Search NASA⌕ Search

SEARCH · Search NASA

Results for “Adaptive learning”

Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 19 records
All sourcesNASA NTRSDOE OSTI
DOE OSTI2026

A score-based diffusion model approach for adaptive learning of stochastic partial differential equation solutions

In this paper, we propose a novel framework for adaptively learning the time-evolving solutions of stochastic partial differential equations (SPDEs) using score-based diffusion models within a recursive Bayesian inference setting. SPDEs play a central role in modeling complex physical systems under uncertainty, but their numerical solutions often suffer from model errors and reduced accuracy due to incomplete physical knowledge and environmental variability. To address these challenges, we encode the governing physics into the score function of a diffusion model using simulation data and incorporate observational information via a likelihood-based correction in a reverse-time stochastic differential equation. This enables adaptive learning through iterative refinement of the solution as new data becomes available. To improve computational efficiency in high-dimensional settings, we introduce the ensemble score filter, a training-free approximation of the score function designed for real-time inference. Numerical experiments on benchmark SPDEs demonstrate the accuracy and robustness of the proposed method under sparse and noisy observations.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2026

Learned adaptive properties for mitigation of weight perturbations in embedded spiking networks

Recent years have seen an increased importance of neural network inference in edge-based scenarios, which impose size and power constraints requiring novel computing devices. These same edge scenarios may require operating over long periods of time, or exposure to extreme environments, resulting in a drift of neural network weights that cause degraded performance. In searching for ways to develop neural network approaches that perform robustly under these conditions, we propose a biologically-inspired mechanism for the dynamic adaptation of within-neuron parameters that is guided by a global context signal carrying information about perturbations and variability in incoming stimuli. Specifically, we demonstrate that adaptive voltage thresholds or neuronal time constants, when informed by a global context signal, can enable network-level mechanisms to recover from perturbed synaptic weights. Consistent with prior literature, the context-modulated approach is effective for recurrent, but not feedforward networks, by modulating network level dynamics. We demonstrate this approach successfully recovers performance in image classification tasks and spatiotemporal tracking tasks under idealized and Gaussian noise as well as for realistic perturbations from a memristive device when exposed to ionizing radiation. Finally, we discuss how this approach enables the design of robust and energy-efficient neuromorphic systems that perform well, even in resource-constrained scenarios with extreme environments such as edge processing.

context modulation↗
DOE OSTI2026

Adaptive Reinforcement Learning Control for Power Distribution in Multi-Output Resonant Converters

This paper presents an adaptive reinforcement learning (ARL)-based control framework for efficient power distribution in a multi-output resonant converter for UAV applications. The proposed system is based on a high-frequency isolated resonant architecture, where a single energy source supplies multiple propulsion loads through independently controlled output rectifiers, addressing the need for coordinated multi-motor power management. The ARL framework dynamically allocates output power by learning optimal phase-shift control actions under varying load demands and operating conditions. The agent autonomously determines control parameters that maximize conversion efficiency while ensuring accurate power sharing among multiple outputs. In addition, the proposed approach enables adaptive operation without requiring detailed system modeling or manual tuning. Experimental results demonstrate stable and efficient performance over a wide range of operating conditions, confirming the effectiveness and robustness of the learning-based control strategy for multi-output resonant converter system.

Asa, Erdem [ORNL] (ORCID:0000000190884812)↗
DOE OSTI2026

Adaptive Reinforcement Learning (ARL) Control of a Multi-port Resonant Converter in UAV Systems

This study presents an adaptive reinforcement learning (ARL) control framework for a multi-port resonant converter used in hybrid unmanned aerial vehicle (UAV) power systems. The converter integrates high-frequency half-bridge input ports connected to a rectified engine–generator set and a battery energy storage system, along with a semi-bridgeless active rectifier supplying the propulsion load. A deep RL agent is trained to dynamically regulate inter-port phase-shift commands in real time based on flight conditions and load power demand. The ARL controller autonomously identifies phase-shift combinations that maximize conversion efficiency while maintaining stable and coordinated power flow, even under rapidly varying operating scenarios. This data-driven approach eliminates the need for explicit system modeling or extensive manual tuning and enables coordinated control among multiple power ports without inter-port communication. Experimental results validate that the ARL based strategy achieves reliable power sharing and consistently high-efficiency operation across diverse UAV operating conditions.

Asa, Erdem [ORNL] (ORCID:0000000190884812)↗
DOE OSTI2026

TANTE: Time-adaptive operator learning via neural Taylor expansion

Operator learning for time-dependent partial differential equations (PDEs) has seen rapid progress in recent years, enabling efficient approximation of complex spatiotemporal dynamics. However, most existing methods rely on fixed time step sizes during rollout, which limits their ability to adapt to varying temporal complexity and often leads to error accumulation. In this work, we propose the Time-Adaptive Transformer with Neural Taylor Expansion (TANTE), a novel operator-learning framework that produces continuous-time predictions with adaptive step sizes. TANTE predicts future states by performing a Taylor expansion at the current state, where neural networks learn both the higher-order temporal derivatives and the local radius of convergence. This allows the model to dynamically adjust its rollout based on the local behavior of the solution, thereby reducing cumulative error and improving computational efficiency. We demonstrate the effectiveness of TANTE across a wide range of PDE benchmarks, achieving superior accuracy and adaptability compared to fixed-step baselines, delivering accuracy gains of 60-80 % and speed-ups of 30-40 % at inference time.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2025

Adaptive Graph Learning with Transformer for Multi-Reservoir Inflow Prediction

Reservoir inflow prediction is crucial for water resource management, yet existing approaches mainly focus on single-reservoir models that ignore spatial dependencies among interconnected reservoirs. We introduce AdaTrip as an adaptive, time-varying graph learning framework for multi-reservoir inflow forecasting. AdaTrip constructs dynamic graphs where reservoirs are nodes with directed edges reflecting hydrological connections, employing attention mechanisms to automatically identify crucial spatial and temporal dependencies. Evaluation on thirty reservoirs in the Upper Colorado River Basin demonstrates superiority over existing baselines, with improved performance for reservoirs with limited records through parameter sharing. Additionally, AdaTrip provides interpretable attention maps at edge and time-step levels, offering insights into hydrological controls to support operational decision-making. Our code is available at https://github.com/humphreyhuu/AdaTrip.

Hu, Pengfei [ORNL] (ORCID:0009000367130950)↗
DOE OSTI2025

A resolution independent neural operator

The Deep operator network (DeepONet) is a powerful yet simple neural operator architecture that utilizes two deep neural networks to learn mappings between infinite-dimensional function spaces. This architecture is highly flexible, allowing the evaluation of the solution field at any location within the desired domain. However, it imposes a strict constraint on the input space, requiring all input functions to be discretized at the same locations; this limits its practical applications. Here, in this work, we introduce a general framework for operator learning from input–output data with arbitrary number and locations of sensors. This begins by introducing a resolution-independent DeepONet (RI-DeepONet), enabling it to handle input functions that are arbitrarily, but sufficiently finely, discretized. To this end, we propose two dictionary learning algorithms to adaptively learn a set of appropriate continuous basis functions, parameterized as implicit neural representations (INRs), from correlated signals defined on arbitrary point cloud data. These basis functions are then used to project arbitrary input function data as a point cloud onto an embedding space (i.e., a vector space of finite dimensions) with dimensionality equal to the dictionary size, which can be directly used by DeepONet without any architectural changes. In particular, we utilize sinusoidal representation networks (SIRENs) as trainable INR basis functions. The introduced dictionary learning algorithms are then used in a similar way to learn an appropriate dictionary of basis functions for the output function data, which defines a new neural operator architecture referred to as the R esolution I ndependent N eural O perator (RINO). In the RINO, the operator learning task simplifies to learning a mapping from the coefficients of input basis functions to the coefficients of output basis functions. We demonstrate the robustness and applicability of RINO in handling arbitrarily (but sufficiently richly) sampled input and output functions during both training and inference through several numerical examples.

Deep operator network (DeepONet)↗
DOE OSTI2025

Reinforcement Learning‐Based Adaptation of Grid Following Inverter's Internal Controller to Networked Microgrids' Strengths

The varying topological configurations, generator commitments and dispatches, and dynamic load demand lead to changing system's strengths during the operations of networked microgrids. When the system's strengths significantly change, the fixed control gains at large devices may result in unsatisfactory system performance; this necessitates the tuning of the control gains at large devices to adapt to the changing system's strengths. In this paper, observer-based reinforcement learning (RL) is utilised to automatically tune the proportional-integral (PI) gains of phase lock loop (PLL) controller of grid-following (GFL) inverters to adapt to the changing strengths of microgrids and networked microgrids. The RL agent in this framework augments an observer predicting system's strengths, from which the RL control policy will adjust accordingly to tune the PLL controller's gains towards the system's strengths. Also, to enhance the control performance, the recently introduced Barrier function-based RL framework is leveraged for the design of reward function to prevent the high frequency nadir. An operational 26 kV electric distribution system, which is modelled as networked microgrids, is used to illustrate the need and effectiveness of the proposed RL-tuned control.

frequency response↗
DOE OSTI2025

Learning with Adaptive Conservativeness for Distributionally Robust Optimization: Incentive Design for Voltage Regulation

Information asymmetry between the Distribution System Operator (DSO) and Distributed Energy Resource Aggregators (DERAs) obstructs designing effective incentives for voltage regulation. To capture this effect, we employ a Stackelberg game-theoretic framework, where the DSO seeks to overcome the information asymmetry and refine its incentive strategies by learning from DERA behavior over multiple iterations. We introduce a model-based online learning algorithm for the DSO, aimed at inferring the relationship between incentives and DERA responses. Given the uncertain nature of these responses, we also propose a distributionally robust incentive design model to control the probability of voltage regulation failure and then reformulate it into a convex problem. This model allows the DSO to periodically revise distribution assumptions on uncertain parameters in the decision model of the DERA. Finally, we present a gradient-based method that permits the DSO to adaptively modify its conservativeness level, measured by the size of a Wasserstein metric-based ambiguity set, according to historical voltage regulation performance. The effectiveness of our proposed method is demonstrated through numerical experiments.

adaptation models↗
DOE OSTI2024

Learning with Adaptive Conservativeness for Distributionally Robust Optimization: Incentive Design for Voltage Regulation: Preprint

Information asymmetry between the Distribution System Operator (DSO) and Distributed Energy Resource Aggregators (DERAs) obstructs designing effective incentives for voltage regulation. To capture this effect, we employ a Stackelberg game-theoretic framework, where the DSO seeks to overcome the information asymmetry and refine its incentive strategies by learning from DERA behavior over multiple iterations. We introduce a model-based online learning algorithm for the DSO, aimed at inferring the relationship between incentives and DERA responses. Given the uncertain nature of these responses, we also propose a distributionally robust incentive design model to control the probability of voltage regulation failure and then reformulate it into a convex problem. This model allows the DSO to periodically revise distribution assumptions on uncertain parameters in the decision model of the DERA. Finally, we present a gradient-based method that permits the DSO to adaptively modify its conservativeness level, measured by the size of a Wasserstein metric-based ambiguity set, according to historical voltage regulation performance. The effectiveness of our proposed method is demonstrated through numerical experiments.

distribution system operator↗
DOE OSTI2025

Deep-learning-based domain adaptation for cavity fault prediction at Jefferson Laboratory

Superconducting radio-frequency (SRF) cavities are the core components of the Continuous Electron Beam Accelerator Facility (CEBAF) at Jefferson Lab, providing high-power electron beams for nuclear physics experiments. The facility comprises 418 SRF cavities, and any fault in these cavities can lead to interruptions in the electron beam supply. Cavity faults are the leading cause of beam trips in CEBAF. Predicting and mitigating those faults before onset can help maintain normal operation. Existing models face challenges in distinguishing between normal and fault signals when changes occur in the underlying time-series data, from changes in control software, operational parameters, or the environment. This work proposes a deep learning domain adaptation model that leverages transfer learning to address fault prediction challenges by improving accuracy. The model is trained and fine-tuned using a dataset collected for faulty and normal operation using a data acquisition system in CEBAF. Our deep learning-based domain adaptation model achieves a prediction accuracy of 89.61% of the fault and normal signals. The developed model effectively predicts normal running signals compared to the baseline approach without domain adaptation. This capacity is essential for the fault prediction task in the CEBAF because of heavily imbalanced data containing vast amounts of normal signals. The model performs well for predicting faults several hundred milliseconds before the fault onset compared to other models where no adaptation is applied. Incorporating deep learning-based domain adaptation techniques will significantly improve the fault prediction performance.

Rahman, Md Monibor [Old Dominion Univ., Norfolk, V↗
DOE OSTI2025

Criticality analysis of nuclear binding energy neural networks

Machine learning methods, in particular deep learning methods such as artificial neural networks (ANNs) with many layers, have become widespread and useful tools in nuclear physics. However, these ANNs are typically treated as ‘black boxes’, with their architecture (width, depth, and weight/bias initialization) and the training algorithm and parameters chosen empirically by optimizing learning based on limited exploration. We test a non-empirical approach to understanding and optimizing nuclear physics ANNs by adapting a criticality analysis based on renormalization group flows in terms of the hyperparameters for weight/bias initialization, training rates, and the ratio of depth to width. This treatment utilizes the statistical properties of neural network initialization to find a generating functional for network outputs at any layer, allowing for a path integral formulation of the ANN outputs as a Euclidean statistical field theory. We use a prototypical example to test the applicability of this approach: a simple ANN for nuclear binding energies. We find that with training using a stochastic gradient descent optimizer, the predicted criticality behavior is realized, and optimal performance is found with critical tuning. However, the use of an adaptive learning algorithm leads to somewhat superior results without concern for tuning and thus obscures the analysis. Nevertheless, the criticality analysis offers a way to look within the black box of ANNs, which is a first step towards potential improvements in network performance beyond using adaptive optimizers.

artificial neural network↗
DOE OSTI2025

Geometry-aware framework for deep energy method: An application to structural mechanics with hyperelastic materials

Here, in this work, we introduce a novel physics-informed framework named the Geometry-Aware Deep Energy Method (GADEM) for solving structural mechanics problems on different geometries. As the weak form of the physical system equation (or the energy-based approach) has demonstrated clear advantages compared to the strong form for solving solid mechanics problems, GADEM employs the weak form and aims to infer the solution on multiple shapes of geometries. Integrating a geometry-aware framework into an energy-based method results in an effective physics-informed deep learning model in terms of accuracy and computational cost. Different ways to represent the geometric information and to encode the geometric latent vectors are investigated in this work. We introduce a loss function of GADEM which is minimized based on the potential energy of all considered geometries. An adaptive learning method is also employed for the sampling of collocation points to enhance the performance of GADEM. We present some applications of GADEM to solve solid mechanics problems, including a loading simulation of a toy tire involving contact mechanics and large deformation hyperelasticity. The numerical results of this work demonstrate the remarkable capability of GADEM to infer the solution on various and new shapes of geometries using only one trained model.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2025

OmniXAS: A universal deep-learning framework for materials x-ray absorption spectra

X-ray absorption spectroscopy (XAS) is a powerful characterization technique for probing the local chemical environment of absorbing atoms. However, analyzing XAS data presents significant challenges, often requiring extensive, computationally intensive simulations, as well as significant domain expertise. These limitations hinder the development of fast, robust XAS analysis pipelines that are essential in high-throughput studies and for autonomous experimentation. Here, we address these challenges with OmniXAS, a framework that contains a suite of transfer learning approaches for XAS prediction, each uniquely contributing to improved accuracy and efficiency, as demonstrated on the K-edge spectra database covering eight 3⁢d transition metals (Ti–Cu). The OmniXAS framework is built upon three distinct strategies. First, we use M3GNet [Nat. Comput. Sci. 2, 718 (2022)] to derive latent representations of the local chemical environment of absorption sites as input for XAS prediction, achieving significant improvements over conventional featurization techniques. Second, we employ a hierarchical transfer learning strategy, training a universal multitask model across elements before fine-tuning for element-specific predictions. Models based on this cascaded approach after elementwise fine-tuning outperform element-specific models by up to 69%. Third, we implement cross-fidelity transfer learning, adapting a universal model to predict spectra generated by simulation of a different fidelity with a much higher computational cost. This approach improves prediction accuracy by up to 11% over models trained on the target fidelity alone. Our approach significantly boosts the throughput of XAS modeling by orders of magnitude as compared to first-principles simulations and is extendable to XAS prediction for a broader range of elements. The proposed transfer learning framework is generalizable to enhance deep-learning models that target other properties in materials research.

36 MATERIALS SCIENCE↗
DOE OSTI2026

Protonation Dynamics of Confined Ethanol–Water Mixtures in H-ZSM-5 from Machine Learning-Driven Metadynamics

Zeolites are indispensable heterogeneous catalysts in industrial chemical processes, valued for their strong Brønsted acidity, well-defined microporous frameworks, and tunable pore structures. Their catalytic activity arises primarily from Brønsted acid sites (BAS), typically present as bridging hydroxyl groups (Si–OH–Al). Under aqueous reaction conditions, these protons interact dynamically with water and alcohol molecules, leading to complex solvation and protonation behavior within confined pores. In this study, we investigate the protonation equilibrium occurring between ethanol and water at the BAS of acidic zeolites under varying hydration levels, i.e., C2H5OH–(H2O)n, n=1–4. Local structure was analyzed through an adaptive-learning global optimization algorithm, while enhanced sampling molecular dynamics simulations with Well-Tempered Metadynamics (WMetaD) and machine learning interatomic potentials (MLPs) provide free-energy surfaces (FES) at variable hydration levels. The results reveal a strong dependence of proton localization on the degree of hydration. At low hydration (1 water molecule), the proton resides predominantly on ethanol; with 2 water molecules, it shifts toward water, and at higher hydration (3 or more water molecules), it becomes extensively delocalized over the water cluster. These findings underscore the critical role of solvation in modulating acid site behavior and suggest that a minimum of three water molecules is necessary to fully stabilize the proton on water within the zeolite framework. This solvation threshold has significant implications for catalytic processes, particularly in biomass conversion reactions where alcohol protonation is a key step in dehydration mechanisms.

machine learning↗
DOE OSTI2024

Pairing a Global Optimization Algorithm with EXAFS to Characterize Lanthanide Structure in Solution

Ensemble-average sampling of structures from ab initio molecular dynamics (AIMD) simulations can be used to predict theoretical extended X-ray absorption fine structure (EXAFS) signals that closely match experimental spectra. However, AIMD simulations are time-consuming and resource-intensive, particularly for solvated lanthanide ions, which often form multiple nonrigid geometries with high coordination numbers. Here, to accelerate the characterization of lanthanide structures in solution, we employed the Northwest Potential Energy Surface Search Engine (NWPEsSe), an adaptive-learning global optimization algorithm, to efficiently screen first-shell structures. As case studies, we examine two systems: Eu(NO 3 ) 3 dissolved in acetonitrile with a terpyridine ligand (terpyNO 2 ), and Nd(NO 3 ) 3 dissolved in acetonitrile. The theoretical spectra for structures identified by NWPEsSe were compared to both experimental and AIMD-derived EXAFS spectra. The NWPEsSe algorithm successfully identified the proper solvation structure for both Eu(NO 3 ) 3 (terpyNO 2 ) and Nd(NO 3 )(acetonitrile) 3 , with the calculated EXAFS signals closely matching the experimental spectra for the Eu-ligand complex and showing good similarity for the Nd salt; the better agreement with the ligand-containing structure is attributed to a less dynamic coordination environment due to the rigid ligand. The key advantage of the global optimization algorithm lies in its ability to sample the coordination environment across the potential energy surface and reduce the time required to identify structures from generally a month to within a week. Additionally, this approach is versatile and can be adapted to characterize main-group metal complexes.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2025

Emulation of Synaptic Plasticity in WO 3 ‐Based Ion‐Gated Transistors

Neuromorphic systems, inspired by the human brain, promise significant advancements in computational efficiency and power consumption by integrating processing and memory functions, thereby addressing the von Neumann bottleneck. This paper explores the synaptic plasticity of a WO3-based ion-gated transistor (IGT) in [EMIM][TFSI] and a 0.1 mol L −1 LiTFSI in [EMIM][TFSI] for neuromorphic computing applications. Cyclic voltammetry (CV), transistor characteristics, and atomic force microscopy (AFM) force–distance (FD) profiling analyses reveal that Li + brings about ion intercalation, together with higher mobility and conductance, and slower response time (τ). WO 3 IGTs exhibit spike amplitude-dependent plasticity (SADP), spike number-dependent plasticity (SNDP), spike duration-dependent plasticity (SDDP), frequency-dependent plasticity (FDP), and paired-pulse facilitation (PPF), which are all crucial for mimicking biological synaptic functions and understanding how to achieve different types of plasticity in the same IGT. The findings underscore the importance of selecting the appropriate ionic medium to optimize the performance of synaptic transistors, enabling the development of neuromorphic systems capable of adaptive learning and real-time processing, which are essential for applications in artificial intelligence (AI).

36 MATERIALS SCIENCE↗
DOE OSTI2025

A randomized sketching trust-region secant method for low-memory dynamic optimization

The numerical solution of dynamic optimization problems is often limited by the memory required to store the state trajectory, which is used to evaluate the objective function and its derivatives. Recently, [R. Muthukumar et al., SIAM Journal on Optimization 31(2), pp. 1242–1275 (2021)] introduced a trust-region method for dynamic optimization that employs randomized sketching to compress the state trajectory, resulting in inexact derivative computations. By adaptively learning the sketch rank, the trust-region algorithm achieves rigorous convergence guarantees. Here, we extend this approach to use secant Hessian approximations. Due to the randomness introduced by the sketch, the traditional secant update formulae can produce poor Hessian approximations. In particular, the difference of two gradients, computed from two different sketches, may be inconsistent. To overcome this, we employ a sketched approximation of the Hessian application, in lieu of computing the gradient difference. We numerically demonstrate the improved stability of this approach on an example from PDE-constrained optimization.

dynamic optimization↗