arXiv subjects

Daniel M. Tartakovsky

Publications and source records attributed to Daniel M. Tartakovsky.

At least 19 recordsLinked to original sources

arXiv2026

TWIG: A Time-Causal Wavelet Operator for Autoregressive Forecasting on Irregular Graphs

We introduce TWIG (Time-Causal Wavelet Operator for Irregular Graphs), a graph-native neural operator for autoregressive surrogate modeling on static irregular graphs. TWIG transforms each node history into causal multiscale temporal features that separate recent variation from progressively slower memory components, then propagates these features through graph-wavelet operator blocks with gated pointwise channel mixing. The architecture is causal by construction and designed for closed-loop forecasting, where predictions are recursively reused as future inputs. We evaluate TWIG on three irregular-domain forecasting problems spanning regional diffusion, three-dimensional subsurface hydrology, and aerodynamic flow, with graphs ranging from 400 to 5,233 nodes and model capacities from approximately 70k to 10M parameters. TWIG achieves the lowest aggregate rollout errors on the subsurface-hydrology and regional-diffusion benchmarks and ranks second on the 10M-parameter aerodynamic-flow benchmark, behind the GPS Transformer. Across all three settings, TWIG consistently outperforms the corresponding non-time-causal Graph WNO baseline. These results demonstrate that TWIG provides an effective and scalable approach to stable autoregressive forecasting of dynamical fields on irregular graphs.

cs.LG↗

arXiv2026

Model predictive control for laser thermal processing: operator learning, closed-loop validation, and out-of-distribution analysis

Laser-based thermal processing, such as laser powder bed fusion, requires tight regulation of the peak surface temperature: heat accumulates where the moving source re-enters previously heated material, driving the temperature out of its process window and causing defects. High-fidelity thermal models capture this physics but are too slow for online optimization, which motivates fast, differentiable, and generalizable surrogates. We develop and validate a complete surrogate-based control pipeline that regulates the maximum surface temperature of a moving laser on a 304-stainless-steel substrate. We also determine conditions under which our surrogate can be trusted inside the control loop by probing its out-of-distribution limits. A key component of our surrogate is a multi-step deep operator network bespoke for moving sources: its branch subnetwork encodes the future power and trajectory (position and velocity) sequence, while its trunk encodes the current peak temperature and the temperature at the future laser locations, yielding a one-shot five-step prediction. By way of illustration, we use this surrogate as a smooth (algebraic-rectifier) nonlinear program inside a receding-horizon model predictive controller solved in CasADi/IPOPT. The surrogate forward pass is over thousand times faster than the equivalent finite-difference steps. We show that aggregate open-loop accuracy is necessary but not sufficient for control-readiness: two surrogates with near-identical offline error behave drastically differently in closed loop. A controlled two-ensemble data design reduces a 91 K path-corner underprediction failure to 1.4 K, and a calibrated one-sided constraint margin of 13 K yields zero violations of the true upper bound on all tested paths.

math.OC↗

arXiv2026

Effects of Wall Roughness on Coupled Flow and Heat Transport in Fractured Media

Heat transfer in fractured media is governed by the interplay between advective transport along rough-walled fractures and conductive transport, both within the fractures and in the surrounding low-permeability matrix. Flow localization induced by aperture heterogeneity, combined with matrix conduction, gives rise to anomalous thermal behavior. To capture these effects, we develop a stochastic modeling framework that couples a time-domain random walk (TDRW) representation of advective and conductive transport in the fractures with a semi-analytical model of conductive heat exchange with the matrix. Matrix trapping times follow a Lévy-Smirnov distribution derived from first-passage theory, capturing the heavy-tailed dynamics typical of fractured systems. Heat flux at the fracture-matrix interface is computed via a nonlocal convolution integral based on Duhamel's principle, accounting for thermal memory effects. The model is validated against analytical benchmarks and finite-element simulations. Monte Carlo simulations over stochastic aperture fields quantify the influence of fracture closure, correlation length, and Péclet number. Results reveal a transition from superdiffusive to subdiffusive regimes, driven by the competition between advective transport along preferential paths, dispersion induced by aperture variability, and matrix-driven heat conduction. In the long-time regime, heat exchange exhibits a characteristic $t^{-1/2}$ decay. At early times, limited thermal penetration into the matrix leads to weaker interfacial fluxes, underscoring the role of matrix thermal inertia. The proposed framework enables physically consistent and computationally efficient simulations of thermal transport in complex fractured systems, with implications for geothermal energy, subsurface thermal storage, and engineered heat exchange in low-permeability environments.

physics.geo-ph↗

arXiv2026

Discovery of Probabilistic Dirichlet-to-Neumann Maps on Graphs

Dirichlet-to-Neumann maps enable the coupling of multiphysics simulations across computational subdomains by ensuring continuity of state variables and fluxes at artificial interfaces. We present a novel method for learning Dirichlet-to-Neumann maps on graphs using Gaussian processes, specifically for problems where the data obey a conservation constraint from an underlying partial differential equation. Our approach combines discrete exterior calculus and nonlinear optimal recovery to infer relationships between vertex and edge values. This framework yields data-driven predictions with uncertainty quantification across the entire graph, even when observations are limited to a subset of vertices and edges. By optimizing over the reproducing kernel Hilbert space norm while applying a maximum likelihood estimation penalty on kernel complexity, our method ensures that the resulting surrogate strictly enforces conservation laws without overfitting. We demonstrate our method on two representative applications: subsurface fracture networks and arterial blood flow. Our results show that the method maintains high accuracy and well-calibrated uncertainty estimates even under severe data scarcity, highlighting its potential for scientific applications where limited data and reliable uncertainty quantification are critical.

cs.LG↗

arXiv2025

Domain-Decomposed Graph Neural Network Surrogate Modeling for Ice Sheets

Accurate yet efficient surrogate models are essential for large-scale simulations of partial differential equations (PDEs), particularly for uncertainty quantification (UQ) tasks that demand hundreds or thousands of evaluations. We develop a physics-inspired graph neural network (GNN) surrogate that operates directly on unstructured meshes and leverages the flexibility of graph attention. To improve both training efficiency and generalization properties of the model, we introduce a domain decomposition (DD) strategy that partitions the mesh into subdomains, trains local GNN surrogates in parallel, and aggregates their predictions. We then employ transfer learning to fine-tune models across subdomains, accelerating training and improving accuracy in data-limited settings. Applied to ice sheet simulations, our approach accurately predicts full-field velocities on high-resolution meshes, substantially reduces training time relative to training a single global surrogate model, and provides a ripe foundation for UQ objectives. Our results demonstrate that graph-based DD, combined with transfer learning, provides a scalable and reliable pathway for training GNN surrogates on massive PDE-governed systems, with broad potential for application beyond ice sheet dynamics.

cs.LG↗

arXiv2025

CODE: A global approach to ODE dynamics learning

Ordinary differential equations (ODEs) are a conventional way to describe the observed dynamics of physical systems. Scientists typically hypothesize about dynamical behavior, propose a mathematical model, and compare its predictions to data. However, modern computing and algorithmic advances now enable purely data-driven learning of governing dynamics directly from observations. In data-driven settings, one learns the ODE's right-hand side (RHS). Dense measurements are often assumed, yet high temporal resolution is typically both cumbersome and expensive. Consequently, one usually has only sparsely sampled data. In this work we introduce ChaosODE (CODE), a Polynomial Chaos ODE Expansion in which we use an arbitrary Polynomial Chaos Expansion (aPCE) for the ODE's right-hand side, resulting in a global orthonormal polynomial representation of dynamics. We evaluate the performance of CODE in several experiments on the Lotka-Volterra system, across varying noise levels, initial conditions, and predictions far into the future, even on previously unseen initial conditions. CODE exhibits remarkable extrapolation capabilities even when evaluated under novel initial conditions and shows advantages compared to well-examined methods using neural networks (NeuralODE) or kernel approximators (KernelODE) as the RHS representer. We observe that the high flexibility of NeuralODE and KernelODE degrades extrapolation capabilities under scarce data and measurement noise. Finally, we provide practical guidelines for robust optimization of dynamics-learning problems and illustrate them in the accompanying code.

cs.LG↗

arXiv2025

Fast Computation of Path Integrals of Killed Processes Using Confined Stochastic Bridges

Expectations of path integrals of killed stochastic processes play a central role in several applications across physics, chemistry, and finance. Simulation-based evaluation of these functionals is often biased and numerically expensive due to the need to explicitly approximate stochastic paths and the challenge of correctly modeling them in the neighborhood of the killing boundary. We consider Itô processes killed at the boundary of some set in the $n$-dimensional space and introduce a novel stochastic method with negligible bias and lower computational cost to evaluate path integrals without simulated paths. Our approach draws a connection between stochastic bridges and killed processes to sample only exit times and locations instead of the full path. We apply it to a Wiener process killed in the $n$-ball and explicitly derive the density of the Brownian bridge confined to the $n$-ball for $n = 1, 2, 3$. Finally, we present two numerical examples that demonstrate the efficiency and negligible bias of the novel procedure compared to an evaluation using the standard Euler-Maruyama method.

math.PR↗

arXiv2025

Lagrangian Liouville models of multiphase flows with randomly forced inertial particles

Eulerian-Lagrangian models of particle-laden (multiphase) flows describe fluid flow and particle dynamics in the Eulerian and Lagrangian frameworks respectively. Regardless of whether the flow is turbulent or laminar, the particle dynamics is stochastic because the suspended particles are subjected to random forces. We use a polynomial chaos expansion (PCE), rather than a postulated constitutive law, to capture structural and parametric uncertainties in the particles' forcing. The stochastic particle dynamics is described by a joint probability density function (PDF) of a particle's position and velocity and random coefficients in the PCE. We deploy the method of distributions (MoD) to derive a deterministic (Liouville-type) partial-differential equation for this PDF. We reformulate this PDF equation in a Lagrangian form, obtaining PDF flow maps and tracing events and their probability in the phase space. That is accomplished via a new high-order spectral scheme, which traces, marginalizes and computes moments of the high-dimensional joint PDF and comports with high-order carrier-phase solvers. Our approach has lower computational cost than either high-order Eulerian solvers or Monte Carlo methods, is not subjected to a CFL condition, does not suffer from Gibbs oscillations and does not require (order-reducing) filtering and regularization techniques. These features are demonstrated on several test cases.

physics.flu-dyn↗

arXiv2025

Transfer Learning on Multi-Dimensional Data: A Novel Approach to Neural Network-Based Surrogate Modeling

The development of efficient surrogates for partial differential equations (PDEs) is a critical step towards scalable modeling of complex, multiscale systems-of-systems. Convolutional neural networks (CNNs) have gained popularity as the basis for such surrogate models due to their success in capturing high-dimensional input-output mappings and the negligible cost of a forward pass. However, the high cost of generating training data -- typically via classical numerical solvers -- raises the question of whether these models are worth pursuing over more straightforward alternatives with well-established theoretical foundations, such as Monte Carlo methods. To reduce the cost of data generation, we propose training a CNN surrogate model on a mixture of numerical solutions to both the $d$-dimensional problem and its ($d-1$)-dimensional approximation, taking advantage of the efficiency savings guaranteed by the curse of dimensionality. We demonstrate our approach on a multiphase flow test problem, using transfer learning to train a dense fully-convolutional encoder-decoder CNN on the two classes of data. Numerical results from a sample uncertainty quantification task demonstrate that our surrogate model outperforms Monte Carlo with several times the data generation budget.

cs.LG↗

arXiv2024

Baseflow identification via explainable AI with Kolmogorov-Arnold networks

Hydrological models often involve constitutive laws that may not be optimal in every application. We propose to replace such laws with the Kolmogorov-Arnold networks (KANs), a class of neural networks designed to identify symbolic expressions. We demonstrate KAN's potential on the problem of baseflow identification, a notoriously challenging task plagued by significant uncertainty. KAN-derived functional dependencies of the baseflow components on the aridity index outperform their original counterparts. On a test set, they increase the Nash-Sutcliffe Efficiency (NSE) by 67%, decrease the root mean squared error by 30%, and increase the Kling-Gupta efficiency by 24%. This superior performance is achieved while reducing the number of fitting parameters from three to two. Next, we use data from 378 catchments across the continental United States to refine the water-balance equation at the mean-annual scale. The KAN-derived equations based on the refined water balance outperform both the current aridity index model, with up to a 105% increase in NSE, and the KAN-derived equations based on the original water balance. While the performance of our model and tree-based machine learning methods is similar, KANs offer the advantage of simplicity and transparency and require no specific software or computational tools. This case study focuses on the aridity index formulation, but the approach is flexible and transferable to other hydrological processes.

cs.LG↗

arXiv2024

Liouville models of particle-laden flow

Langevin (stochastic differential) equations are routinely used to describe particle-laden flows. They predict Gaussian probability density functions (PDFs) of a particle's trajectory and velocity, even though experimentally observed dynamics might be highly non-Gaussian. Our Liouville approach overcomes this dichotomy by replacing the Wiener process in the Langevin models with a (small) set of random variables, whose distributions are tuned to match the observed statistics.

math-ph↗

arXiv2024

High-Precision Geosteering via Reinforcement Learning and Particle Filters

Geosteering, a key component of drilling operations, traditionally involves manual interpretation of various data sources such as well-log data. This introduces subjective biases and inconsistent procedures. Academic attempts to solve geosteering decision optimization with greedy optimization and Approximate Dynamic Programming (ADP) showed promise but lacked adaptivity to realistic diverse scenarios. Reinforcement learning (RL) offers a solution to these challenges, facilitating optimal decision-making through reward-based iterative learning. State estimation methods, e.g., particle filter (PF), provide a complementary strategy for geosteering decision-making based on online information. We integrate an RL-based geosteering with PF to address realistic geosteering scenarios. Our framework deploys PF to process real-time well-log data to estimate the location of the well relative to the stratigraphic layers, which then informs the RL-based decision-making process. We compare our method's performance with that of using solely either RL or PF. Our findings indicate a synergy between RL and PF in yielding optimized geosteering decisions.

cs.LG↗

arXiv2023

Neural oscillators for generalization of physics-informed machine learning

A primary challenge of physics-informed machine learning (PIML) is its generalization beyond the training domain, especially when dealing with complex physical problems represented by partial differential equations (PDEs). This paper aims to enhance the generalization capabilities of PIML, facilitating practical, real-world applications where accurate predictions in unexplored regions are crucial. We leverage the inherent causality and temporal sequential characteristics of PDE solutions to fuse PIML models with recurrent neural architectures based on systems of ordinary differential equations, referred to as neural oscillators. Through effectively capturing long-time dependencies and mitigating the exploding and vanishing gradient problem, neural oscillators foster improved generalization in PIML tasks. Extensive experimentation involving time-dependent nonlinear PDEs and biharmonic beam equations demonstrates the efficacy of the proposed approach. Incorporating neural oscillators outperforms existing state-of-the-art methods on benchmark problems across various metrics. Consequently, the proposed method improves the generalization capabilities of PIML, providing accurate solutions for extrapolation and prediction beyond the training data.

cs.LG↗

arXiv2023

Model discovery for nonautonomous translation-invariant problems

Discovery of mathematical descriptors of physical phenomena from observational and simulated data, as opposed to from the first principles, is a rapidly evolving research area. Two factors, time-dependence of the inputs and hidden translation invariance, are known to complicate this task. To ameliorate these challenges, we combine Lagrangian dynamic mode decomposition with a locally time-invariant approximation of the Koopman operator. The former component of our method yields the best linear estimator of the system's dynamics, while the latter deals with the system's nonlinearity and non-autonomous behavior. We provide theoretical estimators (bounds) of prediction accuracy and perturbation error to guide the selection of both rank truncation and temporal discretization. We demonstrate the performance of our approach on several non-autonomous problems, including two-dimensional Navier-Stokes equations.

math.NA↗

arXiv2023

Neural oscillators for magnetic hysteresis modeling

Hysteresis is a ubiquitous phenomenon in science and engineering; its modeling and identification are crucial for understanding and optimizing the behavior of various systems. We develop an ordinary differential equation-based recurrent neural network (RNN) approach to model and quantify the hysteresis, which manifests itself in sequentiality and history-dependence. Our neural oscillator, HystRNN, draws inspiration from coupled-oscillatory RNN and phenomenological hysteresis models to update the hidden states. The performance of HystRNN is evaluated to predict generalized scenarios, involving first-order reversal curves and minor loops. The findings show the ability of HystRNN to generalize its behavior to previously untrained regions, an essential feature that hysteresis models must have. This research highlights the advantage of neural oscillators over the traditional RNN-based methods in capturing complex hysteresis patterns in magnetic materials, where traditional rate-dependent methods are inadequate to capture intrinsic nonlinearity.

cs.LG↗

arXiv2023

Learning Nonautonomous Systems via Dynamic Mode Decomposition

We present a data-driven learning approach for unknown nonautonomous dynamical systems with time-dependent inputs based on dynamic mode decomposition (DMD). To circumvent the difficulty of approximating the time-dependent Koopman operators for nonautonomous systems, a modified system derived from local parameterization of the external time-dependent inputs is employed as an approximation to the original nonautonomous system. The modified system comprises a sequence of local parametric systems, which can be well approximated by a parametric surrogate model using our previously proposed framework for dimension reduction and interpolation in parameter space (DRIPS). The offline step of DRIPS relies on DMD to build a linear surrogate model, endowed with reduced-order bases (ROBs), for the observables mapped from training data. Then the offline step constructs a sequence of iterative parametric surrogate models from interpolations on suitable manifolds, where the target/test parameter points are specified by the local parameterization of the test external time-dependent inputs. We present a number of numerical examples to demonstrate the robustness of our method and compare its performance with deep neural networks in the same settings.

math.NA↗

arXiv2023

Discovery of sparse hysteresis models for piezoelectric materials

This article presents an approach for modelling hysteresis in piezoelectric materials, that leverages recent advancements in machine learning, particularly in sparse-regression techniques. While sparse regression has previously been used to model various scientific and engineering phenomena, its application to nonlinear hysteresis modelling in piezoelectric materials has yet to be explored. The study employs the least-squares algorithm with a sequential threshold to model the dynamic system responsible for hysteresis, resulting in a concise model that accurately predicts hysteresis for both simulated and experimental piezoelectric material data. Several numerical experiments are performed, including learning butterfly-shaped hysteresis and modelling real-world hysteresis data for a piezoelectric actuator. The presented approach is compared to traditional regression-based and neural network methods, demonstrating its efficiency and robustness. Source code is available at https://github.com/chandratue/SmartHysteresis

cs.LG↗

arXiv2022

Feature-Informed Data Assimilation -- Definitions and Illustrative Examples

We introduce a mathematical formulation of feature-informed data assimilation (FIDA). In FIDA, the information about feature events, such as shock waves, level curves, wavefronts and peak value, in dynamical systems are used for the estimation of state variables and unknown parameters. The observation operator in FIDA is a set-valued functional, which is fundamentally different from the observation operators in conventional data assimilation. Demonstrated in three example, FIDA problems introduced in this note exist in a wide spectrum of applications in science and engineering.

eess.SY↗