Search NASA⌕ Search

SEARCH · Search NASA

Results for “Generative deep 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 361 records · Page 20
All sourcesNASA NTRSDOE OSTI
DOE OSTI2025

A fault-tolerant neutral-atom architecture for universal quantum computation

Quantum error correction (QEC) is essential for the realization of large-scale quantum computers. However, owing to the complexity of operating on the encoded ‘logical’ qubits, understanding the physical principles for building fault-tolerant quantum devices and combining them into efficient architectures is an outstanding scientific challenge. Here we use reconfigurable arrays of up to 448 neutral atoms to implement the key elements of a universal, fault-tolerant quantum processing architecture and experimentally explore their underlying working mechanisms. We first use surface codes to study how repeated QEC suppresses errors, demonstrating 2.14(13)x below-threshold performance in a four-round characterization circuit by leveraging atom loss detection and machine learning decoding. We then investigate logical entanglement using transversal gates and lattice surgery and extend it to universal logic through transversal teleportation with three-dimensional [[15,1,3]] codes, enabling arbitrary-angle synthesis with polylogarithmic overhead. Finally, we develop mid-circuit qubit reuse16, increasing experimental cycle rates by two orders of magnitude and enabling deep-circuit protocols with dozens of logical qubits and hundreds of logical teleportations with [[7,1,3]] and high-rate [[16,6,4]] codes while maintaining constant internal entropy. Our experiments show key principles for efficient architecture design, involving the interplay between quantum logic and entropy removal, judiciously using physical entanglement in logic gates and magic state generation, and leveraging teleportations for universality and physical qubit reset. These results establish foundations for scalable, universal error-corrected processing and its practical implementation in neutral atom systems.

atomic and molecular physics↗
DOE OSTI2026

Decentralised Reinforcement Learning for Dynamic Cyberattack Response in Microgrid Networks

Microgrids rely on communication networks for reliable operation, which makes them inherently vulnerable to cyberattacks. Such attacks can destabilise system dynamics and drive states away from their nominal operating trajectories. Although several physics-informed and machine learning-based strategies have been developed to counter these threats, the rapidly evolving cyber landscape enables adversaries to bypass static defences or rules-based mitigation approaches. This paper proposes a dynamic, online-trained and fully decentralised reinforcement learning (RL)-based cyberattack response framework to protect microgrids from evolving cyberattacks. The proposed framework deploys multiple deep Q-networks (DQNs), each associated with a distributed energy resource (DER), to enable localised and adaptive attack mitigation. In this framework, each DQN processes local voltage and frequency measurements—combined with intrusion detection system (IDS) alerts—as observations and rewards to guide decision-making. Extensive simulation studies demonstrate the robustness of the proposed framework under diverse attack scenarios and varying IDS-induced detection delays. Comparative analysis highlights its superiority over existing static or preexisting rules-based mitigation approaches. Finally, we present an analysis that shows the framework's scalability to real-life microgrids with more interacting agents.

24 POWER TRANSMISSION AND DISTRIBUTION↗
DOE OSTI2024

Decode the Workload: Training Deep Learning Models for Efficient Compute Cluster Representation

Monitoring the status of a high throughput computing cluster running computationally intensive production jobs is a crucial yet challenging system administration task due to the complexity of such systems. To this end, we train autoencoders using the Linux kernel CPU metrics of the cluster. Additionally, we explore assisting these models with graph neural networks to share information across threads within a compute node. The models are compared in terms of their ability to: 1) Produce a compressed latent representation that captures the salient features of the input, 2) Detect anomalous activity, and 3) Make distinction between different kinds of jobs run at Jefferson Lab. The goal is to have a robust encoder whose compressed embeddings are used for several downstream tasks. We extend this study further by deploying these models in a human-in-the-loop production-based setting for the anomaly detection task and discuss the associated implementation aspects such as continual learning and the criterion to generate alarms. This study represents a first step in the endeavor towards building self-supervised large-scale foundation models for computing centers.

Mohammed, Ahmed↗
DOE OSTI2025

Accelerating template generation in resonant anomaly detection searches with optimal transport

We introduce Resonant Anomaly Detection with Optimal Transport (RAD-OT), a method for generating signal templates in resonant anomaly detection searches. RAD-OT leverages the fact that the samples from the conditional probability density of the target features vary approximately linearly along the optimal transport path connecting the resonant feature. This does not assume that the conditional density itself is linear with the resonant feature, allowing RAD-OT to efficiently capture multimodal relationships, changes in resolution, etc. By solving the optimal transport problem, RAD-OT can quickly build a template by interpolating between the background distributions in two sideband regions. We demonstrate the performance of RAD-OT using the LHC Olympics R&D dataset, where we find comparable sensitivity and improved stability with respect to deep learning-based approaches.

Automation↗
DOE OSTI2024

Semantic Stealth: Crafting Covert Adversarial Patches for Sentiment Classifiers Using Large Language Models

Deep learning models have been shown to be vulnerable to adversarial attacks, in which perturbations to their inputs cause the model to produce incorrect predictions. As opposed to adversarial attacks in computer vision, where small changes introduced to pixel values can drastically alter a model's output while remaining imperceptible to humans, text-based attacks are difficult to conceal due to the discrete nature of tokens. Consequently, unconstrained gradient-based attacks often produce adversarial examples that lack semantic meaning, rendering them detectable through visual inspection or perplexity filters. In contrast to methods that rely on gradient-based optimization in the embedding space, we propose an approach that leverages a Large Language Model's ability to generate grammatically correct and semantically meaningful text to craft adversarial patches that seamlessly blend in with the original input text. These patches can be used to alter the behavior of a target model, such as a text classifier. Since our approach does not rely on gradient backpropagation, it only requires access to the target model's confidence scores, making it a grey-box attack. We demonstrate the feasibility of our approach using open-source LLMs, including Intel's Neural Chat, Llama2, and Mistral-Instruct, to generate adversarial patches capable of altering the predictions of a distilBERT model fine-tuned on the IMDB reviews dataset for sentiment classification.

Roa Carvajal, Maria↗
DOE OSTI2024

Machine learning-guided design of direct methanol fuel cells with a platinum group metal-free cathode

Direct methanol fuel cells (DMFCs) offer a promising solution for clean electricity generation, particularly in small electronics and remote auxiliary power units. However, optimizing their efficiency and performance is challenging due to the complex interactions between various factors. Here, we present a novel approach that integrates experiments with machine learning to model and predict the performance of these fuel cells using atomically dispersed platinum group metal (PGM)-free catalysts at the cathode. Further, our machine learning models, trained on diverse input parameters, allow for the comprehensive optimization of DMFC performance prior to fabrication and testing. Through extensive experimental validation, we demonstrate that this data-driven approach accurately predicts key performance metrics, such as maximum power output and polarization curves. By combining our models with interpretable game-theory methods, we provide deep insights into the factors governing fuel cell performance, ultimately paving the way for the design of scalable and efficient DMFC technologies.

25 ENERGY STORAGE↗
DOE OSTI2025

Remote sensing images, DEM, and point clouds associated with “Accuracy evaluation of cost-effective 3D reconstruction approaches for hydrobiogeochemical processes in non-perennial stream riverbeds”

This data package is associated with the publication “Accuracy evaluation of cost-effective 3D reconstruction approaches for hydrobiogeochemical processes in non-perennial stream riverbeds” published in Frontiers in Environmental Science, Environmental Informatics and Remote Sensing (Bao et al., 2026; doi: 10.3389/fenvs.2026.1725258). This data package includes the drone photos for a section of Umtanum Creek in Washington, Unted States. The photos were used to reconstruct the 3-dimensional (3D) digital elevation model (DEM) of the riverbed for the investigated stream section. The reconstruction results from four approaches are provided: (1) unoccupied aerial vehicle (UAV, colloquially known as drone) imagery-based Structure-from-Motion (SfM), (2) a machine learning-based 3D reconstruction model, Visual Geometry Grounded Deep Structure from Motion (VGGSfM), (3) Visual Geometry Grounded Transformer for long sequence of images (VGGT-Long), and (4) handheld smartphone LiDAR scanning. The ground truth measurements by tripod-mounted optical level kit and ground control points GPS locations for evaluating the accuracy of the four reconstruction approaches are also provided in this data package. A preliminary version of this data package was published in October 2025 at the time of manuscript submission. It was updated in March 2026, at the time of manuscript acceptance, to include additional metadata (this readme, data dictionary, and file level metadata). The data did not change. For details on how to navigate data packages generated by this project, see https://data.ess-dive.lbl.gov/portals/PNNLRiverCorridorSFA/About. In addition to a readme, this data package also includes a file-level metadata (FLMD) file that describes each file and a data dictionary (DD) that describes all column/row headers and variable definitions. This dataset is comprised of (1) 8 folders; (2) the detailed flight configuration html files; (3) field metadata; (4) a readme; (5) a data dictionary; and (6) file-level metadata. The folders “2024_10_18_d01” and “2024_10_18_d02” contain the original drone photos for the two drone flights (d01 and d02) on October 18, 2024. The reconstruction results from each of the approaches are in the folders called “ODM_SfM”, “VGGSfM”, “VGGTLong”, and “LiDAR”. The ground truth measurements are in the folder called “optical_level_kit”. Lastly, results comparing the different approaches are in the folder called “comparisons”. All files are .csv, .html, .jpg, .obj, .txt, and .npy. For information on using the .obj and .npy files, see the readme files within the same folder as the files.

54 ENVIRONMENTAL SCIENCES↗
NASA NTRSDate not supplied

Harnessing Artificial Intelligence for Medical Diagnosis and Treatment During Space Exploration Missions

From May 8th to June 9th, 2023, I had the opportunity to participate in an experiential learning experience at Johnson Space Center in Houston, TX with Exploration Medical Capability (ExMC), an element of the NASA Human Research Program. During this research experience, I was not only able to work on the above titled research project, but also gain an immense exposure to the field of aerospace medicine, make numerous connections within the field, tour NASA facilities, as well as travel to the Aerospace Medical Association Annual Conference (AsMA) in New Orleans. To briefly introduce my project, it is well understood that the medical capabilities available to crew medical officers (CMOs) on the International Space Station will be different than the capabilities available and needed during deep space exploration missions to the Moon, Mars, and beyond. Ground support is particularly limited due to distance, communication delays (or lack of communication), and lack of resupply. Therefore, to support medical care by CMOs on these missions, robust clinical decision support systems (CDSSs) must be designed. The recent publication and public launch of generative artificial intelligence (AI) tools based upon large language models (LLM) such as ChatGPT provides the opportunity to create a smart assistant for onboard triage, diagnosis, and treatment of medical conditions. Ultimately, the overall purpose of the project was to research what AI tools currently exist or are in development, and to see how they might be implemented onboard during exploration class spaceflights of the future. The ExMC element is actively developing several tools to be used in preparation for and during deep space exploration missions. One of those tools, known as IMPACT, is a probabilistic risk assessment model which can be used to propose a desired medical system (based on mass and volume) and suggest the clinical outcomes likely to occur for a design reference mission (DRM). The group recently presented the IMPACT model and a DRM of interest titled “Modified Long Duration Lunar Orbital and Lunar Surface” (mLDLOLS) at the recent AsMA conference. The mLDLOLS mock mission is a 9 month and 6-day deep space exploration mission consisting of time in Moon’s orbit (3 months on the Gateway space station), on the lunar surface (3 months within habitat), and another 3 months on Gateway before return to Earth. For this DRM, IMPACT ultimately outlined a preferred medical system that was then associated with medical conditions considered to be most likely based on frequency, most likely to cause astronaut task time loss (TTL), most likely to cause return to definitive care (RTDC), and most likely cause loss of crew life (LOCL). IMPACT also highlighted the medical capabilities/skills that would be required to care for those medical conditions, such as performing a history of present illness or musculoskeletal exam with ultrasound. The primary objective of the project was to perform a survey of the AI tools and systems applicable to the conditions outlined for the proposed mLDLOLS mission. Using PubMed (including most relevant MeSH terms) and Google Scholar, we then created a robust annotated bibliography organized by condition. The 56-page and over 500 reference annotated bibliography was subsequently used to create a review outline that would become the basis for drafting of a future publication. For the review outline, we took those medical conditions researched within the annotated bibliography (condition-based approach) and deployed a systems-based approach, combining those medical conditions and related tools into ten categories. These categories included general/all-purpose CDSSs, tools to diagnose or manage respiratory, dermatologic, neurologic, auditory and vestibular, ophthalmic, musculoskeletal, infection-associated, and gynecologic conditions, as well as tools that could be deployed in the setting of trauma/emergency. With the completion of the 30-page outline, we then began drafting the review paper. To conclude the research experience, I presented the findings from our survey to the ExMC Clinical and Science team. With these objectives, I ultimately learned about the number of AI tools that exist today to assist medical professionals with the triage, diagnosis, and management of several medical conditions. These tools can span from chatbot assistants to help triage knee pain to vision transformer models that can identify ophthalmic conditions based on ocular surface images captured with a cell phone. We also highlighted the current gaps that exist in the literature alongside the advancements that are needed to make the desired CDSS for deep space exploration missions. With this experience, I certainly confirmed an existing career goal and identified several additional skills needed to become an aerospace medical doctor including knowledge of critical care in an extreme medicine setting, aerospace engineering and human integration systems, artificial intelligence, machine learning, and risk models. I also identified numerous transferable skills for this career goal including the basic knowledge of medicine (MD), deployment of the scientific method for critical thought about new scientific questions (PhD), review of published literature, including creating an annotated bibliography (PhD), as well as detailed scientific writing (PhD). The results of my research will likely guide the design of an all-encompassing onboard medical assistant for use during deep space exploration missions of the future. I plan on sharing the outcomes from this experience with my peers at a student seminar in the Fall semester on August 30th. During the seminar, I will detail the project, my experience at NASA and AsMA, as well as offer best practice guidelines for students entertaining similar experiences or careers. In conclusion, I would like to thank the WVU School of Medicine, Research and Graduate Education office, as well as NASA ExMC for the unwavering support of this life-changing experience.

Ryan A. Lacinski↗
DOE OSTI2025

Morphotype-resolved characterization of microalgal communities in a nutrient recovery process with ARTiMiS flow imaging microscopy

Microalgae-driven nutrient recovery represents a promising technology for phosphorus removal from wastewater while simultaneously generating biomass that can be valorized to offset treatment costs. As full-scale processes come online, system parameters including biomass composition must be carefully monitored to optimize performance and prevent culture crashes. In this study, flow imaging microscopy (FIM) was leveraged to characterize microalgal community composition in near real-time at a full-scale municipal wastewater treatment plant (WWTP) in Wisconsin, USA, and population and morphotype dynamics were examined to identify relationships between water chemistry, biomass composition, and system performance. Two FIM technologies, FlowCam and ARTiMiS, were evaluated as monitoring tools. ARTiMiS provided a more accurate estimate of total system biomass, and estimates derived from particle area as a proxy for biovolume yielded better approximations than particle counts. Deep learning classification models trained on annotated image libraries demonstrated equivalent performance between FlowCam and ARTiMiS, and convolutional neural network (CNN) classifiers proved significantly more accurate when compared to feature table-based dense neural network (DNN) models. Across a two-year study period, Scenedesmus spp. appeared most important for phosphorus removal, and were negatively impacted by elevated temperatures and increase in nitrite/nitrate concentrations. Chlorella and Monoraphidium also played an important role in phosphorus removal. For both Scenedesmus and Chlorella, smaller morphological types were more often associated with better system performance, whereas larger morphotypes likely associated with stress response(s) correlated with poor phosphorus recovery rates. Furthermore, these results demonstrate the potential of FIM as a critical technology for high-resolution characterization of industrial microalgal processes.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2025

Idiomatic Correctness-Checking via Julienne in Fortran 2023

This paper presents a unified approach to unit testing and runtime assertion checking using Fortran 2023. The paper describes the support for our approach in the Julienne framework. Julienne leverages recent Fortran standards to implement object-oriented design patterns, support testing parallel programs, and implement functional programming patterns in order to craft idioms inspired by natural-language expressions. The presented idioms employ novel operators to write expressions that evaluate to a test-diagnosis object encapsulating two components: (1) the test outcome or assertion outcome and (2) an automatically generated diagnostic string. Two other novel aspects of the approach include (1) the ability to enforce assertions inside pure procedures and (2) the ability to output rich diagnostic information inside pure procedures during error termination when assertions fail. The latter capability mitigates against a reason that Fortran programmers commonly cite for not writing pure procedures: difficulty obtaining useful program output inside pure procedures when debugging code. This paper demonstrates how the adoption of the proposed idioms leads naturally to a unifying theme across two otherwise disparate technologies: unit testing and runtime assertion checking. Finally, this paper describes the usage of the Julienne testing framework for writing unit tests and assertions in the Matcha high-performance computing application and the Fiats deep learning library.

Rouson, Damian↗
NASA NTRS2012

Launch Pad Closeout Operations for the Mars Science Laboratory's Heat Rejection System

The Mars Science Laboratory (MSL) rover was launched on an Atlas V on November 26, 2011. Preparations were carried out prior to launch in order to closeout the spacecraft's complex heat rejection system (HRS), which consists of two mechanically pumped CFC-11 fluid loops. The first HRS loop, onboard the Curiosity rover, was fully integrated, filled with CFC-11, and successfully operated prior to launch pad operations; however, the second thermal loop, called the cruise HRS loop, required final mechanical and thermal integration activities to occur while on the launch pad in order to accommodate the last minute installation of the rover's Multi-Mission Radioisotope Thermoelectric Generator (MMRTG) power source. In order to prevent overheating of propellant tanks and critical avionics equipment buried deep within the spacecraft's aeroshell, the MMRTG needed to be pre-cooled using a separate non-flight mechanically pumped fluid loop prior to and during the final closeout and subsequent startup of the flight loop. This paper outlines the various steps that took place to safely install the MMRTG while carefully transitioning from the pre-cooling operation to the final startup and operation of the flight cruise HRS loop. Temperature data of the launch pad thermal transition from the ground support loop activity to the final flight loop operation is presented. Some background development of the ground support loop and lessons learned are also discussed. This successful launch pad integration activity required a close-knit coordination between NASA KSC, JPL, the Department of Energy, Idaho National Labs, Pratt and Whitney Rocketdyne Inc., Teledyne Technologies Inc., ULA, and Advanced Thermal Sciences Corp.

thermal↗
NASA NTRS2023

Explainable deep learning for insights in El Niño and river flows

The El Niño Southern Oscillation (ENSO) is a semi-periodic fluctuation in sea surface temperature (SST) over the tropical central and eastern Pacific Ocean that influences interannual variability in regional hydrology across the world through long-range dependence or teleconnections. Recent research has demonstrated the value of Deep Learning (DL) methods for improving ENSO prediction as well as Complex Networks (CN) for understanding teleconnections. However, gaps in predictive understanding of ENSO-driven river flows include the black box nature of DL, the use of simple ENSO indices to describe a complex phenomenon and translating DL-based ENSO predictions to river flow predictions. Here we show that eXplainable DL (XDL) methods, based on saliency maps, can extract interpretable predictive information contained in global SST and discover SST information regions and dependence structures relevant for river flows which, in tandem with climate network constructions, enable improved predictive understanding. Our results reveal additional information content in global SST beyond ENSO indices, develop understanding of how SSTs influence river flows, and generate improved river flow prediction, including uncertainty estimation. Observations, reanalysis data, and earth system model simulations are used to demonstrate the value of the XDL-CN based methods for future interannual and decadal scale climate projections.

SST↗
NASA NTRS2019

Feature Learning for Multispectral Satellite Imagery Classification Using Neural Architecture Search

Automated classification of remote sensing data is an integral tool for earth scientists, and deep learning has proven very successful at solving such problems. However, building deep learning models to process the data requires expert knowledge of machine learning. We introduce DELTA, a software toolkit to bridge this technical gap and make deep learning easily accessible to earth scientists. Visual feature engineering is a critical part of the machine learning lifecycle, and hence is a key area that will be automated by DELTA. Hand-engineered features can perform well, but require a cross functional team with expertise in both machine learning and the specific problem domain, which is costly in both researcher time and labor. The problem is more acute with multispectral satellite imagery, which requires considerable computational resources to process. In order to automate the feature learning process, a neural architecture search samples the space of asymmetric and symmetric autoencoders using evolutionary algorithms. Since denoising autoencoders have been shown to perform well for feature learning, the autoencoders are trained on various levels of noise and the features generated by the best performing autoencoders evaluated according to their performance on image classification tasks. The resulting features are demonstrated to be effective for Landsat-8 flood mapping, as well as benchmark datasets CIFAR10 and SVHN.

Robert Campbell↗
DOE OSTI2025

Artificial Intelligence and Machine Learning Applications in Modern Power Systems

Machine learning (ML) and artificial intelligence (AI) algorithms offer valuable tools for the analysis and interpretation of large datasets. These tools have the capability to uncover insights that may not be readily apparent within these datasets. In recent years, the integration of ML and AI has become increasingly prevalent in various applications within the power system domain. One of the earliest instances of machine learning in power systems can be traced back to demand forecasting, where artificial neural networks were employed for short-term load forecasting. In contemporary power systems, an abundance of high-resolution geospatial and temporal data is generated at various time intervals, ranging from sub-seconds (Phasor Measurement Units or PMUs) to seconds (Supervisory Control and Data Acquisition or SCADA), minutes (Process Information or PI), and extending to days, months, and years. These datasets contain valuable information concerning system reliability and performance. This information holds the potential to offer critical insights into system operations, as well as solutions for predicting and mitigating contingencies to prevent cascading outages. Despite the immense power of machine learning tools, system operators, planners, and utilities often exhibit hesitancy in fully embracing AI-enabled system operations and planning. This cautious approach persists, even as numerous diverse applications of machine learning continue to emerge in the realm of power systems. In this chapter, our focus will delve deep into ML and AI applications tailored for power systems. These applications aim to furnish system operators with enhanced situational awareness and augment their decision-making capabilities, especially during challenging operating conditions. Specific areas of interest encompass root cause analyses of electricity market datasets and the strategic selection of representative samples from vast power system databases for training ML/AI models. Finally, the chapter will conclude with a short discussion on the future of ML/AI in power systems and possible directions that the industry is moving towards.

power system applications, machine learning (ML), ↗
NASA NTRSDate not supplied

Autoencoders for Denoising Atmospheric Profiles from ICESat-2

Abstract: The 2nd generation Ice, Cloud, and land Elevation Satellite (ICESat-2) is an altimetry mission designed primarily for measuring ice sheet elevation and sea ice thickness, provides atmospheric profiles of clouds and aerosols at 532 nm using a photo counting detection approach. While highly sensitive for the detection of tenuous aerosol and cloud features, during the day signal-to-noise-ratio (SNR) photon counting detectors are adversely impacted by solar contributions to the total signal. Averaging the data to coarser horizontal resolutions has been the standard way to increase SNR and thus allow clouds and aerosols to be more easily detectable. Recent work has demonstrated success in boosting SNR without decreasing resolution using advanced filtering techniques [Yorks et al., 2021], however, rapid advancements in Deep Learning based image denoising algorithms can further improve the SNR. Here, we present results using a state-of-the-art Deep Learning autoencoder applied to noisy ICESat-2 data to improve daytime SNR and discuss implications for atmospheric feature detection, classification, and optical property retrievals.

denoising↗
DOE OSTI2025

Enhancing generative molecular design via uncertainty-guided fine-tuning of variational autoencoders

In recent years, deep generative models have been successfully applied to various molecular design tasks, particularly in the life and materials sciences. One critical challenge for pre-trained generative molecular design (GMD) models is to fine-tune them to be better suited for downstream design tasks that aim at optimizing specific molecular properties. However, redesigning and training an existing effective generative model from scratch for each new design task are impractical. Furthermore, the black-box nature of typical downstream tasks that involve property prediction makes it nontrivial to optimize the generative model in a task-specific manner. In this work, we propose an uncertainty-guided fine-tuning strategy that can effectively enhance a pre-trained variational autoencoder (VAE) for GMD through performance feedback in an active learning setting. The strategy begins by quantifying the model uncertainty of the generative model using an efficient active subspace-based UQ (uncertainty quantification) scheme. Next, the decoder diversity within the characterized model uncertainty class is explored to expand the viable space of molecular generation. The low-dimensionality of the active subspace makes this exploration tractable using a black-box optimization scheme, which in turn enables us to identify and leverage a diverse set of high-performing models to generate enhanced molecules. Empirical results across six target molecular properties using multiple VAE-based generative models demonstrate that our uncertainty-guided fine-tuning strategy consistently leads to improved models that outperform the original pre-trained models.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2026

Uncertainty guided online ensemble for non-stationary data streams in fusion science

Machine Learning (ML) is poised to play a pivotal role in the development and operation of next-generation fusion devices. Fusion data shows non-stationary behavior with distribution drifts, resulted by both experimental evolution and machine wear-and-tear. ML models assume stationary distribution and fail to maintain performance when encountered with such non-stationary data streams. Online learning techniques have been leveraged in other domains, however it has been largely unexplored for fusion applications. In this paper, we investigate online learning for continuous adaptation to drifting data streams in the prediction of Toroidal Field (TF) coils deflection at the DIII-D fusion facility. We further address the short-term performance degradation inherent to standard online learning, which arises because ground truth is unavailable at prediction time. To mitigate this issue, we propose an uncertainty-guided online ensemble framework. The method leverages the Deep Gaussian Process Approximation (DGPA) for calibrated uncertainty estimation and uses these uncertainty measures to guide a meta-algorithm that aggregates predictions from learners trained over different historical horizons. Our results show that online learning reduces prediction error by 80% compared to a static model. The online ensemble and the proposed uncertainty-guided ensemble further reduce error by approximately 6%, and 10% respectively, relative to standard single-model online learning, while also providing calibrated uncertainty estimates to support operational decision-making.

AI↗
DOE OSTI2024

Improving Robustness of Spectrogram Classifiers with Neural Stochastic Differential Equations

Signal analysis and classification is fraught with high levels of noise and perturbation. Computer-vision-based deep learning models applied to spectrograms have proven useful in the field of signal classification and detection; however, these methods aren't designed to handle the low signal-to-noise ratios inherent within non-vision signal processing tasks. While they are powerful, they are currently not the method of choice in the inherently noisy and dynamic critical infrastructure domain, such as smart-grid sensing, anomaly detection, and non-intrusive load monitoring. Currently, these models can be brittle, which makes them susceptible to noisy input. This also means they have sub-optimal stability of explanation outputs. Experts and technicians using these models to make decisions in real world scenarios need assurance that a model is performing as it is supposed to. The classification or prediction outputs it generates should be sound and grounded, not likely to change in the presence of shifting noise landscapes. In this work, we explore the idea of Neural Stochastic Differential Equations (NSDE's) to improve the robustness of models trained to classify time series data and the effect of NSDE's on the explainability of outputs. We then test the effectiveness of these approaches by applying them to a non-intrusive load monitoring (NILM) dataset that consists of simulated harmonic signals injected into a real building.

Brogan, Joel↗