Search NASA⌕ Search

SEARCH · Search NASA

Results for “AI Machine 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 469 records · Page 26
All sourcesNASA NTRSDOE OSTI
DOE OSTI2025

Multi-scale, Multi-disciplinary, and Multi-agent Explainable AI with Koopman-Undergirded Learning, Prediction, and Analysis (M3EA KULPA) (Project Closeout Report)

The goal of this project was to develop and use domain-aware machine learning formulations, based on the Koopman Operator (KO), for modelling multi-scale, multi-disciplinary (e.g., multi-physics), and/or multi-agent systems. The project developed these formulations for the following cases: • Systems with dynamics at two separate time scales, • Systems with a bi-level hierarchical control structure, • Systems with bi-level hierarchical control and dynamics at two separate time scales (the lower level controls operating at the faster time scale), and • Systems with n separate but interacting agents/disciplines (with/without control, respectively); the controls for each agent could include bi-level hierarchical control and dynamics at two separate time scales as described above. The project then defined a set of dynamical systems consisting of different nonlinear oscillators that could be used to test these different formulations and then subsequently learned the KO models for those systems. With the KO models, we were able to do the following: • Quantify system stability, including both long-term and transient behavior, • Quantify the effects of feedbacks between the different time scales and agents/disciplines in terms of those feedbacks’ effects on system stability, • Replace a standard Proportional-Integral (PI) control in the hierarchical control structure with a KO-based Linear-Quadratic Regular (LQR), a form of optimal control, • Calculate optimal supervisory control policies a) with and without time scale separated dynamics at the lower level control levels and b) with both PI and KO-based LQR lower level control policies, and • Calculate dynamic Nash equilibria for multi-agent systems where each agent makes its own control decisions.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2020

Machine learning for imaging Cherenkov detectors

Imaging Cherenkov detectors are largely used in modern nuclear and particle physics experiments where cutting-edge solutions are needed to face always more growing computing demands. This is a fertile ground for AI-based approaches and at present we are witnessing the onset of new highly efficient and fast applications. This paper presents novel directions with applications to Cherenkov detectors. In particular, recent advances on detector design and calibration, as well as particle identification are presented.

47 OTHER INSTRUMENTATION↗
DOE OSTI2024

Microscopy modality transfer of steel microstructures: Inferring scanning electron micrographs from optical microscopy using generative AI

Scanning electron microscopy (SEM) is resource intensive, which limits its throughput in some applications. As an alternative, we propose applying computer vision and machine learning to generate high-quality synthetic SEM micrographs from micrographs obtained using light optical microscopy (LOM). Working with a correlated LOM/SEM dataset of dual-phase steel images, we test generative models of various architectures, including encoder-decoder networks, generative adversarial networks (GANs), and diffusion-based models. We find that the diffusion models significantly outperform other methods on both qualitative and quantitative assessments, while preserving key metallurgical meaning. This work establishes diffusion as the state-of-the-art for microscopy modality transfer and demonstrates the potential of AI-powered microscopy to enhance LOM with micron scale structural recreation.

Computer vision↗
DOE OSTI2026

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.]↗
DOE OSTI2026

Exploration of Real Time Inference for MI-RR Deblending on GPU/TPU Systems

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 [Fermilab; Cornell U.]↗
DOE OSTI2026

Analysis of Slow Spill Data for the Mu2e Experiment

The execution of the Mu2e experiment requires a stable, low-intensity proton beam from the Delivery Ring to produce clean data and protect equipment. This is done by performing a “slow extraction,” which is the gradual contraction of the stable region within the accelerator’s beam pipe. The Delivery Ring is currently unable to perform slow extraction with the stability required by Mu2e. To resolve this, the FAN-C team is training machine learning models with the purpose of replacing the Delivery Ring’s current PID controllers with AI-powered controllers. Training these models requires clean, processed data from slow spills. Over the course of this project, data from previous slow spills were processed and analyzed, and the clean data, graphs, and insights gained from the process were provided to the FAN-C team to assist them in their efforts.

Osborn, Thomas [Purdue U., West Lafayette]↗
NASA NTRS2026

Machine Learning for Predicting Team Functioning in HERA Missions

Team functioning is integral to success in future long term space exploration missions. Proactively detecting declines in team functioning can mitigate conflict and ensure mission success. This project developed a speech-based artificial intelligence (AI) system that unobtrusively predicts degradation in team functioning, including performance and cohesion, in the Human Exploration Research Analog (HERA) Campaigns 4 and 5. The AI system conducted automated analysis of the prosodic (tone of voice) and linguistic (language content) components of speech, modeling interpersonal dynamics at both the turn-taking and day-wide levels. We investigated team functioning via observing structured interactions (i.e., multi-mission space exploration vehicle-extra vehicular activity [MMSEV-EVA], team interaction battery [TIB]) and unstructured interactions before the MMSEV-EVA task. We developed machine learning models to predict team functioning (objective task accuracy, self reported team efficacy and self reported team cohesion) by analyzing OpenSmile acoustic features, linguistic descriptors extracted via the linguistic inquiry and word count (LIWC) dictionary, and semantic embeddings. In the TIB, static models using logistic regression and random forests were not able to predict task accuracy, but predicted team efficacy and cohesion during both the decision making and relational tasks to a moderate level (60-70%). Majority voting on the individual turns to predict day long team efficacy further increased accuracies (70-80%). Finally, long short-term memory (LSTM) models showed the best performance across all variables (80-91%), including task performance. In the MMSEV-EVA, static models achieved an accuracy of 60% with majority voting, which increased to 80% through the incorporation of mission day as a variable, accounting for the learning effect. A key finding across both tasks was the "team-dependent" nature of these interactions; models achieved much higher accuracy when trained on prior days of the same team's data rather than attempting to generalize across entirely different teams, with even 1-2 days of prior data per team achieving 5-15% improvement over team-independent models. In addition, the incorporation of pre-task data from the same team also improves model performance, e.g., incorporating data from the decision-making task of the TIB, which preceded the relational task, improved the prediction of team efficacy and cohesion during the latter. We compared model performance when trained on machine-generated data compared to data that had been further corrected by human annotators. Overall, models trained on human-corrected data exhibited a modest improvement in performance, particularly when acoustic features were used. We found no significant correlation between word error rate (WER) and model accuracy (r(55) = -0.08, p = 0.51), but model’s accuracy was significantly higher for medium/high quality transcription (0.74 (SD = 0.48)) compared to the low-quality group (0.64 (SD = 0.36)) (t(63)=2.82, p = 0.006). Based on these, several design recommendation emerge, that could inform Standards at NASA. Models predicting team functioning should incorporate at least one to two days of historical interaction data, include brief pre-task discussions, and explicitly model temporal learning effects, especially for longer operational tasks. Minimum quality standards for automated speech-processing pipelines are needed, given the performance gains observed with manually corrected acoustic data. Finally, systems should leverage both acoustic features and language embeddings in complementary ways, with modality choices and fusion strategies tailored to mission context, task demands, and data quality requirements.

Shrivatsa Mishra↗
DOE OSTI2025

Agentic AI vs ML-Based Autotuning: A Comparative Study for Loop Reordering Optimization

High Performance Computing (HPC) applications rely heavily on code optimizations to achieve good performance on modern CPU and GPU architectures. Traditional Machine Learning auto-tuning approaches have demonstrated success in exploring high-dimensional spaces, but they often require expensive compile-run evaluations and lack adaptability for large HPC applications. The recent advances in Large Language Models (LLMs) and Agentic AI systems raise intriguing questions about the potential of these approaches to address specific optimization methodologies. This work aims to answer an essential question for the HPC community: “How Agentic AI Systems Compare to Traditional ML Autotuning Techniques?” To address this question, we present a comparative analysis between a traditional ML-based optimization approach and an Agentic AI system, evaluating their respective capabilities and limitations for loop-level optimization. In addition, we introduced a new Agentic AI system named LoopGen-AI using three different Large Language Models: GPT-4.1, Claude 4.0, and Gemini 2.5. A key finding is that LoopGen-AI achieves competitive per-formance with only a few program runs, the reasoning logs from the agents revealed that their decisions rely heavily on the combination of semantic understanding of the target kernel with dynamic feedback from the environment, highlighting a promising new dimension in performance tuning. In contrast, ML-based autotuners focus on statistical exploration, and require orders of magnitude more runs to reach peak performance. Additionally, our analysis shows that prompt engineering, particularly using Persona + Context Manager patterns, significantly impacts the effectiveness of Agentic AI. Our results indicate that while Agentic AI systems are not yet a complete replacement for ML-based autotuners, it can effectively complement traditional methods.

Rosas, Miguel Romero↗
DOE OSTI2021

A Reconfigurable Neural Network ASIC for Detector Front-End Data Compression at the HL-LHC

Despite advances in the programmable logic capabilities of modern trigger systems, a significant bottleneck remains in the amount of data to be transported from the detector to off-detector logic where trigger decisions are made. We demonstrate that a neural network (NN) autoencoder model can be implemented in a radiation-tolerant application-specific integrated circuit (ASIC) to perform lossy data compression alleviating the data transmission problem while preserving critical information of the detector energy profile. For our application, we consider the high-granularity calorimeter from the Compact Muon Solenoid (CMS) experiment at the CERN Large Hadron Collider. The advantage of the machine learning approach is in the flexibility and configurability of the algorithm. By changing the NN weights, a unique data compression algorithm can be deployed for each sensor in different detector regions and changing detector or collider conditions. To meet area, performance, and power constraints, we perform quantization-aware training to create an optimized NN hardware implementation. The design is achieved through the use of high-level synthesis tools and the hls4ml framework and was processed through synthesis and physical layout flows based on a low-power (LP)-CMOS 65-nm technology node. The flow anticipates 200 Mrad of ionizing radiation to select gates and reports a total area of 3.6 mm 2 and consumes 95 mW of power. The simulated energy consumption per inference is 2.4 nJ. Furthermore, this is the first radiation-tolerant on-detector ASIC implementation of an NN that has been designed for particle physics applications.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗
DOE OSTI2025

Stacked networks improve physics-informed training: Applications to neural networks and deep operator networks

Physics-informed neural networks and operator networks have shown promise for effectively solving equations modeling physical systems. However, these networks can happen to be difficult or impossible to train accurately. Here, we present a novel multifidelity framework for stacking physics-informed neural networks and operator networks that facilitates training. We successively build a chain of networks, where the output at one step can act as a low-fidelity input for training a longer chain, gradually increasing the expressivity of the learnt model. The equations imposed at each step of the iterative process can be the same or different (akin to simulated annealing). The iterative (stacking) nature of the proposed method allows us to learn progressively features of a solution which could have been hard to learn directly. Through benchmark problems including a nonlinear pendulum, the wave equation, and the viscous Burgers equation, we show how stacking can be used to improve the accuracy and reduce the required size of physics-informed neural networks and operator networks.

97 MATHEMATICS AND COMPUTING↗
NASA NTRSDate not supplied

Evaluating Machine Learning Approaches to Plume Tracking

On July 15, 2022, the Hunga Tonga-Hunga Ha’apai (HTHH) submarine volcano erupted, propelling trace gasses and ash through the troposphere and up into the stratosphere. Previous studies manually tracked the aerosol and trace gas plumes over time across different positions in the southern hemisphere. Using imagery from NASA’s Earth Observing System, including MODIS aerosol products and OMI sulfur dioxide products, this research demonstrates how open-source machine learning (ML) models, like Meta’s Segment Anything Model (SAM), can perform automatic plume tracking following the Hunga Tonga eruption. This extensible methodology, and modular data processing and modeling pipeline, establishes a framework for systematically and rapidly studying natural disasters, including additional volcanic eruptions and large-scale wildfires. By combining advanced machine learning techniques, such as SAM’s zero-shot learning, with large volumes of NASA’s Earth Observation and remote sensing data, this work shows how AI and open science can accelerate research and generate actionable results, even for unprecedented events. The tools and technologies presented here can help translate earth science to action from NASA’s current and future Earth observing satellite missions, and assist researchers and stakeholders in understanding, mapping, and responding to natural disasters in a changing world.

machine learning↗
DOE OSTI2021

Programs and Code for Geothermal Exploration Artificial Intelligence

The scripts below are used to run the Geothermal Exploration Artificial Intelligence developed within the "Detection of Potential Geothermal Exploration Sites from Hyperspectral Images via Deep Learning" project. It includes all scripts for pre-processing and processing, including: - Land Surface Temperature K-Means classifier - Labeling AI using Self Organizing Maps (SOM) - Post-processing for Permanent Scatterer InSAR (PSInSAR) analysis with SOM - Mineral marker summarizing - Artificial Intelligence (AI) Data splitting: creates data set from a single raster file - Artificial Intelligence Model: creates AI from a single data set, after splitting in Train, Validation and Test subsets - AI Mapper: creates a classification map based on a raster file

15 GEOTHERMAL ENERGY↗
NASA NTRSDate not supplied

Repurposing Drilling Control Diagnostics for Subsurface Edge Detection and Boundary Advisement During Planetary Drilling

Informed decision-making during lunar drilling and sampling missions will require data monitoring tools and specialized ground data systems. Accurate and updated situational awareness, with ongoing data monitoring, is critical for timely responses by to incoming science data. Traverse plans and scheduled activities may need to be flexibly changed in order to react to unexpected data or situations. Unlike (for example) Mars missions, the relative lightspeed closeness of the Moon allows for near-real-time ground processing of incoming mission and instrument data. An Apollo-class lunar regolith drill will in a sense “travel” a meter or two vertically at a given subsurface characterization site. As the drill penetrates into lunar regolith, it is likely to encounter a range of material densities, orientations, fracture toughness, and (perhaps) ice percentages. Lunar drill telemetry can provide science teams with a valuable first look into the subsurface structure, the regolith bulk properties, and constituents at each drilled site. Real-time AI-based recognition and reaction to downhole situations has been developed for automated deeper drilling on Mars and beyond. We can leverage the same knowledge bases and pattern-matching as areal-time interpreter of the subsurface, a situational awareness tool during drilling operations. We recently (Sept. 2019) demonstrated this AI drilling monitoring and analysis capability, in control of in-situ drilling and sampling operations, mounted on a KREX-2 rover in Chile’s Atacama Desert. Terrestrial automated drilling log analyses in oil exploration have used similar machine learning techniques in classifying and identifying features in drilling logs –but these typically are designed assuming a drilling fluid influencing downhole measurements and data (permeability, resistivity). Drilling models and existing AI software designed to detect and respond to drilling faults and hard materials can be repurposed, for near-real-time (ground-based) interpretation of drilling telemetry –a potentially valuable advisory tool for strata boundaries and changes in drilling parameters. On the Moon, this approach could be used to study the structure and to some extent the composition of lunar regolith vs. borehole depth, based on recognizable variations in fracture hardness, drilling energy and penetration rates while actively drilling. Since the early 2000s, a series of increasingly-capable real-time drilling telemetry interpretation and characterization software tools have been developed. These subsurface models and software tools have monitored the real-time drilling data received, and automatically identified changes in drill behavior (e.g., encountering a harder target layer, bit inclusions, drill choking due to infall downhole, and others) correlating these with subsurface structures and features. We discuss the mappings between drill borehole parameters, faults or events detected, and modeled changes in rock layer boundaries, in examples drawn from field testing at analog sites in an Arctic impact crater, Rio Tinto, and Chile’s Atacama Desert. These demonstrate how subsurface structural boundaries led to fault detections and responses by the software.

drilling advisor↗
DOE OSTI2025

Predicting homopolymer and copolymer solubility through machine learning

In this work, we report the development of multiple new machine learning (ML) models to accurately predict homopolymer/copolymer solubility over a diverse set of polymers & solvents, using explainable AI to provide polymer design recommendations.

Stubbs, Christopher D. [Department of Chemistry, C↗
DOE OSTI2022

Climbing the Summit and Pushing the Frontier of Mixed Precision Benchmarks at Extreme Scale

The rise of machine learning (ML) applications and their use of mixed precision to perform interesting science are driving forces behind AI for science on HPC. The convergence of ML and HPC with mixed precision offers the possibility of transformational changes in computational science. The HPL-AI benchmark is designed to measure the performance of mixed precision arithmetic as opposed to the HPL benchmark which measures double precision performance. Pushing the limits of systems at extreme scale is nontrivial -little public literature explores optimization of mixed precision computations at this scale. In this work, we demonstrate how to scale up the HPL-AI benchmark on the pre-exascale Summit and exascale Frontier systems at the Oak Ridge Leadership Computing Facility (OLCF) with a cross-platform design. We present the implementation, performance results, and a guideline of optimization strategies employed for delivering portable performance on both AMD and NVIDIA GPUs at extreme scale.

Lu, Hao↗