SEARCH · Search NASA

Results for “AI models”

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 163 records · Page 9

All sources NASA NTRS DOE OSTI

DOE OSTI2023

GeoAI for Public Health

Infectious disease spread within the human population can be conceptualized as a complex system composed of individuals who interact and transmit viruses through spatio-temporal processes that manifest across and between scales. The complexity of this system ultimately means that the spread of infectious diseases is difficult to understand, predict, and respond to effectively. Research interest in GeoAI for public health has been fueled by the increased availability of rich data sources such as human mobility data, OpenStreetMap data, contact tracing data, symptomatic online surveys, retail and commerce data, genomics data, and more. This data availability has resulted in a wide variety of data-driven solutions for infectious disease spread prediction which show potential in enhancing our forecasting capabilities. This chapter (1) motivates the need for AI-based solutions in public health by showing the heterogeneity of human behavior related to health, (2) provides a brief survey of current state-of-the-art solutions using AI for infectious disease spread prediction, (3) describes a use-case of using large-scale human mobility data to inform AI models for the prediction of infectious disease spread in a city, and (4) provides future research directions and ideas.

Zufle, Andreas↗

DOE OSTI2026

ProtNHF: Neural Hamiltonian Flows for Controllable Protein Sequence Generation

This dataset accompanies the publication "ProtNHF: Neural Hamiltonian Flows for Controllable Protein Sequence Generation". This paper introduces a new AI model for protein sequence generation. This dataset contains data related to experiments discussed in the publication. This includes generated sequences and evaluation metrics supporting all unconditional and bias-controlled experiments in the ProtNHF paper.

60 APPLIED LIFE SCIENCES↗

DOE OSTI2022

Using AI for Management of Field Emission in SRF Linacs

Field emission control, mitigation, and reduction is critical for reliable operation of high gradient superconducting radio-frequency (SRF) accelerators. With the SRF cavities at high gradients, the field emission of electrons from cavity walls can occur and will impact the operational gradient, radiological environment via activated components, and reliability of CEBAF’s two linacs. A new effort has started to minimize field emission in the CEBAF linacs by re-distributing cavity gradients. To measure radiation levels, newly designed neutron and gamma radiation dose rate monitors have been installed in both linacs. Artificial intelligence (AI) techniques will be used to identify cavities with high levels of field emission based on control system data such as radiation levels, cryogenic readbacks, and vacuum loads. The gradients on the most offending cavities will be reduced and compensated for by increasing the gradients on least offensive cavities. Training data will be collected during this year’s operational program and initial implementation of AI models will be deployed. Preliminary results and future plans are presented.

Carpenter, Adam↗

DOE OSTI2021

Modeling Noise: Paths toward AI-Enabled Stochastic Earth System Models and Parameterizations

Some of the key challenges in Earth system prediction arise from an uncertain representation of unpredictable natural variability, across time and space scales. This variability, hereafter referred to as noise, represents the quantity against which the strength of a signal of interest is measured to assess predictability. Underestimating or overestimating this noise in Earth system models can lead to issues ranging between overconfidence in an erroneous prediction and a lack thereof in an otherwise accurate one. Noise is part of the physical processes in the Earth system and can amplify or damp a signal of interest in a complex manner that is not systematically characterized. Specifically, while there has been significant progress in our understanding of multiscale interactions among known modes of variability (potentially predictable signals), how these are impacted by the noise is not clear. Recent effort toward stochastic parametrization schemes that provide a representation of noise due to uncertain sub-grid processes in climate models (Berner et al., 2017 and references therein) has shown promise not only in reducing biases and improving probabilistic prediction but also in improving the representation of natural variability in the model toward what is observed. However, today’s standard schemes for stochastic parametrization are still simplistic as they do not take the state of the atmosphere into account (other than by the use of multiplicative noise for model tendencies). Furthermore they require hand-tuning and trial-and-error testing for the magnitude of the added noise, which is difficult in a chaotic system that is as complex as the Earth system.

58 GEOSCIENCES↗

DOE OSTI2021

Using AI for Management of Field Emission in SRF Linacs

Carpenter, Adam↗

DOE OSTI2025

Risks Associated with Sharing the MOSSAIC APIs

The MOSSAIC APIs contain two files which, in theory, could be used to discover information about the pathology report data from the SEER registries on which the AI models were trained. In this document, we explain the contents of these files and assess the associated risk. APPENDIX A contains a set of slides to aid in the dissemination of this information.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2025

Utilizing AI and Spatial Data to Identify & Rapidly Disseminate Energy Infrastructure Insights

GeoGov Summit Final Presentation entitled "Utilizing AI and Spatial Data to Identify & Rapidly Disseminate Energy Infrastructure Insights". Maintaining the integrity of energy infrastructure plays a critical role in ensuring energy security. Robust foundational AI models using data from federal, state, industry, and other sources can help address integrity risk management & mitigation issues as well as evaluate extended use strategies. Trusted foundational models can help with industry adoption and accelerate innovation by enhancing integrity predictions, reduce costs, and informing infrastructure build-out. Coordination, collaboration & data sharing to develop robust models to aid in: Optimizing operations; Minimizing costs; Ensuring energy security.

Advanced Infrastructure Integrity Model (AIIM)↗

DOE OSTI2026

Robust Explanations using Diverse Adversarially Trained Ensembles, Multi-Modal Contrastive Learning, and Attribution-based Confidence Metrics

The primary objective of this project is to strengthen the trustworthiness of AI systems by designing algorithms that make their internal decision-making processes more understandable to human users. This involves creating clear, interpretable explanations for AI decisions and developing metrics to assess these explanations' validity and reliability. Significant progress has been achieved through (i) developing symbolic explanations, (ii) generating meaningful interpretive insights, (iii) establishing accuracy and confidence metrics, and (iv) devising methods to evaluate the knowledge boundaries of AI models. To date, the research findings have been shared in peer-reviewed publications, with accompanying scientific and technical information (STI) detailed below.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2025

Data about data – when, why and how metadata can support the digital plant

A structured approach for recording data quality and contextual information about how and why a signal exists – i.e. metadata – is central to interpret and use sensor data correctly. This is becoming increasingly important with the global trend with data-driven applications such as digital twins and AI-models. But a structured metadata collection and organization of sensor data is not routine in most plants, which can result in lost information and missed opportunities to make use of the investments made in the data collection. Therefore, the IWA task group on Metadata Collection and Organization in wastewater resource recovery systems (MetaCO) was initiated in 2020 and recently delivered the IWA scientific and technical report number 31. The report gives and in-depth description about metadata in water resources recovery facilities (WRRFs) and is available as open access at IWA publishing. The report is the outcome of the collaboration between more than 80 water professionals with the intention to serve WRRF data users with a guide on how to structure and make use of metadata throughout the data pipeline in order to maximize the value of sensor data.

Alferes, Janelcy [VITO, Belgium]↗

DOE OSTI2026

Are the U.S. Biorefineries Over the Hurdle of 2000 Ton Daily Throughput Yet?

The efficient utilization of lignocellulosic biomass for biofuel and biochemical production is hindered by material handling issues such as clogging and segregation among other challenges. Preprocessing methods such as drying, screening, and milling have improved conversion yield but have not sufficiently enhanced flowability, especially herbaceous biomass. The poor flowability of herbaceous biomass is rooted in some particle attributes that remain less altered by those methods, e.g., irregular particle shape, high roughness, and high compressibility, making it hard to scale up throughput to a key benchmark for a biorefinery – 2000 ton per day. Applying additional preprocessing methods like pelletization and torrefaction to drastically change those particle attributes can improve flow and handling but has not been comprehensively verified through test. The flowability of herbaceous biomass feedstock formats generated by three different preprocessing methods was recently assessed at Idaho National Laboratory’s Biomass Feedstock National User Facility: first, loose particles size reduced from as-received materials; second, pellets produced from an efficient densification process; and third, powders milled from torrefied pellets. Benchmarking tests including static angle of repose, basic flow energy measured in a powder rheometer, and discharge flow in an adjustable hopper, were conducted to evaluate those feedstock formats. Beyond the capacity of existing experimental apparatuses, a digital engineering approach involving flow simulations and AI models were used to identity the material attributes and processing parameters that have dominant influences on flow throughput. Techno-economic analysis focusing on hopper flow as a typical material handling operation was conducted for those feedstock formats. Perspectives will be discussed on whether the 2000-ton daily throughput for a biorefinery is achievable at an acceptable cost by using any of the tested preprocessing methods.

09 - BIOMASS FUELS↗

DOE OSTI2024

Toward a Holistic Performance Evaluation of Large Language Models Across Diverse AI Accelerators

Artificial intelligence (AI) methods have become critical in scientific applications to help accelerate scientific discovery. Large language models (LLMs) are being considered a promising approach to address some challenging problems because of their superior generalization capabilities across domains. The effectiveness of the models and the accuracy of the applications are contingent upon their efficient execution on the underlying hardware infrastructure. Specialized Al accelerator hardware systems have recently become available for accelerating Al applications. However, the comparative performance of these AI accelerators on large language models has not been previously studied. In this paper, we systematically study LLMs on multiple AI accelerators and GPUs and evaluate their performance characteristics for these models. We evaluate these systems with (i) a micro-benchmark using a core transformer block, (ii) a GPT-2 model, and (iii) an 1,I,M-driven science use case, GenSLM. We present our findings and analyses of the models' performance to better understand the intrinsic capabilities of AI accelerators. Furthermore, our analysis takes into account key factors such as sequence lengths, scaling behavior, and sensitivity to gradient accumulation steps.

Emani, Murali↗

DOE OSTI2021

Rethink hydrologic modeling framework with AI integrating multi-processes across scales

The proposed work is to develop a new hydrologic modeling framework that leverages vast amount earth and human system observational data, AI technologies, and data-driven information flows to improve predictability of hydrologic system that involves hydrologic, terrestrial, and biogeochemical processes and their interactions with the human and atmosphere systems.

54 ENVIRONMENTAL SCIENCES↗

DOE OSTI2025

Empirically-calibrated H100 node power models for accurate AI training energy estimation

Accurately quantifying the energy use of artificial intelligence (AI) training is critical for infrastructure planning, carbon accounting, and sustainable data center operation, but few studies have directly measured the power consumption of production workloads on contemporary hardware. By combining empirical measurements from Brookhaven National Laboratory during AI training on 8-graphics-processing-unit H100 systems with open-source benchmarking data, we develop statistical models relating computational intensity to node-level power consumption. We measure the gap between manufacturer-rated thermal design power (TDP) and actual power demand during AI training. Our analysis reveals that even computationally intensive workloads operate at only 76% of the 10.2 kW TDP rating. Our architecture-specific model, calibrated to floating-point operations, predicts energy consumption with 11.4% mean absolute percentage error, significantly outperforming TDP-based approaches (27%–37% error). We identified distinct power signatures between transformer and convolutional neural network architectures, with transformers showing characteristic fluctuations that may impact grid stability. These results provide a measurement-grounded basis for improving AI training energy estimates, enabling more reliable infrastructure sizing, cost projections, and environmental impact assessments.

Newkirk, Alex C↗

DOE OSTI2024

Understanding Generative AI Content with Embedding Models

The construction of high-quality numerical features is critical to any quantitative data analysis. Feature engineering has been historically addressed by carefully hand-crafting data representations based on domain expertise. This work views the internal representations of modern deep neural networks (DNNs), called embeddings, as an implicit form of traditional feature engineering. For trained DNNs, we show that these embeddings can reveal interpretable, high-level concepts in unstructured sample data. We use these embeddings in natural language and computer vision tasks to uncover both inherent heterogeneity in the underlying data and human-understandable explanations for it. In particular, we find empirical evidence that there is inherent separability between real data and those generated from AI models.

Vargas, Max↗

DOE OSTI2025

AI-powered topic modeling: comparing LDA and BERTopic in analyzing opioid-related cardiovascular risks in women

Topic modeling is a crucial technique in natural language processing (NLP), enabling the extraction of latent themes from large text corpora. Traditional topic modeling, such as Latent Dirichlet Allocation (LDA), faces limitations in capturing the semantic relationships in the text document although it has been widely applied in text mining. BERTopic, created in 2022, leveraged advances in deep learning and can capture the contextual relationships between words. In this work, we integrated Artificial Intelligence (AI) modules to LDA and BERTopic and provided a comprehensive comparison on the analysis of prescription opioid-related cardiovascular risks in women. Opioid use can increase the risk of cardiovascular problems in women such as arrhythmia, hypotension etc. 1,837 abstracts were retrieved and downloaded from PubMed as of April 2024 using three Medical Subject Headings (MeSH) words: “opioid,” “cardiovascular,” and “women.” Machine Learning of Language Toolkit (MALLET) was employed for the implementation of LDA. BioBERT was used for document embedding in BERTopic. Eighteen was selected as the optimal topic number for MALLET and 23 for BERTopic. ChatGPT-4-Turbo was integrated to interpret and compare the results. The short descriptions created by ChatGPT for each topic from LDA and BERTopic were highly correlated, and the performance accuracies of LDA and BERTopic were similar as determined by expert manual reviews of the abstracts grouped by their predominant topics. The results of the t-SNE (t-distributed Stochastic Neighbor Embedding) plots showed that the clusters created from BERTopic were more compact and well-separated, representing improved coherence and distinctiveness between the topics. Our findings indicated that AI algorithms could augment both traditional and contemporary topic modeling techniques. In addition, BERTopic has the connection port for ChatGPT-4-Turbo or other large language models in its algorithm for automatic interpretation, while with LDA interpretation must be manually, and needs special procedures for data pre-processing and stop words exclusion. Therefore, while LDA remains valuable for large-scale text analysis with resource constraints, AI-assisted BERTopic offers significant advantages in providing the enhanced interpretability and the improved semantic coherence for extracting valuable insights from textual data.

Research & Experimental Medicine↗

DOE OSTI2021

Rapid assimilation and analysis of a suit of remote sensing data for predicting extreme events and their impact on ecological-human systems

Insight gleaned from complex data using AI, and other advanced methods, including explainable AI and physics- or knowledge-guided AI. Predictive modeling through the use of AI techniques and AI-derived model components; the use of AI and other tools to design a prediction system comprising of a hierarchy of models.

54 ENVIRONMENTAL SCIENCES↗

DOE OSTI2021

AI-Based Integrated Modeling and Observational Framework for Improving Seasonal to Decadal Prediction of Terrestrial Ecohydrological Extremes

Focal Areas: (1) Insight gleaned from complex data (both observed and simulated) using artificial intelligence(AI), big data analytics, and other advanced methods, including explainable AI and physics- or knowledge-guided AI (2) Data acquisition and assimilation enabled by machine learning, AI, and advanced methods including experimental/network design/optimization, unsupervised learning (including deep learning), and hardware-related efforts involving AI (e.g., edge computing).

54 ENVIRONMENTAL SCIENCES↗

DOE OSTI2021

AI-Batt (Autonomous Identification of Battery Life Models) [SWR 21-36]

Autonomous Identification of Battery Life Models (AI-Batt) AI-Batt is a MATLAB code base for developing lifetime models for batteries from accelerated aging data. The code base provides many functions for processing, visualizing, and modeling battery aging data, making the data processing, exploration, and modeling workflow substantially faster. These tools are tailored for working with battery aging data sets, which usually consist of many separate time-series for each cell, with many test conditions and possible replicates at each condition, which makes it difficult to simply process or visualize the data set. Complex modeling tasks, such as cross-validation, sensitivity analysis, and uncertainty quantification have been implemented to enable thorough statistical investigation of model predictions. Additionally, several machine-learning algorithms are implemented to autonomously identify suitable models via symbolic regression. Data processing functions automatically cast data from the struct data type, which is commonly used to store experimental data, but is not an acceptable input for most algorithms, to the table data type, which can be easily used as input to any optimization algorithm. Also, the data can be separated into time-invariant and time-variant data tables, which is helpful for exploring the data set as well as developing separate models for time-variant and time-invariant aging mechanisms. For example, in aging tests with constant temperature, temperature is a time-invariant experimental condition. Visualization tools enable plotting of data, model fits, and model simulations possible with single-line function calls, empowering data exploration of complex data sets with both time-varying and time-invariant trends. Plots can be automatically generated for the whole data set, or separated by data group (groups of test replicates) or individual data series. Data points or data series can be automatically colored by the value of a variable with a variety of color maps, and model predictions can also be colored by the value of a fit statistic. Comparisons between data sets and the predictions/simulations of different models on the same data set can be easily plotted as well. Distributions of parameter values from bootstrap resampling can be plotted to visualize the reliability of parameter estimation, or determine any correlations between parameters. Modeling tools handle the complex task of creating and parsing symbolic equations for modeling battery lifetime. Equations are parsed to grab relevant data variables, parameter values, or specified sub-models for input into optimization, evaluation, or simulation functions. Models can be optimized locally (one set of parameters for each data series), bi-level (some parameters shared across the data set), or globally (single set of parameters for all data). Functions implementing symbolic regression algorithms help users to discover effective model equations, even in poorly sampled, high-dimensional data.

Smith, Kandler↗