-of-the-art methods. It is noteworthy that, even in high-noise and low-data scenarios, mesh-free SINDy demonstrates robust PDE discovery, achieving successful identification with up to 75% noise for the Burgers' equation using 5,000 samples and with as few as 100 samples and 1% noise. All of this is achieved within a training time of under one minute.

Spatial temporal reconstruction of dynamical system is indeed a crucial problem with diverse applications ranging from climate modeling to numerous chaotic and physical processes. These reconstructions are based on the harmonious relationship between the Koopman operators and the choice of dictionary, determined implicitly by a kernel function. This leads to the approximation of the Koopman operators in a reproducing kernel Hilbert space (RKHS) associated with that kernel function. Data-driven analysis of Koopman operators demands that Koopman operators be closable over the underlying RKHS, which still remains an unsettled, unexplored, and critical operator-theoretic challenge. We aim to address this challenge by investigating the embedding of the Laplacian kernel in the measure-theoretic sense, giving rise to a rich enough RKHS to settle the closability of the Koopman operators. We leverage Kernel Extended Dynamic Mode Decomposition with the Laplacian kernel to reconstruct the dominant spatial temporal modes of various diverse dynamical systems. After empirical demonstration, we concrete such results by providing the theoretical justification leveraging the closability of the Koopman operators on the RKHS generated by the Laplacian kernel on the avenues of Koopman mode decomposition and the Koopman spectral measure. Such results were explored from both grounds of operator theory and data-driven science, thus making the Laplacian kernel a robust choice for spatial-temporal reconstruction.

Reduced-order models (ROMs) are becoming increasingly important for rendering complex and multiscale spatiotemporal dynamics computationally tractable. Computationally efficient ROMs are especially essential for optimized design of technologies as well as for gaining physical understanding. Plasma simulations, in particular those applied to the study of E × B plasma discharges and technologies, such as Hall thrusters for spacecraft propulsion, require substantial computational resources in order to resolve the multidimensional dynamics that span across wide spatial and temporal scales. While high-fidelity computational tools are available, their applications are limited to simplified geometries and narrow conditions, making simulations of full-scale plasma systems or comprehensive parametric studies computationally prohibitive. In addition, experimental setups involve limitations such as the finite spatial resolution of diagnostics and constraints imposed by geometrical accessibility. Consequently, both scientific research and industrial development of plasma systems, including E × B technologies, can greatly benefit from advanced ROM techniques that enable estimating the distributions of plasma properties across the entire system. We develop a model reduction scheme based upon a shallow recurrent decoder (SHRED) architecture using as few measurements of the system as possible. This scheme employs a neural network to encode limited sensor measurements in time (of either local or global properties) and reconstruct full spatial state vector via a shallow decoder network. Leveraging the theory of separation of variables, the SHRED architecture demonstrates the ability to reconstruct complete spatial fields with as few as three-point sensors, including fields dynamically coupled to the measured variables but not directly observed. The effectiveness of the ROMs derived with SHRED is demonstrated across several plasma configurations representative of different geometries in typical E × B plasma discharges and Hall thrusters.

Computationally efficient reduced-order plasma models, able to predict plasma behavior reliably and self-consistently, have remained unachievable so far. The need for these models has nonetheless continuously increased over the past decade for both fundamental studies and engineering applications. With the increase in computational power in recent years and the emergence of several approaches that lower the computational burden of generating extensive high-fidelity plasma datasets, data-driven (DD) dynamics discovery methods can play a transformative role toward the realization of predictive, generalizable and interpretable reduced-order models (ROMs) for plasma systems. In this work, we introduce a novel DD algorithm—the ‘Phi Method’—for the discovery of discretized systems of differential equations describing the dynamics. The success and generalizability of Phi Method is rooted in its constrained regression on a library of candidate terms that is informed by numerical discretization schemes. The Phi Method’s performance is first demonstrated for a one-dimensional plasma problem, representative of the discharge evolution along the azimuthal direction of a typical Hall thruster. Next, we assess the Phi Method’s application toward parametric dynamics discovery, i.e. deriving models that embed parametric variations of the dynamics and in turn aim to provide faithful predictions of the systems’ behavior over unseen parameter spaces. In terms of salient results, we observe that the Phi-method-derived ROM provides remarkably accurate predictions of the evolution dynamics of the involved plasma state variables. The parametric Phi Method is further able to well recover the governing parametric partial differential equation for the adopted plasma test case and to provide accurate predictions of the system dynamics over a wide range of test parameters.

The Shallow Recurrent Decoder networks are a novel paradigm recently introduced for state estimation, combining sparse observations with high-dimensional model data. This architecture features important advantages compared to standard data-driven methods including: the ability to use only three sensors (even randomly selected) for reconstructing the entire dynamics of a physical system; the ability to train on compressed data spanned by a reduced basis; the ability to measure a single field variable (easy to measure) and reconstruct coupled spatio-temporal fields that are not observable and minimal hyper-parameter tuning. This approach has been verified on different test cases within different fields including nuclear reactors, even though an application to a real experimental facility, adopting the employment of in-situ observed quantities, is missing. This work aims to fill this gap by applying the Shallow Recurrent Decoder architecture to the DYNASTY facility, built at Politecnico di Milano, which studies the natural circulation established by internally heated fluids for Generation IV applications, especially in the case of Circulating Fuel reactors. The RELAP5 code is used to generate the high-fidelity data, and temperature measurements extracted by the facility are used as input for the state estimation. The results of this work will provide a validation of the Shallow Recurrent Decoder architecture to engineering systems, showing the capabilities of this approach to provide and accurate state estimation.

The recent developments in data-driven methods have paved the way to new methodologies to provide accurate state reconstruction of engineering systems; nuclear reactors represent particularly challenging applications for this task due to the complexity of the strongly coupled physics involved and the extremely harsh and hostile environments, especially for new technologies such as Generation-IV reactors. Data-driven techniques can combine different sources of information, including computational proxy models and local noisy measurements on the system, to robustly estimate the state. This work leverages the novel Shallow Recurrent Decoder architecture to infer the entire state vector (including neutron fluxes, precursors concentrations, temperature, pressure and velocity) of a reactor from three out-of-core time-series neutron flux measurements alone. In particular, this work extends the standard architecture to treat parametric time-series data, ensuring the possibility of investigating different accidental scenarios and showing the capabilities of this approach to provide an accurate state estimation in various operating conditions. This paper considers as a test case the Molten Salt Fast Reactor (MSFR), a Generation-IV reactor concept, characterised by strong coupling between the neutronics and the thermal hydraulics due to the liquid nature of the fuel. The promising results of this work are further strengthened by the possibility of quantifying the uncertainty associated with the state estimation, due to the considerably low training cost. 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.

Monitoring the atmospheric dispersion of pollutants is increasingly critical for environmental impact assessments. High-fidelity computational models are often employed to simulate plume dynamics, guiding decision-making and prioritizing resource deployment. However, such models can be prohibitively expensive to simulate, as they require resolving turbulent flows at fine spatial and temporal resolutions. Moreover, there are at least two distinct dynamical regimes of interest in the plume: (i) the initial ejection of the plume where turbulent mixing is generated by the shear-driven Kelvin-Helmholtz instability, and (ii) the ensuing turbulent diffusion and advection which is often modeled by the Gaussian plume model. We address the challenge of modeling the initial plume generation. Specifically, we propose a data-driven framework that identifies a reduced-order analytical model for plume dynamics -- directly from video data. We extract a time series of plume center and edge points from video snapshots and evaluate different regressions based to their extrapolation performance to generate a time series of coefficients that characterize the plume's overall direction and spread. We regress to a sinusoidal model inspired by the Kelvin-Helmholtz instability for the edge points in order to identify the plume's dispersion and vorticity. Overall, this reduced-order modeling framework provides a data-driven and lightweight approach to capture the dominant features of the initial nonlinear point-source plume dynamics, agnostic to plume type and starting only from video. The resulting model is a pre-cursor to standard models such as the Gaussian plume model and has the potential to enable rapid assessment and evaluation of critical environmental hazards, such as methane leaks, chemical spills, and pollutant dispersal from smokestacks.

Glasses are traditionally characterized by their rugged landscape of disordered low-energy states and their slow relaxation towards thermodynamic equilibrium. Far from equilibrium, dynamical forms of glassy behavior with anomalous algebraic relaxation have also been noted, e.g., in networks of coupled oscillators. Due to their disordered and high-dimensional nature, such systems have been difficult to study analytically, but data-driven methods are emerging as a promising alternative that may aid in their characterization. Here, we show that the gap between oscillatory and decaying modes in the Koopman spectrum vanishes in systems exhibiting algebraic relaxation. The dynamic mode decomposition, which is a data-driven spectral computation that approximates the Koopman spectrum, thus provides a model-agnostic signature for detecting and analyzing glassy dynamics. We demonstrate the utility of our approach through both a minimal example of one-dimensional ODEs and a high-dimensional example of coupled oscillators.

Reduced Order Modeling is of paramount importance for efficiently inferring high-dimensional spatio-temporal fields in parametric contexts, enabling computationally tractable parametric analyses, uncertainty quantification and control. However, conventional dimensionality reduction techniques are typically limited to known and constant parameters, inefficient for nonlinear and chaotic dynamics, and uninformed to the actual system behavior. In this work, we propose sensor-driven SHallow REcurrent Decoder networks for Reduced Order Modeling (SHRED-ROM). Specifically, we consider the composition of a long short-term memory network, which encodes the temporal dynamics of limited sensor data in multiple scenarios, and a shallow decoder, which reconstructs the corresponding high-dimensional states. SHRED-ROM is a robust decoding-only strategy that circumvents the numerically unstable approximation of an inverse which is required by encoding-decoding schemes. To enhance computational efficiency and memory usage, the full-order state snapshots are reduced by, e.g., proper orthogonal decomposition, allowing for compressive training of the networks with minimal hyperparameter tuning. Through applications on chaotic and nonlinear fluid dynamics, we show that SHRED-ROM (i) accurately reconstructs the state dynamics for new parameter values starting from limited fixed or mobile sensors, independently on sensor placement, (ii) can cope with both physical, geometrical and time-dependent parametric dependencies, while being agnostic to their actual values, (iii) can accurately estimate unknown parameters, and (iv) can deal with different data sources, such as high-fidelity simulations, coupled fields and videos.

The unsupervised and principled diagnosis of multiscale data is a fundamental obstacle in modern scientific problems from, for instance, weather and climate prediction, neurology, epidemiology, and turbulence. Multiscale data are characterized by a combination of processes acting along multiple dimensions simultaneously, spatiotemporal scales across orders of magnitude, nonstationarity, and/or invariances such as translation and rotation. Existing methods are not well-suited to multiscale data, usually requiring supervised strategies such as human intervention, extensive tuning, or selection of ideal time periods. We present the multiresolution coherent spatio-temporal scale separation (mrCOSTS), a hierarchical and automated algorithm for the diagnosis of coherent patterns or modes in multiscale data. mrCOSTS is a variant of dynamic mode decomposition which decomposes data into bands of spatial patterns with shared time dynamics, thereby providing a robust method for analyzing multiscale data. It requires no training but instead takes advantage of the hierarchical nature of multiscale systems. We demonstrate mrCOSTS using complex multiscale datasets that are canonically difficult to analyze: 1) climate patterns of sea surface temperature, 2) electrophysiological observations of neural signals of the motor cortex, and 3) horizontal wind in the mountain boundary layer. With mrCOSTS, we trivially retrieve complex dynamics that were previously difficult to resolve while additionally extracting hitherto unknown patterns of activity embedded in the dynamics, allowing for advancing the understanding of these fields of study. This method is an important advancement for addressing the multiscale data which characterize many of the grand challenges in science and engineering.