Note: When clicking on a Digital Object Identifier (DOI) number, you will be taken to an external site maintained by the publisher.
Some full text articles may not yet be available without a charge during the embargo (administrative interval).
What is a DOI Number?
Some links on this page may take you to non-federal websites. Their policies may differ from this site.
-
Accurate temporal extrapolation presents a fundamental challenge for neural operators in modeling dynamical systems, where reliable predictions must extend significantly beyond the training time horizon. Conventional deep operator network (DeepONet) approaches rely on two inherently limited training paradigms: fixed-horizon rollouts, which predict complete spatiotemporal solutions while disregarding temporal causality, and autoregressive formulations, which accumulate errors through sequential predictions in time. We introduce TI-DeepONet (Time-Integratorembedded Deep Operator Network), a framework that integrates neural operators with adaptive numerical time-stepping techniques to preserve the underlying Markovian structure of dynamical systems while substantially mitigating error propagation in extended temporal forecasting. Our approach reformulates the learning objective from direct state prediction to the approximation of instantaneous time-derivative fields, which are subsequently integrated using established numerical schemes. This design naturally supports continuous-time prediction and enables the use of higher-precision integrators at inference than those employed during training, striking a balance between computational efficiency and predictive accuracy. We further develop TI(L)-DeepONet (Learnable Time-Integrator-embedded Deep Operator Network), which incorporates learnable coefficients for intermediate stages in a multi-stage numerical integration scheme, thereby adapting to solution-specific variations and enhancing predictive fidelity. Rigorous evaluation across six canonical partial differential equations (PDEs) spanning diverse, high-dimensional, chaotic, dissipative, and dispersive dynamics shows that TI(L)-DeepONet marginally outperforms TIDeepONet, with both frameworks achieving significant reductions in relative đż2 extrapolation error: approximately 96.3% compared to autoregressive implementations and 83.6% compared to fixed-horizon approaches. Notably, both methods maintain stable predictions over temporal domains extending to nearly twice the training interval. This research establishes a physics-aware operator learning paradigm that bridges neural approximation with numerical analysis principles, preserving the causal structure of dynamical systems while addressing a critical gap in long-term forecasting of complex physical phenomena.more » « lessFree, publicly-accessible full text available July 1, 2027
-
Early health sciences learners often have limited structured exposure to artificial intelligence/machine learning (AI/ML), research methods, and ethical issues relevant to data-driven healthcare. IGNITE (Innovation, Growth, Network, Integration, Technology, and Ethics) was a one-week interdisciplinary pilot workshop designed to introduce relevant AI/ML methodologies and research literacy. Four pre-pharmacy students in a 2â+â4 PharmD pathway participated in the inaugural workshop at a teaching-intensive institution. A descriptive pre/post evaluation showed increased self-reported confidence across selected AI, ethics, research, and ImageJ-related competencies, with positive participant feedback on relevance, organization, and mentorship. Findings support IGNITE as a feasible and acceptable educational model. Future iterations should include larger cohorts, integrated assessments, longitudinal follow-up, and adaptation for postgraduate health professional learners.more » « lessFree, publicly-accessible full text available June 19, 2027
-
Accurately modeling and inferring solutions to time-dependent partial differential equations (PDEs) over extended temporal horizons remains a core challenge in scientific machine learning. Traditional full rollout (FR) methods, predicting entire trajectories in a single pass, often fail to capture the causal dependencies inherent to dynamical systems and exhibit poor generalization outside the training time horizon. In contrast, autoregressive (AR) approaches, which evolve the system step by step, are prone to error accumulation, as predictions at each time step depend on potentially erroneous prior outputs. These shortcomings limit the long-term accuracy and reliability of both strategies. To overcome these issues, we introduce Physics-Informed Time-Integrated Deep Operator Network (PITI-DeepONet), an operator learning framework designed for stable and accurate long-term time evolution, well beyond the training time horizon. PITI-DeepONet employs a dual-output DeepONet architecture trained via either fully physics-informed or hybrid physics- and data-driven objectives. The training enforces consistency between the learned temporal derivative and its counterpart obtained via automatic differentiation. Rather than directly forecasting future states, the network learns the time-derivative operator from the current state, which is then integrated using classical time-stepping schemes - such as explicit Euler, fourthorder Runge-Kutta, second-order Adams-Bashforth-Moulton, or implicit Euler - to advance the solution sequentially in time. Additionally, the framework supports residual monitoring during inference to estimate prediction quality and flags when the learned temporal tangent becomes unreliable, e.g., outside the training domain. Applied to benchmark problems, PITI-DeepONet demonstrates enhanced accuracy and stability over extended inference time horizons when compared to traditional methods. Mean relative L2 errors reduced by 84% (versus FR) and 79% (versus AR) for the one-dimensional heat equation; by 87% (versus FR) and 98% (versus AR) for the onedimensional Burgers equation; by 42% (versus FR) and 89% (versus AR) for the two-dimensional Allen-Cahn equation; and by 58% (vs. FR) and 61% (vs. AR) for the one-dimensional Kuramoto- Sivashinsky equation. By moving beyond classic FR and AR schemes, PITI-DeepONet paves the way for more reliable, long-term integration of complex, time-dependent PDEs.more » « lessFree, publicly-accessible full text available June 1, 2027
-
Numerical solvers for partial differential equations (PDEs) often struggle to balance computational efficiency with accuracy, especially in multiscale and time-dependent systems. Neural operators offer a promising avenue to accelerate simulations, but their practical deployment is hindered by several challenges: they typically require large volumes of training data generated from highfidelity solvers, tend to accumulate errors over time in dynamical settings, and often exhibit poor generalization in multiphysics scenarios. This work introduces a novel hybrid framework that integrates physics-informed deep operator network (PI-DeepONet) with finite element method (FEM) through domain decomposition and leverages numerical analysis for time marching. The core innovation lies in efficient coupling FEM and DeepONet subdomains via a Schwarz alternating method, expecting to solve complex and nonlinear regions by a pre-trained DeepONet, while the remainder is handled by conventional FEM. To address the challenges of dynamic systems, we embed the Newmark-Beta time-stepping scheme directly into the DeepONet architecture, substantially reducing long-term error propagation. Furthermore, an adaptive subdomain evolution strategy enables the ML-resolved region to expand dynamically, capturing emerging fine-scale features without remeshing. The frameworkâs efficacy has been rigorously validated across a range of solid mechanics problemsâspanning static, quasi-static, and dynamic regimes including linear elasticity, hyperelasticity, and elastodynamicsâdemonstrating accelerated convergence rates (up to 20% improvement in convergence rates compared to conventional FE coupling approaches) while preserving solution fidelity with error margins consistently below 3 %. Our extensive case studies demonstrate that our proposed hybrid solver: (1) reduces computational costs by eliminating fine mesh requirements, (2) mitigates error accumulation in time-dependent simulations, and (3) enables automatic adaptation to evolving physical phenomena. This work establishes a new paradigm for coupling state-of-the-art physics-based and machine learning solvers in a unified framework offering a robust, reliable, and scalable pathway for high-fidelity multiscale simulations.more » « less
-
We present Basis-to-Basis (B2B) operator learning, a novel approach for learning operators on Hilbert spaces of functions based on the foundational ideas of function encoders. We decompose the task of learning operators into two parts: learning sets of basis functions for both the input and output spaces and learning a potentially nonlinear mapping between the coefficients of the basis functions. B2B operator learning circumvents many challenges of prior works, such as requiring data to be at fixed locations, by leveraging classic techniques such as least squares to compute the coefficients. It is especially potent for linear operators, where we compute a mapping between bases as a single matrix transformation with a closed-form solution. Furthermore, with minimal modifications and using the deep theoretical connections between function encoders and functional analysis, we derive operator learning algorithms that are directly analogous to eigen-decomposition and singular value decomposition. We empirically validate B2B operator learning on seven benchmark operator learning tasks and show that it demonstrates a two-orders-of-magnitude improvement in accuracy over existing approaches on several benchmark tasks.more » « less
An official website of the United States government
