Search NASA⌕ Search

SEARCH · Search NASA

Results for “learning dynamics”

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 253 records · Page 14
All sourcesNASA NTRSDOE OSTI
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 OSTI2025

Weighted active space protocol for multireference machine-learned potentials

Multireference methods such as multiconfiguration pair-density functional theory accurately capture electronic correlation in systems with strong multiconfigurational character, but their cost precludes direct use in molecular dynamics. Combining these methods with machine-learned interatomic potentials (MLPs) can extend their reach. However, the sensitivity of multireference calculations to the choice of the active space complicates the consistent evaluation of energies and gradients across structurally diverse nuclear configurations. To overcome this limitation, we introduce the weighted active space protocol (WASP), a systematic approach to assign a consistent active space for a given system across uncorrelated configurations. By integrating WASP with MLPs and enhanced sampling techniques, we propose a data-efficient active learning cycle that enables the training of an MLP on multireference data. We demonstrated the approach on the TiC + -catalyzed C–H activation of methane, a reaction that poses challenges for Kohn–Sham density functional theory due to its significant multireference character. This framework enables accurate and efficient modeling of catalytic dynamics, establishing a paradigm for simulating complex reactive processes beyond the limits of conventional electronic-structure methods.

enhanced sampling↗
DOE OSTI2026

A Physics-Informed Reinforcement Learning Framework for Economic-Thermal Co-Optimization of Crypto Mining Data Centers: Preprint

The rapid expansion of cryptocurrency mining has created a new class of high-density data centers characterized by extreme thermal flux and high sensitivity to volatile economic markets. Traditional thermal management strategies, typically reliant on rule-based control, maintain static setpoints that fail to account for fluctuating electricity prices and cryptocurrency values - factors critical to mining profitability. To address this, we present a physics-informed reinforcement learning (PIRL) framework for economic-thermal co-optimization in crypto mining data centers. This framework consists of a proximal policy optimization (PPO) agent, a virtual testbed powered by high-fidelity physics-based models, and an interactive frontend dashboard. The PPO agent is trained using the virtual testbed and strict hardware safety limits. This physics-informed approach allows the agent to learn a stochastic policy that dynamically balances mining revenue against operational costs by co-optimizing HVAC cooling setpoints and IT computational hashrate. The simulation results demonstrate that the integrated framework achieved an 8.62% increase in net operational profit compared to traditional baseline strategies while strictly adhering to safety-critical temperature constraints (coolant supply temperature < 32 degrees C). This work provides a scalable template for the deployment of reinforcement learning in mission critical facilities where economic volatility and physical safety must be managed simultaneously.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗
DOE OSTI2025

Real-time tracking and analysis of gas bubble dynamics in laser powder bed fusion using in-situ X-ray characterization and machine learning

Porosity defects remain a significant challenge in the laser powder bed fusion (LPBF) process, adversely affecting the mechanical properties and reliability of additively manufactured components. Here, this study investigates the real-time formation and trajectory of gas bubbles during LPBF of Al6061 alloy using advanced in-situ X-ray characterization and machine learning. The unsupervised Gaussian mixture model and particle tracking algorithm developed are able to precisely track and quantify the properties of gas bubbles and keyhole pores. Our analysis identified five distinct types of gas bubble formation and movement patterns, emphasizing the diverse origins and behaviors of these defects. It enables precise quantification of trajectories, velocities, and morphological changes of gas bubbles, offering a granular view of the subsurface dynamics within the melt pool. Additionally, we explored keyhole-induced pore dynamics, revealing the critical role of keyhole oscillation and collapse for the formation of both large and small gas pores. It defines four different regions of gas bubble movement within the melt pool, providing a clearer understanding of how local fluid dynamics affect pore behavior. The results underscore the importance of integrating in-situ experimental observation and automated machine learning to develop a more robust predictive model for defect formation in LPBF.

In-situ X-ray imaging↗
DOE OSTI2024

Unexpected Observation of Disorder and Multiple Phase-Transition Pathways in Shock-Compressed Zr

The response of materials under dynamic compression involves a complex interplay of various deformation mechanisms aimed at relieving shear stresses, yielding a remarkable diversity in material behavior. Here, in this Letter, we utilize femtosecond x-ray diffraction coupled with nanosecond laser compression to reveal an intricate competition between multiple shear-relieving mechanisms within an elemental metal. Our observations in shocked-compressed single-crystal Zr indicate a disorder-mediated shear relaxation at lower pressures. Above the phase-transition pressure, we observe the increasing contribution of structural phase transition in relieving shear stress. We detect not one but three concurrent pathways during the transition from the hcp to a hex-3 structure. These complex dynamics are partially corroborated through multimillion-atom molecular dynamics simulations employing a machine-learned interatomic potential. Our observation of multiple concurrent pathways and disorder during shock compression underscore the far greater intricacies in the dynamic response of metals than previously assumed.

75 CONDENSED MATTER PHYSICS, SUPERCONDUCTIVITY AND↗
DOE OSTI2024

Integrating machine learning interatomic potentials with hybrid reverse Monte Carlo structure refinements in RMCProfile

Structure refinement with reverse Monte Carlo (RMC) is a powerful tool for interpreting experimental diffraction data. To ensure that the under-constrained RMC algorithm yields reasonable results, the hybrid RMC approach applies interatomic potentials to obtain solutions that are both physically sensible and in agreement with experiment. To expand the range of materials that can be studied with hybrid RMC, we have implemented a new interatomic potential constraint in RMCProfile that grants flexibility to apply potentials supported by the Large-scale Atomic/Molecular Massively Parallel Simulator ( LAMMPS ) molecular dynamics code. This includes machine learning interatomic potentials, which provide a pathway to applying hybrid RMC to materials without currently available interatomic potentials. To this end, we present a methodology to use RMC to train machine learning interatomic potentials for hybrid RMC applications.

Cuillier, Paul↗
DOE OSTI2026

A transfer learning approach to energy-efficient control of small and medium-sized commercial buildings

Model-free reinforcement learning (RL) provides a data-driven and adaptive approach to optimize building energy use while satisfying occupant comfort. This powerful tool does not need any prior knowledge about the environment and system it is optimizing and can adapt its policy based on the changes in captures. Like any other data-driven tool, it faces high training costs due to the extensive agent-environment interactions required to capture long-term building dynamics and user comfort. Transfer learning, particularly policy distillation, offers a promising way to accelerate training by leveraging pretrained RL agents in different building and system types. Here, this study investigates online student distillation, in which the student model updates its neural network weights using outputs from teacher models. The work introduces a student distillation strategy designed for efficient knowledge transfer, along with a teacher selection method that ensures high-quality guidance. The approach is validated using a highly calibrated whole building energy model for a small/medium commercial building test facility. Results show substantial reductions in training time and data requirements while surpassing the performance of ASHRAE Guideline 36, an advanced rule-based control strategy. The distilled RL model required 45% less data and achieved 20% higher cumulative rewards than a state-of-the-art RL model, with faster convergence and lower energy consumption. These outcomes demonstrate that effective transfer learning enables a scalable and data-efficient energy management solution for commercial buildings.

ASHRAE guideline 36↗
DOE OSTI2024

Unusual dynamics of tetrahedral liquids caused by the competition between dynamic heterogeneity and structural heterogeneity

Tetrahedral liquids exhibit intriguing thermodynamic and transport properties because of the various ways tetrahedra can be packed and connected. Recently, an unusual temperature dependence of the stretching exponent β in a model tetrahedral liquid ZnCl 2 from T m + 85 K to T m + 35 K has been reported using neutron-spin echo spectroscopy. This discovery stands in sharp contrast to other glass-forming liquids. In this study, we conducted neural network force field driven molecular dynamic simulations of ZnCl 2 . We found a non-monotonic temperature dependence of β from liquid to supercooled liquid temperatures. Further structural decomposition and dynamic analysis suggest that this unusual dynamic behavior is a result of the competition between the decrease in the diversity of tetrahedra motifs (structural heterogeneity) and the increase in glassy dynamic heterogeneity. Furthermore, this result may contribute to new understandings of the structural relaxation of other network liquids.

36 MATERIALS SCIENCE↗
DOE OSTI2024

Unveiling the Potential of MeshGraphNets for Predicting Subsurface Evolution in Carbon Storage Projects

This is the conference paper accompanying an oral presentation “Unveiling the Potential of MeshGraphNets for Predicting Subsurface Evolution in Carbon Storage Projects” at the 17th International Conference on Greenhouse Gas Control Technologies GHGT-17 held in Calgary, Canada, October 20-24 , 2024. Carbon capture and storage (CCS) technology is critical for mitigating climate change but requires effective subsurface reservoir management to ensure safe containment of injected CO2. Accurate predictions of reservoir pressure and saturation are essential for assessing long-term CCS performance. Traditional numerical simulations, while effective, are computationally intensive, time-consuming, and constrained by data discretization. Previous work has shown the effectiveness of MeshGraphNets (MGN), a graph-based machine learning framework, as an innovative alternative for predicting reservoir behavior. MGN leverages graph neural networks (GNNs) and mesh representations to model complex geological formations, offering superior adaptability across different discretizations and reservoir configurations. Classic MGN implementations utilize an autoregressive technique to predict future behavior based on current predictions, but this technique is hampered by error accumulation over time. To enhance the model accuracy in time-series predictions, this study implemented a multi-step rollout strategy that integrates autoregressive predictions during training to stabilize prediction of saturation over time. Using the Illinois Basin – Decatur Project (IBDP) dataset, comprising 100 simulations of CO2 injection, pressure, and saturation changes, the framework demonstrated its ability to learn spatial dependencies and temporal dynamics. With inputs including permeabilities, porosities, and injection rates, MGN accurately predicted CO2 plume evolution over time, even with limited training data. Moreover, the addition of a multi-step rollout procedure during training improved the ability of MGN to predict stably over time by ~15%. This research positions MGN, enhanced with multi-step rollout capabilities, as a robust and efficient tool for CCS applications. It advances the field by enabling precise, computationally efficient predictions of reservoir behavior, providing a foundation for the broader adoption of machine learning frameworks in CCS and other geoscience domains.

Holcomb, Paul↗
DOE OSTI2024

Learning nonlinear operators in latent spaces for real-time predictions of complex dynamics in physical systems

Abstract Predicting complex dynamics in physical applications governed by partial differential equations in real-time is nearly impossible with traditional numerical simulations due to high computational cost. Neural operators offer a solution by approximating mappings between infinite-dimensional Banach spaces, yet their performance degrades with system size and complexity. We propose an approach for learning neural operators in latent spaces, facilitating real-time predictions for highly nonlinear and multiscale systems on high-dimensional domains. Our method utilizes the deep operator network architecture on a low-dimensional latent space to efficiently approximate underlying operators. Demonstrations on material fracture, fluid flow prediction, and climate modeling highlight superior prediction accuracy and computational efficiency compared to existing methods. Notably, our approach enables approximating large-scale atmospheric flows with millions of degrees, enhancing weather and climate forecasts. Here we show that the proposed approach enables real-time predictions that can facilitate decision-making for a wide range of applications in science and engineering.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2026

Neural entropy-stable conservative flux form neural networks for learning hyperbolic conservation laws

We propose a neural entropy-stable conservative flux form neural network (NESCFN) for learning hyperbolic conservation laws and their associated entropy functions directly from solution trajectories, without requiring any predefined numerical discretization. While recent neural network architectures have successfully integrated classical numerical principles into learned models, most rely on prior knowledge of the governing equations or assume a fixed discretization. Our approach removes this dependency by embedding entropy-stable design principles into the learning process itself, enabling the discovery of physically consistent dynamics in a fully data-driven setting. By jointly learning both the flux function and a corresponding entropy, NESCFN promotes conservation and entropy dissipation, which is critical for long-term stability and fidelity in the system of hyperbolic conservation laws. Furthermore, numerical results demonstrate that the method achieves stability and conservation over extended time horizons and accurately captures shock propagation speeds, even without oracle access to future-time solution profiles in the training data.

Conservative flux form↗
DOE OSTI2024

Linking Threat Agents to Targeted Organizations: A Pipeline for Enhanced Cybersecurity Risk Metrics

In this study, we present a methodology leveraging Large Language Models (LLMs) to transform Cybersecurity Threat Intelligence (CTI) narratives into actionable insights for individual organizations. Our approach automates the extraction of machine-readable adversary SKRAM (Skills, Knowledge, Resources, Authorities, and Motivation) attributes from open-source reports, extending LLM utility beyond typical interactions. This innovation enables precise, automated assessments of cybersecurity risks posed by various adversaries. Using a chain-of-thought and multi-shot prompting strategy, our methodology advances the automation of cybersecurity feature extraction for new machine-learning models that predict the risk of adversary targeting. This approach is refined using a substantial dataset of over 150 analyst-validated threat reports and synthetic organizational data from 900 companies. Here, by bootstrapping the training data with a rule-based heuristic over synthetic data, we have developed a high-accuracy machine-learning model that allows entities to dynamically prioritize threats and defensive actions.

Cyber Threat Intelligence↗
DOE OSTI2025

Integrating Analytical Solutions and U-Net Model for Predicting Groundwater Contaminant Plumes in Pump-and-Treat Systems

Pump-and-treat (P&T) is a common technique for groundwater remediation involving the extraction and treatment of contaminated water above ground. Optimizing the design and operation of the P&T well network is essential for maximizing the system’s effectiveness and efficiency. However, this optimization often necessitates many model evaluations, leading to computationally demanding tasks. This study introduces a novel approach that integrates analytical solutions for groundwater dynamics with the U-Net (Ronneberger et al., 2015) deep learning framework to predict groundwater contaminant plume migration under dynamic pumping conditions. By incorporating the Thiem equation (Thiem, 1906) into the input preprocessing, the U-Net model transforms sparse well data into a continuous spatial field that captures the hydraulic impacts of pumping activities. This integration enables the model to leverage both deep learning capabilities and classical physics-based groundwater theories, enhancing prediction accuracy and computational efficiency. These advancements can facilitate rapid, large-scale evaluations of P&T optimization simulations, allowing for timely and effective decision-making in well placement and system management. We demonstrate the model's robust performance across both simplified transient 2D models and a more complex 3D heterogeneous site model at the 200 West P&T facility at the Hanford Site. The U-Net-based model offers substantial computational advantages, reducing simulation times significantly compared to full physics-based models and providing a powerful tool for rapid site evaluation and P&T system optimization, such as evaluating alternative P&T well network designs. Our findings highlight the potential of advanced machine learning models to significantly enhance the efficiency and sustainability of groundwater remediation efforts, offering a novel application of U-Net architecture in environmental science.

Pump-and-treat↗
DOE OSTI2026

Continual Learning for Production-Level Machine Learning in Particle Accelerators

Particle accelerators operate in complex environments where data distribution can change dynamically, leading to data drifts that significantly challenge Machine Learning (ML) models. These non-stationary conditions often cause ML models to deteriorate in performance, making it difficult to maintain reliable predictions in operation. The primary sources of data drifts are changes in accelerator settings and changes in equipment performance which cannot be measured directly. To bridge this gap between ML development and long-term deployment in operational settings, we identify key areas within particle accelerators where continual learning can help mitigate drift-induced performance degradation. We will provide a practical guide on selecting the appropriate method given resource constraints and desired stability plasticity trade offs. As a concrete example, we will present a real-world use case for anomaly detection to predict errant beams at the Spallation Neutron Source accelerator, where continual learning has been employed to demonstrate stable performance on drifting data streams. We will present practical challenges, lessons learned, and the results from the deployed ML model.

Rajput, Kishansingh [Thomas Jefferson National Acc↗
DOE OSTI2025

Two-dimensional ring polymer molecular dynamics determination of the MnO + + H 2 /D 2 reaction rates on a Δ-machine learned potential energy surface

In this work, we investigate the impact of nuclear quantum effects in the kinetics of the MnO + + H 2 reaction, a prototypical system for gas-phase H 2 activation by transition metal oxide ions. The DFT based potential energy surfaces (PESs) for the lowest-lying quintet and septet spin states reported in our previous work are improved by 2953 newly calculated CCSD(T)/AVDZ points using a delta-machine learning (Δ-ML) method. To examine nuclear quantum effects, the rate coefficients are computed using ring-polymer molecular dynamics (RPMD). Due to the mechanistic complexity of the reaction, two reaction coordinates are necessary to map out the free-energy surface and an extended RPMD rate theory is developed. The calculated RPMD rate coefficients on the new PES are in better agreement with experimental data. The calculated kinetic isotope effects (KIEs) range from 1.6 to 1.8, also in good agreement with the experimental values. Additionally, the converged RPMD rate coefficients are 2.3 to 3.1 times higher than their classical counterparts across the studied temperature range, suggesting the presence of moderate nuclear quantum effects in this reaction.

Liu, Yang [University of New Mexico, Albuquerque, ↗
DOE OSTI2025

Optimizing on-ramp merging for connected and automated vehicles: A hierarchical approach using deep reinforcement learning and optimal control

On-ramp merging for Connected and Automated Vehicles (CAVs) presents significant challenges in dynamic traffic environments. Traditional methods and recent learning-based approaches often fail to simultaneously address decision-making complexity and execution precision under fluctuating conditions. This study introduces a novel hierarchical framework that combines: (1) a high-level Deep Reinforcement Learning (DRL) module that coordinates merging sequences through Virtual Traffic Signals (VTS) with Yield/Green phases and (2) a low-level optimal controller generating collision-free speed trajectories via pseudospectral convex optimization. A convolutional autoencoder compresses high-dimensional traffic states to enhance responsiveness. Extensive simulations demonstrate a 12.5% improvement in mainline throughput a 28% reduction in emergency braking events, and 31.66% lower fuel consumption compared to baseline methods. Furthermore, the framework’s effectiveness in coordinating CAV merges highlights its potential for real-world deployment. Future work will extend validation to multi-lane scenarios with mixed traffic and large-scale multiple merging points.

Connected and automated vehicles↗
DOE OSTI2026

Tandem bulk oxygen diffusion and surface reactions in reducible metal oxides control redox cycle dynamics

The interplay between bulk oxygen diffusion and surface reactions in reducible metal oxides is key in heterogeneous catalysts, but direct measurements of oxygen mobility, transient kinetics, and in situ spectroscopies have been lacking. Here, we reveal complex dynamic behavior of ceria-zirconia by H 2 using transient kinetics via mass spectrometry and in situ Raman and near-ambient pressure x-ray photoelectron spectroscopies. Molecular dynamics simulations with a machine learning potential delineate competitive oxygen diffusion mechanisms, with an optimal mobility at intermediate reductions. We expose a compensation between vacancy availability and lattice distortion at intermediate to high reductions and Frenkel defects at low reductions, underscoring a potential deficiency of 16 O/ 18 O exchange experiments in deducing oxygen mobility. Vacancies in proximity require electron localization on Ce atoms further away. The continuous replenishment of surface oxygen results in a varying reduction rate, with H 2 dissociation being the rate-limiting step. Multiscale transient simulations, consistent with experiments, indicate catalysts of potentially spatially varying oxidation states. The approach is broadly applicable to reducible oxide materials.

36 MATERIALS SCIENCE↗
DOE OSTI2024

Defect Production and Microstructural Feature Impact for Radiation Damage in Additively Manufactured 316 Stainless Steel

This milestone presents multi-scale modeling research results for additively manufactured 316 stainless steel. A combination of phase field, cluster dynamics, molecular dynamics, and density functional theory with machine learning is used, allowing for predictions of radiation-driven microstructural evolution in additively manufactured 316 stainless steel over a range of temperatures, damage rates, neutron spectra, and microstructures, and supporting the development of combined ion and neutron irradiation for material qualification. Informed by ion irradiation and neutron irradiation results across the Advanced Materials and Manufacturing Technologies program, we investigate the unique aspects of radiation-driven microstructure evolution in additively manufactured 316 stainless steel. In particular, we focus on understanding the impact of carbon concentration (varying, for example, between the 316L and 316H standards) on void formation; radiation-induced segregation at dislocation cells and grain boundaries; and the evolution of dislocation loops and network dislocation populations. We find that the unique characteristics of the additively manufactured microstructures must be accounted for in understanding the evolution of dislocation populations under thermal and irradiation conditions, such as the variation in sink strengths arising due to the variation in dislocation density. We also find that the radiation-induced segregation of Cr and Ni to grain boundaries and cell walls differs due to the differences in their defect sink biases. We also find that increasing the Ni content can slow vacancy diffusion, which may provide a mechanism for the observed reduction in transient swelling rate for austenitic Fe-Cr-Ni alloys with increasing Ni content. In addition, ion irradiations have shown that increasing carbon content in 316 SS results in a larger population of smaller voids, suggesting reduced vacancy diffusion. Our results show that the carbon content of additively manufactured 316 SS has a significant impact on the migration rate of defect clusters. The presence of carbon atoms results in carbon-vacancy trapping, significantly reducing the diffusion rate of vacancies. Carbon atoms may also be trapped near the surface of a void, which may reduce void growth by trapping vacancies that diffuse toward the void.

11 NUCLEAR FUEL CYCLE AND FUEL MATERIALS↗