Search NASA⌕ Search

SEARCH · Search NASA

Results for “Machine learning (ML)”

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 1,513 records · Page 84

Fast Adaptive Neural Control of Resonant Extraction at Fermilab

We present the development of a machine learning (ML) based regulation system for third-order resonant beam extraction in the Mu2e experiment at Fermilab. Classical and ML-based controllers have been optimized using semi-analytic simulations and evaluated in terms of regulation performance and training efficiency. We compare several controller architectures and discuss the integration of neural control into an adaptive framework. We also present progress on surrogate models that predict the controller response given a spill intensity and controller action history. To enable real-time deployment, we report progress on implementing low-latency, edge-based inference suitable for hardware-constrained environments. Our results demonstrate the feasibility and advantages of ML-based control in managing complex, time-varying physical systems, with broader implications for accelerator operations and other domains requiring fast, adaptive regulation.

Berlioz, Jose Rene [Fermilab]↗

Fast Adaptive Neural Control of Resonant Extraction at Fermilab

We present progress on the development of a machine learning (ML) regulation system for third-order resonant extraction of the beam delivered to the Mu2e experiment at Fermilab. We consider classical and ML-based controllers optimized on semi-analytic simulations and provide perfor- mance comparisons for several models. Additionally, we discuss the efficiency of each model in training, which has implications for future work on adaptive control. We also discuss progress on developing optimized implementations of ML models for edge-based inference.

Whitbeck, A. [Fermilab]↗

Cooperative Agreement To Analyze variabiLity, change and predictabilitY in the earth SysTem (CATALYST)

CATALYST proposes to perform foundational coordinated research in a team-oriented collaborative effort aimed at advancing a robust understanding of modes of Earth system variability and change using models, observations and process studies. The proposed research will address the DOE/BER mission by exploring the limits to predictability, identifying fundamental underlying mechanisms, quantifying interactions among modes of variability, and discovering tipping points in the Earth system to understand the current and future impacts of these phenomena on regional and global climate. Four fundamental gaps are identified in our knowledge of the Earth system: 1) What are the limits to predictability on various timescales? 2) What are the interactions among modes of Earth system variability? 3) How may modes of Earth system variability change in response to changes in external forcing, and what are the tipping points involved with those changes? 4) How are high impact events connected to modes of Earth system variability and how may they change in the future? Related to those gaps in our knowledge, we formulate four research objectives to address those gaps using a combination of Earth system models (ESMs) and machine learning (ML) methods. Research Objective 1 (RO1) addresses the first gap above and proposes to understand modes of variability and their limits of predictability on subseasonal to decadal timescales using ESMs and ML. Research Objective 2 (RO2) addresses the second gap and proposes to use a hierarchy of models to understand relevant processes and feedbacks related to how modes of variability interact with each other. Research Objective 3 (RO3) is designed to study the third gap and proposes to examine the role of external forcings in changes of modes of Earth system variability and their interactions, and the likelihood and predictability of tipping points and irreversible changes. Research Objective 4 (RO4) will address the fourth gap and proposes to use high resolution ESMs, regionally refined models (RRMs), and ML methods to investigate the relationships between high impact events (e.g. flash droughts and precipitation extremes, atmospheric rivers (ARs), tropical cyclones (TCs), storm surge/sea level rise), the synoptic systems that produce them, and their changes related to modes of Earth system variability. The research will involve the use of the Community Earth System Model (CESM), Energy Exascale Earth System Model (E3SM), CMIP multi-model data sets, a hierarchy of simpler models, and numerous observational data sets. In the course of the proposed research, CATALYST will contribute to metrics and diagnostics that will be integrated in Coordinated Model Evaluation Capabilities (CMEC), particularly with regards to the Quasi-biennial Oscillation (QBO) and its interactions with the Madden-Julian Oscillation (MJO), high atmospheric pressure blocking, and new precipitation metrics.

54 ENVIRONMENTAL SCIENCES↗

Investigating the Future of Scientific Data Search [Slides]

Searching for usable, actionable, data in a trustworthy manner is a challenge across scientific communities. Artificial Intelligence (AI) and Machine Learning (ML) techniques may be leveraged to increase the utility of scientific data by: Demystify unstructured data to aid curation & sharing Surfacing hard to find datasets. User Experience (UX) Research can help uncover scientists needs & challenges finding data and using AI/ML enabled tools.

97 MATHEMATICS AND COMPUTING↗

Cybersecurity Center for Offshore Wind Energy (Final Project Report)

This project establishes a Cybersecurity Center for Offshore Wind Energy with the objective of designing and operating a cyber-physical testbed for wind energy farms (WEFs) that enables comprehensive cybersecurity research. The testbed incorporates a Supervisory Control and Data Acquisition (SCADA) system connected to turbine models via industrial-grade programmable logic controllers (PLCs) and remote terminal units (RTUs). It supports side-channel data acquisition, implementation and analysis of various cyberattack scenarios, and development of attack detection, mitigation, and best-practice guidance tailored to wind energy systems. During the project, the team expanded the number and fidelity of mathematical turbine models (MTMs), integrated these models with SCADA infrastructure, and deployed a scaled physical turbine and associated sensors. High-resolution operational and side-channel data streams were collected and used to refine machine-learning (ML)-based attack detection systems and to extend the WindCRAFT framework to multi-turbine threat scenarios. The project demonstrated a realistic, scalable environment for evaluating cyber threats, validated attack detection approaches using enriched datasets, and identified new multi-turbine and inter-turbine communication attack vectors. The resulting testbed, models, and security mechanisms provide a foundation for ongoing R&D and deployment of cyber-resilient offshore wind energy systems.

17 WIND ENERGY↗

Flexible AI Models for Grid Resilience

The rapid growth in size and complexity of artificial intelligence (AI) and machine learning (ML) models has led to increased energy demands, posing a threat to the reliability of the existing power grid. This project addresses the challenge of highly intermittent and energy-intensive inference workloads by (1) developing fidelity-adaptive neural networks capable of dynamic response to grid conditions and (2) integrating these networks with power flow simulations to assess their impact on power grid reliability. We will explore both top-down and bottom-up approaches to create hierarchies of submodels that provide a controlled trade-off between power draw and prediction accuracy. The top-down method utilizes NN pruning to reduce a flagship model into progressively smaller, energy-efficient variants. The bottom-up approach employs geometrically principled weight setting strategies to construct depth-efficient models from the ground up. A real-time hardware-in-the-loop (HIL) platform will be developed to simulate a scaled AC power grid, integrating live AI workload power draw and enabling dynamic model switching in response to grid feedback. This work will provide a novel framework for evaluating the impact of flexible AI/ML workloads on grid performance and establish new methodologies for energy-aware computing in data centers. The outcomes will demonstrate that adaptive AI/ML can play a critical role in improving grid stability while advancing NREL's leadership in energy-efficient computing research.

24 POWER TRANSMISSION AND DISTRIBUTION↗

Evaluation of Damage in Medium Voltage Cable Using Machine Learning

Developments in cable test instrumentation coupled with artificial intelligence and machine learning (ML) to aid in interpretation of cable test signals supports the feasibility for automated analysis of reflectometry tests for low voltage power cables. This work seeks to leverage prior ML work and success for low voltage cables to evaluate potential application to medium voltage (2kV to 10kV) installations. The Accelerated and Real-Time Environmental Nodal Assessment (ARENA) Cable Motor Test Bed at Pacific Northwest National Laboratory (PNNL) was used to test a medium voltage cable with several types of damage including thermal aging and low resistance conductor-to-shield faults. The cable was tested using an inductive clamshell coupler to protect the test instruments from the energized cable voltages that would damage the test instruments if coupled directly to the energized conductor.

42 ENGINEERING↗

Generative AI for Grid Operations [Slides]

In the last few years, the development and use of generative artificial intelligence (AI) and large-language models (LLMs) have changed the landscape of how AI and machine learning (ML) are being used in power systems. LLMs are built on foundational models based on large data sets that can be trained to provide information rapidly and through simple natural language prompts. Generative AI can then perform human-like tasks using ML models to identify and mimic pattens in the data sets. This presentation explores how generative AI can enhance grid operations by improving forecasts, enabling rapid contingency analyses, and offering real-time operational suggestions. By providing grid operators with valuable insights, generative AI will empower them to manage power systems more effectively.

24 POWER TRANSMISSION AND DISTRIBUTION↗

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↗

Towards a Robust Adaptive Digital Twin for Fusion Applications

The development of a digital twin system for fusion applications is essential for enhancing the prediction, analysis, and optimization of complex plasma processes. Machine learning (ML), particularly deep learning has demonstrated strong capabilities in modeling such highly nonlinear and intricate systems. However, two critical challenges limit the deployment of deep learning-based digital twins: Uncertainty Quantification (UQ) and data drift. UQ is vital for ensuring trustworthy predictions, especially in decision-support scenarios. Additionally, data-driven models are often sensitive to changes in the underlying data distribution, such as shot-to-shot variations in fusion experiments, which can lead to performance degradation over time. To address these challenges, we are developing an uncertainty-aware, adaptive digital twin framework. Our approach incorporates deep learning models enhanced with Gaussian Process approximations for predictive uncertainty estimation, coupled with an online learning mechanism that enables continuous model adaptation to new experimental data. This adaptive capability allows the data driven models to respond effectively to evolving plasma behaviors and equipment conditions. Specifically, to mitigate the effects of shot-to-shot drift, our system updates itself incrementally as new data becomes available, improving both robustness and fidelity. Our vision is to evolve this data driven model into a self-sustaining digital twin system that leverages UQ based feedback to continuously refine itself and potentially support real-time decision making. This presentation will cover a brief background on uncertainty quantification for ML, our ongoing effort on development of UQ capabilities for ML, our data science pipeline from data collection to model development and analysis and online learning framework for modeling coil deflection at DIII-D. I will also briefly touch upon opportunities and challenges in development of digital twin framework.

Sammuli, Brian [General Atomics]↗

Intelligent Experiments Through Real-time AI: Fast Data Processing and Autonomous Detector Control for sPHENIX and Future EIC Detectors (Final Report)

The overall vision of this project was to integrate real-time artificial intelligence (AI) directly into the data acquisition and detector-control systems of nuclear physics experiments, including both fast online event selection and an autonomous detector-control feedback loop. The work carried out under the award focused on the fast online event-selection half of that vision: the efficient recording of low-momentum heavy-flavor (HF) hadron decays in proton-proton collisions at the sPHENIX experiment at the Relativistic Heavy Ion Collider (RHIC)—an observable that requires fast tracking and topological trigger selection not previously demonstrated at RHIC, and that is essential for QCD studies at future facilities such as the Electron-Ion Collider (EIC). The autonomous detector-control (GPU-based feedback) component named in the project title remained a design concept and was not implemented under this award. The Massachusetts Institute of Technology (MIT) group led the offline simulation and data processing needed to train the machine-learning (ML) models, the translation of trained models to Field-Programmable Gate Array (FPGA) firmware using the hls4ml framework, and the physics validation of heavy-flavor reconstruction. Over the award period, the team developed and hardware-tested the principal components of an AI-based heavy-flavor trigger on simulated and recorded sPHENIX tracker data: a software Bipartite Graph Attention Network (BiGAT) trigger model reaching > 95% signal efficiency at 99% background rejection; an FPGA-native hit clusterizer matching the offline clustering; smaller networks synthesized to FPGA within the required sub-10 µs latency; and an assembled decoder–clusterizer–inference firmware chain exercised on the FELIX readout board. A complete, fully integrated hardware demonstrator was not finished within the award period. This report documents the project goals, the MIT group’s contributions, the technical accomplishments, and the outlook toward applications at the future EIC ePIC detector.

73 NUCLEAR PHYSICS AND RADIATION PHYSICS↗

Real-Time Inference For MI/RR Deblending

The Fermilab Main Injector (MI) and Recycler Ring (RR) share a common beam loss monitor (BLM) system, making loss events difficult to attribute to their source machine when beam is present in both simultaneously. The Real-time Edge AI for Distributed Systems (READS) project addresses this by deblending BLM readings in real time using machine learning (ML). The current FPGA based implementation meets the sub-3 ms latency requirement but carries a resource intensive hls4ml development cycle, motivating exploration of GPU based deployment. This paper characterizes inference latency on an NVIDIA Jetson Orin Nano and introduces a packet organization scheme for assembling synchronized event frames from seven distributed BLM DAQ streams. Using a Python based DAQ simulation with injected timing jitter in place of unavailable live beam data, the pipeline achieved an average end to end latency of 0.456 ms (σ = 0.122 ms) across 167,000 test frames, comfortably meeting the timing constraint. Early outliers were attributed to TensorRT warm-up rather than steady state limitations, suggesting GPU based inference is a viable alternative to the existing FPGA implementation.

Yu, Kellen [Cornell U.]↗

Applying Transfer Learning for Street-Scale Nuisance Flood Forecasting in Coastal-Urban Cities

An important challenge with Machine Learning (ML) is its transferability; that is, whether a ML model trained on one set of data can be applied to a second set of data without requiring a full re-training of the model. Transfer Learning (TL) addresses this challenge by transferring knowledge learned in the source domain (the data it was trained on) to the target domain (a second set of data that is statistically different but related, which the model was not trained on). This study investigates the use of TL for street-scale nuisance flood forecasting by exploring whether a ML model trained on data collected for one set of streets can effectively forecast flooding for another set of streets in the same city using TL. The envisioned use case is a city deploying a new flood depth monitoring sensor on a street and using TL to apply a ML model, trained on sensor data from an existing flood depth sensor network, to this new street. Eventually, the new flood depth sensor will have a sufficient dataset for training its own ML model, but TL can be used to fill the gap in time while this new dataset is being generated. This method is explored using a Long Short-Term Memory (LSTM) model trained on data for the flood-prone streets of Norfolk City, Virginia. The data used for training includes environmental time series (rainfall, tide), topographic features (Digital Elevation Model (DEM), Topographic Wetness Index (TWI), Depth To Water (DTW)), and street-scale flood depth time series obtained from a high-fidelity physics-based model, acting as a synthetic street-scale stream depth sensor dataset since actual stream depth sensor data is generally unavailable for most cities. A set of 180 flood-prone streets was used to train a base model, while another set of 180 flood-prone streets was used to re-train that model using different TL strategies. The results show that full-weight re-training proved most effective and minimal re-training of only the output layer was insufficient. The advantage of TL was most pronounced when target data was limited, meaning data collected at the new water depth sensor location included generally less than 18 flood events. As target data increased beyond 18 flood events, the benefit of TL diminished relative to training a ML model directly on the local flood events. These findings can assist cities as they implement street-scale flood sensing systems to create accurate forecasts for new sensing locations that do not yet have sufficient data records to train a local ML model.

Roy, Binata [Univ. of Virginia, Charlottesville, V↗

Physics-Informed Machine Learning for Modeling and Control of Dynamical Systems

Physics-informed machine learning (PIML) is a set of methods and tools that systematically integrate machine learning (ML) algorithms with physical constraints and abstract mathematical models developed in scientific and engineering domains. As opposed to purely data-driven methods, {PIML} models can be trained from additional information obtained by enforcing physical laws such as energy and mass conservation. More broadly, {PIML} models can include abstract properties and conditions such as stability, convexity, or invariance. The basic premise of {PIML} is that the integration of ML and physics can yield more effective, physically consistent, and data-efficient models. This paper aims to provide a tutorial-like overview of the recent advances in {PIML} for dynamical system modeling and control. Specifically, the paper covers an overview of the theory, fundamental concepts and methods, tools, and applications on topics of: 1) physics-informed learning for system identification; 2) physics-informed learning for control; 3) analysis and verification of {PIML} models; and 4) physics-informed digital twins. The paper is concluded with a perspective on open challenges and future research opportunities.

Nghiem, Truong↗

An Algebra of Machine Learners with Applications

Machine learning (ML) methods are increasingly being applied to solve complex, data-driven problems in diverse areas, by exploiting the physical laws derived from first principles such as thermal hydraulics and the abstract laws developed recently for data and computing infrastructures. These physical and abstract laws encapsulate, typically in compact algebraic forms, the critical knowledge that complements data-driven ML models. We present a unified perspective of these laws and ML methods using an abstract algebra (A;⊕,Ⓧ), wherein the performance estimation and classification tasks are characterized by the additive ⊕ operations, and the diagnosis, reconstruction, and optimization tasks are characterized by the difference Ⓧ operations. This abstraction provides ML codes and their performance characterizations that are transferable across different areas. We describe practical applications of these abstract operations using examples of throughput profile estimation tasks in data transport infrastructures, and power-level and sensor error estimation tasks in nuclear reactor systems.

Rao, Nageswara↗

Study of Overfitting by Machine Learning Methods Using Generalization Equations

The training error of Machine Learning (ML) methods has been extensively used for performance assessment, and its low values have been used as a main justification for complex methods such as estimator fusion and ensembles, and hyper parameter tuning. We present two practical cases where independent tests indicate that the low training error is more of a reflection of over-fitting rather than the generalization ability. We derive a generic form of the generalization equations that separates the training error terms of ML methods from their epistemic terms that correspond to approximation and learnability properties. It provides a framework to separately account for both terms to ensure an overall high generalization performance. For regression estimation tasks, we derive conditions for performance enhancements achieved by hyper parameter tuning, and fusion and ensemble methods over their constituent methods. We present experimental measurements and ML estimates that illustrate the analytical results for the throughput profile estimation of a data transport infrastructure.

Rao, Nageswara↗

The Cognitive Effects of Machine Learning Aid in Domain-Specific and Domain-General Tasks.

With machine learning (ML) technologies rapidly expanding to new applications and domains, users are collaborating with artificial intelligence-assisted diagnostic tools to a larger and larger extent. But what impact does ML aid have on cognitive performance, especially when the ML output is not always accurate? Here, we examined the cognitive effects of the presence of simulated ML assistance—including both accurate and inaccurate output—on two tasks (a domain-specific nuclear safeguards task and domain-general visual search task). Patterns of performance varied across the two tasks for both the presence of ML aid as well as the category of ML feedback (e.g., false alarm). These results indicate that differences such as domain could influence users’ performance with ML aid, and suggest the need to test the effects of ML output (and associated errors) in the specific context of use, especially when the stimuli of interest are vague or ill-defined

97 MATHEMATICS AND COMPUTING↗

A Survey of Machine Learning-Based Physics Event Generation

Event generators in high-energy nuclear and particle physics play an important role in facilitating studies of particle reactions. We survey the state of the art of machine learning (ML) efforts at building physics event generators. We review ML generative models used in ML-based event generators and their specific challenges, and discuss various approaches of incorporating physics into the ML model designs to overcome these challenges. Finally, we explore some open questions related to super-resolution, fidelity, and extrapolation for physics event generation based on ML technology.

Alanazi, Yasir↗