SEARCH · Engineering Papers

Results for “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.

SourceResearch connectionFrom yearThrough year

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

At least 109 records · Page 6

All sources NASA NTRS DOE OSTI

DOE OSTI2026

Multi‐Scale Model‐Informed Deep Learning for Plasma‐Nanoparticle Interaction

The Overarching Goal of this proposed research is to understand and quantitively determine the interactions between non-thermal plasma (hot electrons, reactive radicals, vibrationally excited species) and surface reactions on influencing the activity and selectivity of the desired reactions via developing multi-scale model informed deep learning algorithm. Investigating non-thermal plasma-surface interaction is feasible due to the low bulk temperature in the discharge region. To investigate the role of plasma-nanoparticle interaction on enhancing the reaction kinetics, we will focus on ammonia cracking to generate clean hydrogen over earth-abundant, non-critical metallic nanoparticles, which is of great significance for decarbonization. We hypothesize that (1) reactive radicals interacting with surface reaction species via Eley–Rideal mechanism will significantly lower the energetics of the potential rate-limiting step of nitrogen formation; (2) the surface will be charged heterogeneously under non-thermal plasma conditions and the charged site will lower the energetics of ammonia cracking through Langmuir– Hinshelwood mechanism; (3) vibrationally excited ammonia will further promote the initial N-H bond cleavage. To access the hypothesis, we will (1) reveal the surface charge effects on tunning the reaction energetics via interpretable, physics-informed deep learning accelerated density functional theory (DFT) calculations; (2) determine the reactive radicals interacting with surface reaction species on tuning the reaction energetics via DFT; (3) reveal the surface charge effects on tunning the reaction energetics via DFT and deep learning models, (4) quantify how vibrationally excited species, reactive radicals, and surface charging effects on enhancing the catalysis via developing DFT-based microkinetic modeling (MKM) and active learning. Deep and active learning of plasma-nanoparticle interactions effects on enhancing ammonia cracking to generate hydrogen represents a new paradigm for designing high performance plasma materials. The fundamental science of how plasma-nanoparticle interactions will change the plasma kinetics and will improve the energy efficiency for decarbonization and sustainability. The interpretable and physics-informed machine learning model will accelerate low temperature plasma chemistry and material discovery with physics rules and model interpretation.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗

DOE OSTI2025

MOOSE ProbML: Parallelizable Probabilistic Machine Learning and Uncertainty Quantification Capabilities

The Multiphysics Object Oriented Simulation Environment (MOOSE) is a widely used open- source finite element software for performing multiphysics multiscale simulations in a massively parallel fashion. Recently, the computational team at Idaho National Laboratory (INL) has implemented Probabilistic Machine Learning (ProbML) capabilities in MOOSE—in a parallelized fashion—and enable active learning with large-scale computational models for tasks such as surrogate model development, scale bridging, forward/inverse uncertainty quantification (UQ), Bayesian optimization, etc. This presentation summarizes these developments in MOOSE along with demonstrations on several real applications relevant to nuclear energy. At the fundamental level, samplers like Monte Carlo/Latin Hypercube, variance reduction, parallelized Markov Chain Monte Carlo (MCMC) support uncertainty propagation in both forward and inverse settings. These samplers can be integrated with the Gaussian processes (GP) suite in MOOSE, which offer several variants like scalar GPs, multi-output GPs, and deep GPs, to enable active learning. These GPs can be tuned using gradient-based optimization methods like Adam and its variants or gradient-free methods like the elliptical slice sampler (a variant of MCMC adept under Gaussian settings) for more complex covariance kernels or likelihoods whose gradient computations can be cumbersome. A variety of batch acquisition functions permit parallelized evaluation of the computational model and support different learning objectives with high efficiency like Bayesian inference, global surrogate development, optimization, etc. Furthermore, libtorch integration supports training, evaluation, and re-training of neural networks and other complex machine learning models in active learning settings. The impacts of these developments are shown on several real applications: (1) nuclear fuel inverse UQ and model inadequacy assessment using the Kennedy O’Hagan framework; (2) uncertainty aware surrogate modeling for additive manufacturing to predict field quantities; (3) nuclear reactor rare events analysis; and (4) complex fluid flow prediction using a global surrogate with quantified prediction uncertainty. Finally, the outlook of MOOSE ProbML is discussed for both outer-loop and inner-loop computations in the broad view to accelerate fuels and materials qualification, address gaps in knowledge and data, and assess new reactor/fuel systems.

11 - NUCLEAR FUEL CYCLE AND FUEL MATERIALS↗

DOE OSTI2024

Transfer learning for probabilistic localization of hidden cracks in concrete structures

Abstract The utility of discriminative supervised learning models built using multiple training-data sources is investigated for hidden crack localization in concrete. Feed-forward neural network (FFNN) is chosen as the model architecture, and transfer learning is used to assimilate the information obtained from different sources (computational physics simulations and laboratory experiments). The labeled training data consists of values of a damage index and the known locations of hidden cracks. The classification models need to learn how the presence of damage (hidden cracks) affects the damage index at different sensors for different test conditions. To this end, diagnostic FFNN models are built by sequentially adding and training new hidden layers to assimilate labeled information from computer models (different model geometries, test conditions, crack lengths, crack locations) and laboratory experiments on a plain cement slab. These transfer learning-based models are then used to localize damage in concrete specimens that reflect real-world conditions (i.e., specimens with steel reinforcement and randomly distributed aggregate). The actual damage state in these specimens is determined by extracting cores and performing petrographic studies on the extracted cores. The damage probability estimated by transfer learning-based models is compared with the petrographic damage rating index (DRI) to identify the most suitable approach to train the diagnostic models. The transfer learning-based diagnostic methodology shows promise and could be used in various structural health monitoring applications, where sufficient labeled data are typically not available from a single data source.

Miele, S.↗

DOE OSTI2026

Subseasonal Forecasting and MJO Teleconnections in Machine Learning Weather Prediction Models

Abstract In recent years, machine‐learning (ML) models trained on reanalysis data have rivaled physics‐based forecast models in terms of performance skill for global weather forecasting. With increased rollout stability, the question of how these models perform for subseasonal to seasonal (S2S, week 3–8) forecasting has emerged. In this study we run a large set of subseasonal hindcasts over 2004–2023 to evaluate two ML weather forecast models at the S2S time scale, SFNO‐HENS (Nvidia, fully ML) and NeuralGCM (Google Research, hybrid). Corresponding hindcasts from the European Centre for Medium‐Range Weather Forecasts (ECMWF) are used as a baseline for comparison to a physics‐based model. Because our focus is on predicting moisture transport over the Western United States between October and March, we evaluate the models' prediction skill for the Madden‐Julian Oscillation (MJO) and its associated teleconnections in the North Pacific. We find that both ML models are competitive with the ECWMF model, with comparable skill in predicting the North Pacific large‐scale circulation and the MJO at week 3 and beyond. Even though overall the mid‐latitude subseasonal prediction skill remains low, the ML models exhibit interesting behavior such as a realistic propagation of the MJO across the Maritime Continent and realistic teleconnections. A SFNO‐HENS sensitivity experiment with altered initial conditions in the tropics demonstrates the stability of the model, and it illustrates the capability of ML models to represent important physical processes of the atmosphere at the S2S time scale. Plain Language Summary Predicting weather patterns and precipitation a few weeks in advance (subseasonal time scale) is of great interest for stakeholders such as water managers in the Southwest United States (US), where arid conditions prevail. Subseasonal forecasts from traditional weather forecast models exhibit low skill in the region, limiting their applicability. Here we examine whether the recent breakthrough in weather forecasting made with machine learning/artificial intelligence models can translate to improved subseasonal forecasts. Recently‐developed machine learning models exhibit comparable skill to a state‐of‐the‐art physics‐based model for predicting weather patterns in the North Pacific/North America region, and associated moisture transport. The same applies to their skill in predicting the tropical pattern, the Madden‐Julian Oscillation, and its important remote perturbations over the midlatitude East Pacific and Southwest US. Additionally, a perturbation experiment carried out with one of the machine learning models illustrates their ability to not only predict the evolution of atmospheric fields, but also to learn and represent physical processes such as tropics‐extratropics Rossby wave propagation. Key Points Two machine learning weather forecast models exhibit state‐of‐the‐art prediction skill at the subseasonal time scale in the Pacific sector The models equal ECWMF in terms of Madden‐Julian oscillation (MJO) prediction skill, and they accurately predict the MJO propagation and associated teleconnections The two machine‐learning models represent key physical processes for subseasonal prediction, despite being trained for weather forecasting

Peings, Yannick↗

DOE OSTI2025

Efficient and assured reinforcement learning-based building HVAC control with heterogeneous expert-guided training

Abstract Building heating, ventilation, and air conditioning (HVAC) systems account for nearly half of building energy consumption and $$20\%$$ of total energy consumption in the US. Their operation is also crucial for ensuring the physical and mental health of building occupants. Compared with traditional model-based HVAC control methods, the recent model-free deep reinforcement learning (DRL) based methods have shown good performance while do not require the development of detailed and costly physical models. However, these model-free DRL approaches often suffer from long training time to reach a good performance, which is a major obstacle for their practical deployment. In this work, we present a systematic approach to accelerate online reinforcement learning for HVAC control by taking full advantage of the knowledge from domain experts in various forms . Specifically, the algorithm stages include learning expert functions from existing abstract physical models and from historical data via offline reinforcement learning, integrating the expert functions with rule-based guidelines, conducting training guided by the integrated expert function and performing policy initialization from distilled expert function. Moreover, to ensure that the learned DRL-based HVAC controller can effectively keep room temperature within the comfortable range for occupants, we design a runtime shielding framework to reduce the temperature violation rate and incorporate the learned controller into it. Experimental results demonstrate up to 8.8 X speedup in DRL training from our approach over previous methods, with low temperature violation rate.

Xu, Shichao↗

DOE OSTI2025

Advancing molecular machine learning representations with stereoelectronics-infused molecular graphs

Molecular representation is a critical element in our understanding of the physical world and the foundation for modern molecular machine learning. Previous molecular machine learning models have used strings, fingerprints, global features and simple molecular graphs that are inherently information-sparse representations. However, as the complexity of prediction tasks increases, the molecular representation needs to encode higher fidelity information. This work introduces a new approach to infusing quantum-chemical-rich information into molecular graphs via stereoelectronic effects, enhancing expressivity and interpretability. Learning to predict the stereoelectronics-infused representation with a tailored double graph neural network workflow enables its application to any downstream molecular machine learning task without expensive quantum-chemical calculations. We show that the explicit addition of stereoelectronic information substantially improves the performance of message-passing two-dimensional machine learning models for molecular property prediction. We show that the learned representations trained on small molecules can accurately extrapolate to much larger molecular structures, yielding chemical insight into orbital interactions for previously intractable systems, such as entire proteins, opening new avenues of molecular design. Finally, we have developed a web application (simg.cheme.cmu.edu) where users can rapidly explore stereoelectronic information for their own molecular systems.

Boiko, Daniil A↗

DOE OSTI2026

Particle trajectory representation learning with masked point modeling

Liquid argon time projection chambers (LArTPCs) offer millimeter-scale 3D images of particle trajectories, enabling precision studies of neutrino oscillation, detection of supernova and solar neutrinos, searches for exotic dark matter, and proton decay. Current approaches utilize supervised machine learning models, requiring extensive simulations of particle physics and detector response that can introduce bias. Self-supervised learning (SSL), a machine learning approach that learns useful representations of unlabeled data from the data itself, has significantly advanced how large datasets are utilized for representation learning; however, its potential for applications to sensory data in high precision particle physics experiments remains largely unexplored. We introduce the Point-based liquid argon masked autoencoder (PoLAr-MAE), a self-supervised framework that learns physically meaningful representations directly from unlabeled LArTPC images. PoLAr-MAE achieves remarkable data efficiency for a point-level segmentation task, outperforming fully supervised methods in low data regimes. Linear classifiers on model outputs demonstrate robust performance across multiple downstream tasks. Our results position sensor-level SSL as a practical foundation model strategy for LArTPCs.

Young, Samuel [Stanford Univ., CA (United States)]↗

DOE OSTI2024

Chemical reaction enhanced graph learning for molecule representation

Abstract Motivation Molecular representation learning (MRL) models molecules with low-dimensional vectors to support biological and chemical applications. Current methods primarily rely on intrinsic molecular information to learn molecular representations, but they often overlook effectively integrating domain knowledge into MRL. Results In this article, we develop a reaction-enhanced graph learning (RXGL) framework for MRL, utilizing chemical reactions as domain knowledge. RXGL introduces dual graph learning modules to model molecule representation. One module employs graph convolutions on molecular graphs to capture molecule structures. The other module constructs a reaction-aware graph from chemical reactions and designs a novel graph attention network on this graph to integrate reaction-level relations into molecular modeling. To refine molecule representations, we design a reaction-based relation learning task, which considers the relations between the reactant and product sides in reactions. In addition, we introduce a cross-view contrastive task to strengthen the cooperative associations between molecular and reaction-aware graph learning. Experiment results show that our RXGL achieves strong performance in various downstream tasks, including product prediction, reaction classification, and molecular property prediction. Availability and implementation The code is publicly available at https://github.com/coder-ACAC/RLM.

Biochemistry & Molecular Biology↗

DOE OSTI2025

Contrastive learning for robust representations of neutrino data

In neutrino physics, analyses often depend on large simulated datasets, making it essential for models to generalize effectively to real-world detector data. Contrastive learning, a well-established technique in deep learning, offers a promising solution to this challenge. By applying controlled data augmentations to simulated data, contrastive learning enables the extraction of robust and transferable features. This improves the ability of models trained on simulations to adapt to real experimental data distributions. In this paper, we investigate the application of contrastive learning methods in the context of neutrino physics. Through a combination of empirical evaluations and theoretical insights, we demonstrate how contrastive learning enhances model performance and adaptability. Additionally, we compare it to other domain adaptation techniques, highlighting the unique advantages of contrastive learning for this field. Published by the American Physical Society 2025

Wilkinson, Alex (ORCID:0000000253404506)↗

DOE OSTI2024

Metric Learning to Accelerate Convergence of Operator Splitting Methods

Recent developments in machine learning have led to promising advances in accelerating the solution of constrained optimization problems. Increasing demand for real-time decision-making capabilities in applications such as artificial intelligence and optimal control has led to a variety of proposed strategies for learning to produce fast solutions to optimization problems. For example, recent works have shown that it is possible to accelerate the convergence of optimization algorithms by learning to select their parameters, such as gradient descent stepsizes. This work proposes a new approach, in which the underlying metric spaces of proximal operator splitting algorithms are learned to maximize convergence rate. While prior works in optimization theory have derived optimal metrics in simple cases, no such result exists for many practical problem forms including general Quadratic Programming (QP). This paper shows how differentiable optimization can enable the end-to-end learning of proximal metrics, enhancing the convergence of proximal algorithms for QP problems beyond what is possible based on known theory. Additionally, the results illustrate a strong connection between the learned proximal metrics and active constraints at the optima, leading to an interpretation in which the predicted proximal metrics can be viewed as a form of active set prediction.

King, Ethan [BATTELLE (PACIFIC NW LAB)]↗

DOE OSTI2025

Kinetic Deep Learning v0.1

Here, we present a method that uses protein levels to predict times series of metabolite concentrations. Understanding this type of pathway dynamics is important in order to predict the behavior of the pathway and, more pragmatically, to be able to design biological systems (such as strains bioengineered to produce chemical products) reliably. Typically, for this purpose, kinetic models consisting of differential equations based on the Michaelis-Menten dynamics have been used in the past. However, these methods can rarely produce good fits to measured data time series. Possibly, this happens because the kinetic constants are unknown or are different from the ones measured in vivo, or perhaps because Michaelis-Menten dynamics is not a satisfactory description. In order to improve the predictive nature of these kinetic models we have eliminated the Michaelis-Menten description of pathway dynamics and we have substituted it by algorithms that automatically learn these dynamics from previously obtained metabolomics and proteomics data using machine learning approaches. Specifically, kinetic deep learning uses deep learning to map proteomics time series to metabolite concentration time series, instead of learning the first metabolite derivative and integrating in (as in the first version of kinetic learning). This approach is shown to provide good to excellent results with a data set specifically collected for this purpose.

Garcia Martin, Hector [Joint BioEnergy Institute (↗

DOE OSTI2025

Model-based Hierarchical Reinforcement Learning for Improved Physical Security Design: A Prototype

Prior work in FY24 developed an adversarial AI agent aid in path analysis of physical protection systems. This agent, trained using a model-based reinforcement learning algorithm, was able to successfully learn the most vulnerable path in facilities. It was able to extend the current state of practice for physical protection design by exhibiting dynamic behavior based on current environmental conditions. Whereas PathTrace largely performs a static, graph-based analysis, the AI agent was able to make decisions based on relative position in the facility, current conditions (was the adversarial agnet discovered?), and proximity to secondary targets. The agent demonstrated some novel capabilities, but had limitations that need to be resolved before it can be used for production purposes. For example, the adversarial agent generalizes poorly and takes a relatively long time to train. Nonetheless, there is still considerable promise for developing the adversarial agent further in order to explore even richer, more dynamic behaviors (e.g., adversary motivations, environmental debris, and more). This work considers a complementary idea; development of a planning agent. The planning agent is envisioned as an auto-complete-like tool that can help accelerate security system design by human experts. The agent would respect existing barriers and sensors placed by a human expert while offering cost-effective suggestions (i.e., implicitly balancing effectiveness with cost) to improve the design. The goal is for this agent to be part of an expert’s toolbox, not to totally upend the current state-of-practice, or to displace human experts. The ultimate goal would be concurrent training of both the adversarial and planning agent together, to learn entirely through self-play. This would represent an entirely new way of performing system deign. We selected a hierarchical, model-based reinforcement learning algorithm to serve as the planning agent. This is an extension of concepts used in the prior FY24 adversarial agent work. There, we had a single agent acting an environment. Here, we have two different sub-agents (policies), working together, to form a complete agent. There is a manager policy, which can select abstract goals on slower time scales, and a worker, which performs primitive actions to reach goals selected by the manager. It is worth noting that this class of algorithm is challenging to work with. From our understanding, our work is one of the first successful uses of model-based reinforcement learning (MBRL) in nuclear energy1 , and likely the first hierarchical model-based reinforcement learning application in nuclear energy. Further, this work is one of the first known attempts to apply AI to perform a design tasks in nuclear energy. Consequently, there were significant implementation challenges and the bulk of the work was focused on successful implementation and algorithm design. The results presented here are very low technology readiness level as a consequence of the lack of related literature, but still represent a significant step forward in the pursuit of applied AI for design.

42 ENGINEERING↗

DOE OSTI2025

Explainable and Differentiable Reinforcement Learning for Multi-objective Optimization in Particle Accelerators

Operating particle accelerators involves optimizing multiple goals simultaneously, which can be challenging due to trade-offs among objectives. While evolutionary algorithms like the genetic algorithm (GA) have been used for various Multi-Objective Optimization (MOO) tasks, they are not inherently suited for complex control problems. This talk highlights two variations of Reinforcement Learning (RL) for concurrently optimizing heat load and trip rates at the Continuous Electron Beam Accelerator Facility (CEBAF). The problem involves strict constraints on individual states, actions, and overall energy requirements of the beam. First, this talk highlights how differentiability can be harnessed through a Deep Differentiable Reinforcement Learning (DDRL) approach to address MOO issues within particle accelerators. We examine the DDRL method alongside Model Free Reinforcement Learning (MFRL), GA, and Bayesian Optimization (BO). The performance of these methods is assessed by generating a Pareto-front for two objectives. Our findings indicate that DDRL excels in handling high-dimensional problems more effectively than MFRL, BO, and GA. Next, we will show integration of explainable physics-based constraints into RL algorithms to enhance trans- parency and trust in decision-making processes by enabling users to verify that agents adhere to established physical principles. This surrogate function can be modeled using neural networks or sparse dictionary mod- els. By examining the mathematical form of the learned constraint function, we are able to confirm the agent has learned to use the established physics of each environment provided but the surrogate model. In addi- tion, we find that the introduction of a mathematical functional dictionary based surrogate model enables our reinforcement learning algorithms to reliably converge for difficult high-dimensional accelerator controls environments.

Rajput, Kishansingh [Thomas Jefferson National Acc↗

DOE OSTI2026

Adaptive Cybersecurity for Distributed Energy Resources (AdCyDER): Online Reinforcement Learning with Stackelberg-Optimized Defenses — Pipeline Architecture, Evaluation Methodology, and Findings from a Synthetic-Data Evaluation

This report documents the design and evaluation of an integrated online-learning pipeline developed within the AdCyDER project for Distributed Energy Resource (DER) cybersecurity. The pipeline couples a Reinforcement Learning (RL) attack classifier — which produces an attack-type probability distribution — with a Stackelberg game-theoretic (GT) defense selector that consumes those distributions alongside SME-encoded priors over (defense, attack) effectiveness pairings and perdefense costs to choose grid-health-preserving defenses. The objective is not attack classification per se but production of distributions that drive effective defense selection through the Stackelberg layer, learned from delayed grid-health feedback rather than labeled attack data. AdCyDER as a whole is broader than the work presented here; this report covers the specific RL/GT loop integration and its evaluation. We present the integrated pipeline (SCADA telemetry with Fronius inverter physics, Suricata IDS, time-windowed aggregation, per-facility LSTM classifier, Stackelberg optimizer, OpenC2 actuators), an experimental campaign of 28 eight-hour iterations across three baseline modes, and a pipeline-ordered diagnostic protocol. The protocol identifies two distinct failure modes within the loop: paired supervised ceilings on the same features establish that the deployed online RL classifier (macro F1 ≈ 0.07) sits at least 4.7× below a same-architecture supervised LSTM (≈ 0.34) and 10–11× below a linear feature-signal ceiling (≈ 0.70–0.79 depending on per-facility isolation), localizing the dominant failure to the training procedure; and the reward signal driving online updates carries weak directional coupling with classifier correctness in the methodology-expected direction (multi-lens convergent: top-decile P(true) records produce more frequent state changes and slightly larger improvements, top-vs-bot Cohen’s 𝑑 ≈ −0.19), but at effect magnitudes too small to drive gradient-based learning at the campaign sample size. The original learning hypothesis is not supported by the data. The primary contributions are the diagnostic methodology — proposed as a transferable falsification protocol for online RL/GT defense pipelines learning from delayed environmental reward — and the open, reproducible experimental infrastructure. We outline reward reformulation as the highest-priority aspirational next step given the underpowered-but-aligned Q6 reading, with hardware-in-the-loop evaluation as the broadest scope-expansion option.

Blakely, Benjamin [Argonne National Laboratory (AN↗

DOE OSTI2024

Quantum Annealing for Real-World Machine Learning Applications

Optimizing the training of a machine learning pipeline is important for reducing training costs and improving model performance. One such optimizing strategy is quantum annealing, which is an emerging computing paradigm that has shown potential in optimizing the training of a machine learning model. The implementation of a physical quantum annealer has been realized by D-Wave systems and is available to the research community for experiments. Recent experimental results on a variety of machine learning applications have shown interesting results especially under the conditions where the performance of classical machine learning techniques are limited such as limited training data and high dimensional features. This chapter explores the application of D-Wave’s quantum annealer for optimizing machine learning pipelines for real-world classification problems. We review the application domains on which a physical quantum annealer has been used to train machine learning classifiers. We discuss and analyze the experiments performed on the D-Wave quantum annealer for applications such as image recognition, remote sensing imagery, security, computational biology, biomedical sciences, and physics. We discuss the possible advantages and the problems for which quantum annealing is likely to be advantageous over classical computation.

Kumar nath, Rajdeep↗

DOE OSTI2025

Enhancing Unknown Waveform Detection by Learning Intra and Inter-domain Dependencies with Advanced Attention Fusion Mechanisms

Detection of unknown waveforms in mission-critical communications is a crucial area of interest for the Department of Energy (DoE). Traditional methods and recent deep learning-based approaches often assume that the training set includes all possible classes, which is impractical for detecting new waveforms. This limitation gives rise to the problem of open-set recognition (OSR), which involves correctly identifying known classes while detecting and rejecting unknown or unseen classes. To address this limitation, we propose a novel dual-domain complex-valued neural architecture that jointly processes time-domain and frequency-domain signal representations using transformer mechanisms. A transformer model is a deep learning architecture that uses self-attention mechanisms to process and learn relationships in sequential data. Our model employs a cosine similarity loss to extract domain-specific features and incorporates a transformer architecture in the latent space to weigh the importance of different features from the time and frequency domains. The transformer layer includes stacked self-attention and cross-attention modules to learn intra-domain and inter-domain dependencies, creating a more holistic signal representation. An attention-based fusion module intelligently combines the time and frequency-domain features using multi-head attention, enabling the network to learn the optimal feature for each domain in each input signal. Quantitative results demonstrate the impact of these architectural choices on overall performance, showing significant improvement after incorporating self and cross-attention modules and using complex attention fusion over simple weighted fusion. Our ongoing work will focus on addressing the limitations of threshold-based OSR methods by developing a novel generative framework that integrates a conditional diffusion probabilistic model (DPM). DPM is a generative framework that learns to synthesize complex data by reversing a gradual noising process using a neural network trained to denoise step-by-step. Our goal is to leverage the inherent strengths of DPMs for identifying unknown signals more robustly. One primary advantage of using a DPM is its ability to provide a more reliable anomaly score based on the model's reconstruction error, rather than relying solely on classifier confidence. Additionally, the iterative denoising process of DPMs makes this approach naturally resilient to low Signal-to-Noise Ratio (SNR) conditions, where traditional methods often fail. By implementing this generative framework, we aim to enhance the model's capability to accurately detect unknown waveforms and maintain performance in challenging environments.

99 - GENERAL AND MISCELLANEOUS↗

DOE OSTI2026

Enabling probabilistic learning on manifolds through double diffusion maps

Here, we present a generative learning framework for probabilistic sampling that extends Probabilistic Learning on Manifolds (PLoM), which is designed to generate statistically consistent realizations of a random vector in a finite-dimensional Euclidean space, informed by a (representative) set of observations. In its original form, PLoM constructs a reduced-order probabilistic model by combining three main components: (a) kernel density estimation to approximate the underlying probability measure, (b) Diffusion Maps to characterize the manifold of the data, and (c) a reduced-order Itô Stochastic Differential Equation (ISDE) to sample from the learned distribution. However, its sampling dynamics are posed in the ambient space and the retained number of reduced coordinates is chosen by projection-reconstruction error. In practice, this often (i) requires more coordinates than the data’s intrinsic dimension to achieve stable sampling and (ii) lacks a smooth, basis-independent lifting back to the data domain; moreover, standard Diffusion Maps emphasize harmonic eigenfunctions and can miss non-harmonic latent structure. We address these limitations by decoupling geometry learning from sampling: a first Diffusion Maps pass identifies non-harmonic coordinates on which we formulate a full-order ISDE directly in the latent space, while Double Diffusion Maps captures multiscale geometric features and Geometric Harmonics (GH) learns a smooth lifting map to the ambient variables that is independent of the particular diffusion basis. This hybrid design preserves the system’s dynamical richness with a compact geometric representation and enables principled out-of-sample inference. The effectiveness and robustness of the proposed method are illustrated through two numerical studies: one based on data generated from two-dimensional Hermite polynomial functions and another based on high-fidelity simulations of a detonation wave in a reactive flow.

Double diffusion maps↗

DOE OSTI2024

A Generation-Storage Coordination Dispatch Strategy for Power System Based on Causal Reinforcement Learning

In the backdrop of global energy transformation, power systems integrating high proportions of renewable energy sources are facing unprecedented challenges in operational stability and dispatch efficiency. To address these challenges, this study introduces a generation-storage coordination real-time dispatch strategy based on Causal Power System Dynamic Reinforcement Learning (CPSDRL). Diverging from traditional reinforcement learning approaches, CPSDRL innovatively incorporates causal inference within the state prediction model - the crux of model-based reinforcement learning - thereby establishing the Power Causal Dynamic Model (PCDM). Assisted by the prior knowledge of power systems, the model significantly enhances prediction accuracy and reliability through a two-stage training process. Utilizing PCDM, this study further applies a direct policy search algorithm to optimize the real-time dispatch strategy. Experimental results indicate that the proposed method improves the stability of generation-storage coordination real-time dispatch and exhibits competitive advantages in sample efficiency and computational speed, compared to traditional model-based and model-free reinforcement learning algorithms. This method is expected to enhance the practicality and adaptability of causal reinforcement learning techniques in power system scheduling and control.

causal reinforcement learning↗