Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “Responsible AI”

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 127 records · Page 7

Harnessing large language models’ zero-shot and few-shot learning capabilities for regulatory research

Abstract Large language models (LLMs) are sophisticated AI-driven models trained on vast sources of natural language data. They are adept at generating responses that closely mimic human conversational patterns. One of the most notable examples is OpenAI's ChatGPT, which has been extensively used across diverse sectors. Despite their flexibility, a significant challenge arises as most users must transmit their data to the servers of companies operating these models. Utilizing ChatGPT or similar models online may inadvertently expose sensitive information to the risk of data breaches. Therefore, implementing LLMs that are open source and smaller in scale within a secure local network becomes a crucial step for organizations where ensuring data privacy and protection has the highest priority, such as regulatory agencies. As a feasibility evaluation, we implemented a series of open-source LLMs within a regulatory agency’s local network and assessed their performance on specific tasks involving extracting relevant clinical pharmacology information from regulatory drug labels. Our research shows that some models work well in the context of few- or zero-shot learning, achieving performance comparable, or even better than, neural network models that needed thousands of training samples. One of the models was selected to address a real-world issue of finding intrinsic factors that affect drugs' clinical exposure without any training or fine-tuning. In a dataset of over 700 000 sentences, the model showed a 78.5% accuracy rate. Our work pointed to the possibility of implementing open-source LLMs within a secure local network and using these models to perform various natural language processing tasks when large numbers of training examples are unavailable.

Biochemistry & Molecular Biology↗

GIScience in the era of Artificial Intelligence: a research agenda towards Autonomous GIS

The advent of generative AI exemplified by large language models (LLMs) opens new ways to represent and compute geographic information and transcends the process of geographic knowledge production, driving geographic information systems (GIS) towards autonomous GIS. Leveraging LLMs as the decision core, autonomous GIS can independently generate and execute geoprocessing workflows to perform spatial analysis. In this vision paper, we further elaborate on the concept of autonomous GIS and present a conceptual framework that defines its five autonomous goals, five levels of autonomy, five core functions, and three operational scales. We demonstrate how autonomous GIS could perform geospatial data retrieval, spatial analysis, and map making with four proof-of-concept GIS agents. We conclude by identifying critical challenges and future research directions, including fine-tuning and self-growing decision-cores, autonomous modelling, and examining the societal and practical implications of autonomous GIS. By establishing the groundwork for a paradigm shift in GIScience, this paper envisions a future where GIS moves beyond traditional workflows to autonomously reason, derive, innovate, and advance geospatial solutions to pressing global challenges. Meanwhile, we emphasize that as we design and deploy increasingly intelligent geospatial systems, we carry a responsibility to ensure they are developed in socially responsible ways, serve the public good, and support the continued value of human geographic insight in an AI-augmented future.

Autonomous GI↗

Correlating structural changes in thermoresponsive hydrogels to the optical response of embedded plasmonic nanoparticles

Stimuli-responsive microgels, composed of small beads with soft, deformable polymer networks swollen through a combination of synthetic control over the polymer and its interaction with water, form a versatile platform for development of multifunctional and biocompatible sensors. The interfacial structural variation of such materials at a nanometer length scale is essential to their function, but not yet fully comprehended. Here, we take advantage of the plasmonic response of a gold nanorod embedded in a thermoresponsive microgel (AuNR@PNIPMAm) to monitor structural changes in the hydrogel directly near the nanorod surface. By direct comparison of the plasmon response against measurements of the hydrogel structure from dynamic light scattering and nuclear magnetic resonance, we find that the microgel shell of batch-polymerized AuNR@PNIPMAm exhibits a heterogeneous volume phase transition reflected by different onset temperatures for changes in the hydrodyanmic radius (R H ) and plasmon resonance, respectively. The new approach of contrasting plasmonic response (a measure of local surface hydrogel structure) with R H and relaxation times paves a new path to gain valuable insight for the design of plasmonic sensors based on stimuli-responsive hydrogels.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

AICCA: AI-Driven Cloud Classification Atlas

Clouds play an important role in the Earth’s energy budget, and their behavior is one of the largest uncertainties in future climate projections. Satellite observations should help in understanding cloud responses, but decades and petabytes of multispectral cloud imagery have to date received only limited use. This study describes a new analysis approach that reduces the dimensionality of satellite cloud observations by grouping them via a novel automated, unsupervised cloud classification technique based on a convolutional autoencoder, an artificial intelligence (AI) method good at identifying patterns in spatial data. Our technique combines a rotation-invariant autoencoder and hierarchical agglomerative clustering to generate cloud clusters that capture meaningful distinctions among cloud textures, using only raw multispectral imagery as input. Cloud classes are therefore defined based on spectral properties and spatial textures without reliance on location, time/season, derived physical properties, or pre-designated class definitions. We use this approach to generate a unique new cloud dataset, the AI-driven cloud classification atlas (AICCA), which clusters 22 years of ocean images from the Moderate Resolution Imaging Spectroradiometer (MODIS) on NASA’s Aqua and Terra instruments—198 million patches, each roughly 100 km × 100 km (128 × 128 pixels)—into 42 AI-generated cloud classes, a number determined via a newly-developed stability protocol that we use to maximize richness of information while ensuring stable groupings of patches. AICCA thereby translates 801 TB of satellite images into 54.2 GB of class labels and cloud top and optical properties, a reduction by a factor of 15,000. The 42 AICCA classes produce meaningful spatio-temporal and physical distinctions and capture a greater variety of cloud types than do the nine International Satellite Cloud Climatology Project (ISCCP) categories—for example, multiple textures in the stratocumulus decks along the West coasts of North and South America. We conclude that our methodology has explanatory power, capturing regionally unique cloud classes and providing rich but tractable information for global analysis. AICCA delivers the information from multi-spectral images in a compact form, enables data-driven diagnosis of patterns of cloud organization, provides insight into cloud evolution on timescales of hours to decades, and helps democratize climate research by facilitating access to core data.

97 MATHEMATICS AND COMPUTING↗

Physics Coupled Machine Learning Applications for Geological Carbon Storage

Poster presented at the 17th International Conference on Greenhouse Gas Control Technologies GHGT-17 held in Calgary, Canada, October 20-24, 2024. In this poster, a physics-based method, CRM is coupled with the advanced artificial intelligence (AI)/machine learning (ML) models in virtual learning environment (VLE) for three-dimension details of reservoir responses and evaluations for a comprehensive understanding for CCS field operations and reservoir managements.

Liu, Guoxiang↗

Physics Coupled Machine Learning Applications for Geological Carbon Storage

This is the conference paper accompanying a poster presentation at the 17th International Conference on Greenhouse Gas Control Technologies GHGT-17 held in Calgary, Canada, October 20-24, 2024. In this paper, a physics-based method, CRM is coupled with the advanced artificial intelligence (AI)/machine learning (ML) models in virtual learning environment (VLE) for three-dimension details of reservoir responses and evaluations for a comprehensive understanding for CCS field operations and reservoir managements.

Liu, Guoxiang↗

Safety in Artificial Intelligence: Challenges and Opportunities for the U.S. National Labs and Beyond

This report discusses the importance of the critical and underexplored topic of artificial intelligence (AI) safety, as highlighted during the “Strategy Alignment on AI Safety” workshop convened at Lawrence Livermore National Laboratory (LLNL) in April 2024. Through a summary of keynote talks, panel discussions, and breakout sessions, world-leading AI safety experts from academic, industry, national labs, and government agencies clearly agree on the need for and importance of large-scale investments for research and capabilities in AI safety. With the field innovating at unprecedented rates, there is increasing urgency to develop novel evaluation methodologies that allow full considerations of risks/threats of AI technologies in different domains. Quantitative metrics and effective methodologies that can evaluate and audit the “safeness” of how a given AI technology is trained, deployed, or regulated are, at best, nascent for certain scenarios or, more commonly, nonexistent. This maturation gap presents the possibility of serious threats to national security, and further inaction may have serious consequences. Additionally, the gap between the public’s and research community’s perceptions of AI risks/rewards is significant. While numerous voices from the AI community have expressed concern that the risks could be so high that future AI systems could inflict extinction-level damage to humanity if deployed incorrectly, the public largely is aware only of risk in low-impact scenarios. This discrepancy highlights the crucial need for researchers to articulate to governmental bodies what, why, and when various AI risks matter as part of motivating funding requests. Thus, the call to action for this community is to pursue AI safety as a “Big Science” project on a scale comparable to the Manhattan Project. High risks and high payoffs are on the table, but safe AI is a fast-moving target, and large-scale investments are needed to guide development of this technology in a responsible way. We highlight the need for a multilayered solution combining the development of new methods and algorithmic approaches to mitigate threats with an active participation of the government(s) in setting high industry standards and regulations based on state-of-the-art technology. The U.S. Department of Energy (DOE) national laboratories have served as leading institutions for scientific innovation in the U.S. for more than 70 years. Drawing on their expertise in the AI community and their history of safeguarding critical and sensitive information, and as we look to the future, national labs are the best choice for evaluating and safeguarding AI technologies.

97 MATHEMATICS AND COMPUTING↗

Intelligent resolution: Integrating Cryo-EM with AI-driven multi-resolution simulations to observe the severe acute respiratory syndrome coronavirus-2 replication-transcription machinery in action

The severe acute respiratory syndrome coronavirus-2 (SARS-CoV-2) replication transcription complex (RTC) is a multi-domain protein responsible for replicating and transcribing the viral mRNA inside a human cell. Attacking RTC function with pharmaceutical compounds is a pathway to treating COVID-19. Conventional tools, e.g., cryo-electron microscopy and all-atom molecular dynamics (AAMD), do not provide sufficiently high resolution or timescale to capture important dynamics of this molecular machine. Consequently, we develop an innovative workflow that bridges the gap between these resolutions, using mesoscale fluctuating finite element analysis (FFEA) continuum simulations and a hierarchy of AI-methods that continually learn and infer features for maintaining consistency between AAMD and FFEA simulations. We leverage a multi-site distributed workflow manager to orchestrate AI, FFEA, and AAMD jobs, providing optimal resource utilization across HPC centers. Our study provides unprecedented access to study the SARS-CoV-2 RTC machinery, while providing general capability for AI-enabled multi-resolution simulations at scale.

Trifan, Anda↗

The ovarian DNA damage repair response is induced prior to phosphoramide mustard-induced follicle depletion, and ataxia telangiectasia mutated inhibition prevents PM-induced follicle depletion

Phosphoramide mustard (PM) is an ovotoxic metabolite of cyclophosphamide and destroys primordial and primary follicles potentially by DNA damage induction. The temporal pattern by which PM induces DNA damage and initiation of the ovarian response to DNA damage has not yet been well characterized. This study investigated DNA damage initiation, the DNA repair response, as well as induction of follicular demise using a neonatal rat ovarian culture system. Additionally, to delineate specific mechanisms involved in the ovarian response to PM exposure, utility was made of PKC delta (PKCδ) deficient mice as well as an ATM inhibitor (KU 55933; AI). Fisher 344 PND4 rat ovaries were cultured for 12, 24, 48 or 96 h in medium containing DMSO ± 60 μM PM or KU 55933 (48 h; 10 nM). PM-induced activation of DNA damage repair genes was observed as early as 12 h post-exposure. ATM, PARP1, E2F7, P73 and CASP3 abundance were increased but RAD51 and BCL2 protein decreased after 96 h of PM exposure. PKCδ deficiency reduced numbers of all follicular stages, but did not have an additive impact on PM-induced ovotoxicity. ATM inhibition protected all follicle stages from PM-induced depletion. In conclusion, the ovarian DNA damage repair response is active post-PM exposure, supporting that DNA damage contributes to PM-induced ovotoxicity. - Highlights: • PM exposure induces DNA damage repair gene expression. • Inhibition of ATM prevented PM-induced follicle depletion. • PKCδ deficiency did not impact PM-induced ovotoxicity.

60 APPLIED LIFE SCIENCES↗

Nondestructive In Operando Imaging of Thin Film Composite Membrane Compaction Enhanced by AI-Based Segmentation

Reverse osmosis (RO) membranes are essential for desalination and water reuse, yet their permeability declines in high-pressure applications due to membrane compaction. This study investigates the structural and functional responses of commercial brackish, seawater, and high-pressure RO membranes at applied pressures up to 120 bar using a multiscale, nondestructive in operando scanning electron microscopy (iSEM) imaging platform. The iSEM technique reveals progressive densification across the composite membrane structure, which correlates with observed declines in water and solute permeance. To quantify these structural changes with greater fidelity, we combined X-ray computed tomography with AI-based segmentation enabling precise analysis of pore size distribution and thickness of the polysulfone support layer. Compared to traditional thresholding, AI segmentation accurately delineates material phases and void spaces, enhancing the reproducibility and resolution of morphological assessments. The results demonstrate that compaction-induced reductions in porosity and thickness strongly impact membrane transport properties. These findings provide mechanistic insights into the compaction behavior of RO membranes and underscore the potential for advanced imaging and AI-driven data analysis to guide the design of next-generation membranes with improved mechanical resilience and operational longevity.

13 HYDRO ENERGY↗

Machine Intelligence-Centered System for Automated Characterization of Functional Materials and Interfaces

Classic design of experiment relies on a time-intensive workflow that requires planning, data interpretation, and hypothesis building by experienced researchers. Here, in this paper, we describe an integrated, machine-intelligent experimental system which enables simultaneous dynamic tests of electrical, optical, gravimetric, and viscoelastic properties of materials under a programmable dynamic environment. Specially designed software controls the experiment and performs on-the-fly extensive data analysis and dynamic modeling, real-time iterative feedback for dynamic control of experimental conditions, and rapid visualization of experimental results. The system operates with minimal human intervention and enables time-efficient characterization of complex dynamic multifunctional environmental responses of materials with simultaneous data processing and analytics. The system provides a viable platform for artificial intelligence (AI)-centered material characterization, which, when coupled with an AI-controlled synthesis system, could lead to accelerated discovery of multifunctional materials.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

Effectiveness of denoising diffusion probabilistic models for fast and high-fidelity whole-event simulation in high-energy heavy-ion experiments

Artificial intelligence (AI) generative models, such as generative adversarial networks (GANs), variational autoencoders, and normalizing flows, have been widely used and studied as efficient alternatives for traditional scientific simulations. However, they have several drawbacks, including training instability and inability to cover the entire data distribution, especially for regions where data are rare. This is particularly challenging for whole-event, full-detector simulations in high-energy heavy-ion experiments, such as sPHENIX at the Relativistic Heavy Ion Collider and Large Hadron Collider experiments, where thousands of particles are produced per event and interact with the detector. This work investigates the effectiveness of denoising diffusion probabilistic models (DDPMs) as an AI-based generative surrogate model for the sPHENIX experiment that includes the heavy-ion event generation and response of the entire calorimeter stack. DDPM performance in sPHENIX simulation data is compared with a popular rival, GANs. Results show that both DDPMs and GANs can reproduce the data distribution where the examples are abundant (low-to-medium calorimeter energies). Nonetheless, DDPMs significantly outperform GANs, especially in high-energy regions where data are rare. Additionally, DDPMs exhibit superior stability compared to GANs. The results are consistent between both central and peripheral centrality heavy-ion collision events. Moreover, DDPMs offer a substantial speedup of approximately a factor of 100 compared to the traditional Geant4 simulation method.

42 ENGINEERING↗

A situated reasoning architecture for space-based repair and replace tasks

Space-based robots need low level control for collision detection and avoidance, short-term load management, fine-grained motion, and other physical tasks. In addition, higher level control is required to focus strategic decision making as missions are assigned and carried out. Reasoning and control must be responsive to ongoing changes in the environment. Research aimed at bridging the gap between high level artificial intelligence (AI) planning techniques and task-level robot programming for telerobotic systems is described. Situated reasoning is incorporated into AI and Robotics systems in order to coordinate a robot's activity within its environment. An integrated system under development in a component maintenance domain is described. It is geared towards replacing worn and/or failed Orbital Replacement Units (ORUs) designed for use aboard NASA's Space Station Freedom based on the collection of components available at a given time. High level control reasons in component space in order to maximize the number operational component-cells over time, while the task-level controls sensors and effectors, detects collisions, and carries out pick and place tasks in physical space. Situated reasoning is used throughout the system to cope with component failures, imperfect information, and unexpected events.

Bloom, Ben↗

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↗

An AI-accelerated pathway for reproducible and stable halide perovskites

Halide perovskites (HPs) have remarkable optoelectronic properties, and in the last decade their photovoltaic power conversion efficiency and light-emitting diode efficiency have skyrocketed. Despite the surge in research on these burgeoning materials, two key challenges in the field remain: material irreproducibility and instability. Their behavior is especially dynamic in response to environmental stressors, due to complex interactions with the perovskite crystal lattice. Here, in this review, we survey the latest achievements in HP materials research accomplished with the assistance of artificial intelligence (AI), through the implementation of automated experimentation and machine learning (ML) data analysis. Automated synthesis and characterization tackle problems with material irreproducibility by systematically controlling parameters with very high precision, creating massive datasets, and allowing methodical comparisons from which unbiased conclusions can be drawn. AI can reveal otherwise unnoticed trends, inform future experiments with the highest potential information gain, and forecast future performance. The review concludes with a forward viewpoint of how human-assisted closed-loop laboratories and shared databases allow halide perovskite materials’ processing, properties, and performance to be potentially optimized with AI, accelerating the development of highly reproducible and stable optoelectronic devices.

Hering, Abigail R. [Univ. of California, Davis, CA↗

Short latency vestibular evoked potentials in the Japanese quail (Coturnix coturnix japonica)

Short-latency vestibular-evoked potentials to pulsed linear acceleration were characterized in the quail. Responses occurred within 8 ms following the onset of stimuli and were composed of a series of positive and negative peaks. The latencies and amplitudes of the first four peaks were quantitatively characterized. Mean latencies at 1.0 g ms-1 ranged from 1265 +/- 208 microseconds (P1, N = 18) to 4802 +/- 441 microseconds (N4, N = 13). Amplitudes ranged from 3.72 +/- 1.51 microV (P1/N1, N = 18) to 1.49 +/- 0.77 microV (P3/N3, N = 16). Latency-intensity (LI) slopes ranged from -38.7 +/- 7.3 microseconds dB-1 (P1, N = 18) to -71.6 +/- 21.9 microseconds dB-1 (N3, N = 15) and amplitude-intensity (AI) slopes ranged from 0.20 +/- 0.08 microV dB-1 (P1/N1, N = 18) to 0.07 +/- 0.04 microV dB-1 (P3/N3, N = 11). The mean response threshold across all animals was -21.83 +/- 3.34 dB re: 1.0 g ms-1 (N = 18). Responses remained after cochlear extirpation showing that they could not depend critically on cochlear activity. Responses were eliminated by destruction of the vestibular end organs, thus showing that responses depended critically and specifically on the vestibular system. The results demonstrate that the responses are vestibular and the findings provide a scientific basis for using vestibular responses to evaluate vestibular function through ontogeny and senescence in the quail.

NASA Discipline Neuroscience↗

Combining artificial intelligence, Earth observations, and climate models to improve predictability of ice-biogeochemistry interactions

Focal Area: Predictive Modeling. We describe how artificial intelligence (AI) can be combined with state-of-the-science Earth system models to better predict future regional climate responses. To demonstrate, we describe a case study in biogeochemical interactions with sea ice. Science Challenge: Biogeochemical models are poorly constrained for high latitude systems. Machine learning methods and edge computing can be combined with Earth system models, such as the Energy Exascale Earth System Model (E3SM), to gain insight into ice-biogeochemical interactions and improve sea ice extent prediction.

54 ENVIRONMENTAL SCIENCES↗