Results for “AI Challenges” — Page 19

NASA NTRS2022

Sustainable Aviation Operations and the Role of Information Technology and Data Science: Background, Current Status and Future Directions

This paper reviews the achievements of the international community towards environmentally friendly aviation operations, also referred to as Sustainable Aviation Operations in the last 25 years and the aspirations and goals to limit the impact of aviation and climate in the future. The framework for achieving global progress is provided by the International Civil Aviation Organization. NASA and FAA supported research and development to advance ATM concepts, and implemented the technology, concepts, and procedures that were responsible for creating fuel efficient flights. Historically aviation operations have been analyzed using physics-based models and provide information for making operational decisions. Future developments in aviation operations require new concepts, procedure, modeling, and analysis techniques. There is an increasing interest in applying methods based on Machine Learning Techniques to problems in Air Traffic Management. Aviation operations involving many decision makers, multiple objectives, poor or unavailable physics-based models and the availability of a rich historical database provide opportunities to exploit the richness of data-driven methods. The promises and challenges in applying Machine Learning Techniques to Air Traffic Management are discussed in the paper along with the testing and trustworthiness required for adoption of the techniques in operations.

Sustainable Aviation, Data Science, Machine Learni↗

NASA NTRS2022

Sustainable Aviation Operations and the Role of Information Technology and Data Science: Background, Current Status and Future Directions

This paper reviews the achievements of the international community towards environmentally friendly aviation operations, also referred to as Sustainable Aviation Operations in the last 25 years and the aspirations and goals to limit the impact of aviation and climate in the future. The framework for achieving global progress is provided by the International Civil Aviation Organization. NASA and FAA supported research and development to advance ATM concepts, and implemented the technology, concepts, and procedures that were responsible for creating fuel efficient flights. Historically aviation operations have been analyzed using physics-based models and provide information for making operational decisions. Future developments in aviation operations require new concepts, procedure, modeling, and analysis techniques. There is an increasing interest in applying methods based on Machine Learning Techniques to problems in Air Traffic Management. Aviation operations involving many decision makers, multiple objectives, poor or unavailable physics-based models and the availability of a rich historical database provide opportunities to exploit the richness of data-driven methods. The promises and challenges in applying Machine Learning Techniques to Air Traffic Management are discussed in the paper along with the testing and trustworthiness required for adoption of the techniques in operations.

Sustainable Aviation, Data Science, Machine Learni↗

NASA NTRS2011

Commercially Hosted Government Payloads: Lessons from Recent Programs

In a commercially hosted operational mode, a scientific instrument or operational device is attached to a spacecraft but operates independently from the spacecraft s primary mission. Despite the expected benefits of this arrangement, there are few examples of hosted payload programs actually being executed by government organizations. The lack of hosted payload programs is largely driven by programmatic challenges, both real and perceived, rather than by technical challenges. Partly for these reasons, NASA has not sponsored a hosted payload program, in spite of the benefits and visible community interest in doing so. In the interest of increasing the use of hosted payloads across the space community, this paper seeks to alleviate concerns about hosted payloads by identifying these programmatic challenges and presenting ways in which they can be avoided or mitigated. Despite the challenges, several recent hosted payload programs have been successfully completed or are currently in progress. This paper presents an assessment of these programs, with a focus on acquisition, costs, schedules, risks, and other programmatic aspects. The hosted payloads included in this study are the Federal Aviation Administration's Wide Area Augmentation System (WAAS) payloads, United States Coast Guard's Automatic Identification System (AIS) demonstration payload, Department of Defense's IP Router In Space (IRIS) demonstration payload, the United States Air Force's Commercially Hosted Infrared Payload (CHIRP), and the Australian Defence Force's Ultra High Frequency (UHF) payload. General descriptions of each of these programs are presented along with issues that have been encountered and lessons learned from those experiences. A set of recommended approaches for future hosted payload programs is presented, with a focus on addressing risks or potential problem areas through smart and flexible contracting up front. This set of lessons and recommendations is broadly applicable to future hosted payload programs, whether they are technology demonstrations, communications systems, or operational sensors. Additionally, we present a basic cost model for commercial access to space for hosted payloads as a function of payload mass

Andraschko, Mark A.↗

DOE OSTI2024

TEAMER - Field Demonstration of MarineSitu’s Marine Energy Monitoring Tools - CRADA 664 (Abstract)

In order to effectively monitor for marine life around marine energy devices and thus minimize the risk of collision, multiple sensors working in coordination and augmented with around-the-clock automated monitoring algorithms need to be installed in challenging high-energy tidal and wave environments. Such systems are often too expensive for widespread adoption, or lack sufficient sensors or smarts to enable around-the-clock, real-time monitoring without human involvement. MarineSitu has been working to tackle this problem by developing a low-cost, combined sonar and stereo camera sensor array with connected real-time AI-based algorithms for automatically detecting marine life in these marine energy suitable environments. In this TEAMER project with Pacific Northwest National Lab (PNNL), MarineSitu will be testing this novel sensor system for the first time in the high-energy tidal channel environment at PNNL’s Marine and Coastal Research Lab. Throughout this deployment, MarineSitu will be monitoring their system and running analytics on the sensor’s data in real-time. Meanwhile, PNNL Data Scientists and Ocean Engineers, will be evaluating the system’s effectiveness and ease of use both as a tool for plug-and-play environmental monitoring and novel environmental monitoring research. In doing so, the team will improve MarineSitu’s system and software, produce insightful data products, and develop novel visualizations and AI algorithms for combining and analyzing the data produced by systems like MarineSitu’s.

16 TIDAL AND WAVE POWER↗

DOE OSTI2025

TEAMER – Field Demonstration of MarineSitu’s Marine Energy Monitoring (Abstract)

In order to effectively monitor for marine life around marine energy devices and thus minimize the risk of collision, multiple sensors working in coordination and augmented with around-the-clock automated monitoring algorithms need to be installed in challenging high-energy tidal and wave environments. Such systems are often too expensive for widespread adoption, or lack sufficient sensors or smarts to enable around-the-clock, real-time monitoring without human involvement. MarineSitu has been working to tackle this problem by developing a low-cost, combined sonar and stereo camera sensor array with connected real-time AI-based algorithms for automatically detecting marine life in these marine energy suitable environments. In this TEAMER project with Pacific Northwest National Lab (PNNL), MarineSitu will be testing this novel sensor system for the first time in the high-energy tidal channel environment at PNNL’s Marine and Coastal Research Lab. Throughout this deployment, MarineSitu will be monitoring their system and running analytics on the sensor’s data in real-time. Meanwhile, PNNL Data Scientists and Ocean Engineers, will be evaluating the system’s effectiveness and ease of use both as a tool for plug-and-play environmental monitoring and novel environmental monitoring research. In doing so, the team will improve MarineSitu’s system and software, produce insightful data products, and develop novel visualizations and AI algorithms for combining and analyzing the data produced by systems like MarineSitu’s.

16 TIDAL AND WAVE POWER↗

NASA NTRS2015

Certification Considerations for Adaptive Systems

Advanced capabilities planned for the next generation of aircraft, including those that will operate within the Next Generation Air Transportation System (NextGen), will necessarily include complex new algorithms and non-traditional software elements. These aircraft will likely incorporate adaptive control algorithms that will provide enhanced safety, autonomy, and robustness during adverse conditions. Unmanned aircraft will operate alongside manned aircraft in the National Airspace (NAS), with intelligent software performing the high-level decision-making functions normally performed by human pilots. Even human-piloted aircraft will necessarily include more autonomy. However, there are serious barriers to the deployment of new capabilities, especially for those based upon software including adaptive control (AC) and artificial intelligence (AI) algorithms. Current civil aviation certification processes are based on the idea that the correct behavior of a system must be completely specified and verified prior to operation. This report by Rockwell Collins and SIFT documents our comprehensive study of the state of the art in intelligent and adaptive algorithms for the civil aviation domain, categorizing the approaches used and identifying gaps and challenges associated with certification of each approach.

Bhattacharyya, Siddhartha↗

DOE OSTI2024

PCAST: Report to the President on Supercharging Research: Harnessing Artificial Intelligence to Meet Global Challenges

The President’s Council of Advisors on Science and Technology (PCAST) is the sole body of advisors from outside the federal government charged with making science, technology, and innovation policy recommendations to the President and the White House. Established by Executive Order, it is an independent Federal Advisory Committee comprised of distinguished individuals from industry, academia, and non-profit organizations with a range of perspectives and expertise. On April 29, 2024, PCAST sent a report to the President with recommendations to help the U.S. harness the full potential of AI to equitably and responsibly supercharge scientific discovery.

97 MATHEMATICS AND COMPUTING↗

NASA NTRSDate not supplied

From 3D Printing Lunar and Mars Habitats to Affordable Sustainable Housing on Earth

In 2015, the NASA Centennial Challenges program launched the 3D-Printed Habitat (3DPH) competition to develop housing solutions for extended-duration missions on planetary surfaces using advanced additive construction technology. The challenge was executed in three phases with increasing complexities and requirements. The main goal of the competition was to use of planetary indigenous materials and mission recyclables as feedstock for large-scale, autonomous 3D printers to construct a habitat on the Moon or Mars. Phase 1 challenged teams to develop state-of-the-art architecture concepts that took advantage of unique capabilities offered by 3D-printing. In Phase 2, teams autonomously 3D-printed structural components using terrestrial/space-based materials and recyclables. Phase 3 tasked competitors to fabricate sub-scale habitats using indigenous materials with or without mission-generated recyclables and ended in a head-to-head competition. The developments from this challenge are applicable both to the fulfillment of NASA’s Moon to Mars mission and to the creation of affordable and sustainable housing solutions on Earth. This paper will summarize the results of the four-year challenge and provide an overview of team achievements as a result of the competition. Results from the competition include humanitarian and business opportunities created/negotiated and the development of 3D-printed housing solutions for people such those in need of shelter in Austin, Texas and 3D-printing houses at the United Nations habitat headquarters in Nairobi, Keyna. The Phase 3: Level 5 winner, AI. SpaceFactory, is currently 3D-printing an ecofriendly house in New York called Terra, a full-size habitat design for Mars and available on Earth.

M C Roman↗

DOE OSTI2024

Workflow Provenance in the Computing Continuum for Responsible, Trustworthy, and Energy-Efficient AI

As Artificial Intelligence (AI) becomes more pervasive in our society, it is crucial to develop, deploy, and assess Responsible and Trustworthy AI (RTAI) models, i.e., those that consider not only accuracy but also other aspects, such as explainability, fairness, and energy efficiency. Workflow provenance data have historically enabled critical capabilities towards RTAI. Provenance data derivation paths contribute to responsible workflows through transparency in tracking artifacts and resource consumption. Provenance data are well-known for their trustworthiness helping explainability, reproducibility, and accountability. However, there are complex challenges to achieve RTAI, which are further complicated by the heterogeneous infrastructure in the computing continuum (Edge-Cloud-HPC) used to develop and deploy models. As a result, a significant research and development gap remains between workflow provenance data management and RTAI. In this paper, we present a vision of the pivotal role of workflow provenance in supporting RTAI and discuss related challenges. We present a schematic view between RTAI and provenance, and highlight open research directions.

Santos Souza, Renan↗

DOE OSTI2024

Artificial intelligence to unlock real-world evidence in clinical oncology: A primer on recent advances

Purpose: Real world evidence is crucial to understanding the diffusion of new oncologic therapies, monitoring cancer outcomes, and detecting unexpected toxicities. In practice, real world evidence is challenging to collect rapidly and comprehensively, often requiring expensive and time-consuming manual case-finding and annotation of clinical text. In this Review, we summarise recent developments in the use of artificial intelligence to collect and analyze real world evidence in oncology. Methods: We performed a narrative review of the major current trends and recent literature in artificial intelligence applications in oncology. Results: Artificial intelligence (AI) approaches are increasingly used to efficiently phenotype patients and tumors at large scale. These tools also may provide novel biological insights and improve risk prediction through multimodal integration of radiographic, pathological, and genomic datasets. Custom language processing pipelines and large language models hold great promise for clinical prediction and phenotyping. Conclusions: Despite rapid advances, continued progress in computation, generalizability, interpretability, and reliability as well as prospective validation are needed to integrate AI approaches into routine clinical care and real-time monitoring of novel therapies.

60 APPLIED LIFE SCIENCES↗

DOE OSTI2025

Decentralized Distributed Proximal Policy Optimization (DD-PPO) for High Performance Computing Scheduling on Multi-User Systems

Resource allocation in High Performance Computing (HPC) environments presents a complex and multifaceted challenge for job scheduling algorithms. Beyond the efficient allocation of system resources, schedulers must account for and optimize multiple performance metrics, including job wait time and system throughput. Traditional heuristic-based scheduling algorithms increasingly struggle and lack the efficiency needed to meet the demands and address the complexity and scale of modern HPC systems. Consequently, recent research efforts have focused on leveraging advancements in Artificial Intelligence (AI) and Deep Learning (DL), particularly Reinforcement Learning (RL), to develop more adaptable and intelligent scheduling strategies. Previous RL-based scheduling approaches have explored a range of algorithms, from Deep Q-Networks (DQN) to Proximal Policy Optimization (PPO), and more recently, hybrid methods that integrate Graph Neural Networks (GNNs) with RL techniques. However, a common limitation across these methods is their reliance on relatively small datasets, with few methods being evaluated using large-scale, multi-million-job trace datasets representative of real-world HPC workloads. Moreover, existing RL schedulers face scalability issues due to centralized policy updates, which hinder training efficiency and performance when applied to large datasets. This study introduces a novel RL-based scheduler utilizing Decentralized Distributed Proximal Policy Optimization (DD-PPO) algorithm, which supports large-scale distributed training across multiple workers without requiring parameter synchronization at every step. By eliminating reliance on centralized updates to a shared policy, the DD-PPO scheduler enhances scalability, training efficiency, and sample utilization. Experimental validation using a large real-world dataset containing over 11.5 million job traces collected from petascale HPC systems over six years assesses the influence of dataset scale on training effectiveness and compares DD-PPO performance to traditional and advanced scheduling approaches. The experimental results demonstrate improved scheduling performance in comparison to both heuristic-based schedulers and existing RL-based scheduling algorithms.

AI↗

DOE OSTI2025

AQuaRef: machine learning accelerated quantum refinement of protein structures

Cryo-EM and X-ray crystallography provide crucial experimental data for obtaining atomic-detail models of biomacromolecules. Refining these models relies on library-based stereochemical data, which, in addition to being limited to known chemical entities, do not include meaningful noncovalent interactions. Quantum mechanical (QM) calculations could alleviate these issues but are too expensive for large molecules. Here we present a novel AI-enabled Quantum Refinement (AQuaRef) based on AIMNet2 machine learned interatomic potential (MLIP) mimicking QM at substantially lower computational costs. By refining 41 cryo-EM and 30 X-ray structures, we show that this approach yields atomic models with superior geometric quality compared to standard techniques, while maintaining an equal or better fit to experimental data. Notably, AQuaRef aids in determining proton positions, as illustrated in the challenging case of short hydrogen bonds in the parkinsonism-associated human protein DJ-1 and its bacterial homolog YajL.

Zubatyuk, Roman [Carnegie Mellon University, Pitts↗

DOE OSTI2026

Pixel-Resolved Long-Context Learning for Turbulence at Exascale: Resolving Small-scale Eddies Toward the Viscous Limit

Turbulence plays a crucial role in multiphysics applications, including aerodynamics, fusion, and combustion. Accurately capturing turbulence's multiscale characteristics is essential for reliable predictions of multiphysics interactions, but remains a grand challenge even for exascale supercomputers and advanced deep learning models. The extreme-resolution data required to represent turbulence, ranging from billions to trillions of grid points, pose prohibitive computational costs for models based on architectures like vision transformers. To address this challenge, we introduce a multiscale hierarchical Turbulence Transformer that reduces sequence length from billions to a few millions and a novel RingX sequence parallelism approach that enables scalable long-context learning. We perform scaling and science runs on the Frontier supercomputer. Our approach demonstrates excellent performance up to 1.1 EFLOPS on 32,768 AMD GPUs, with a scaling efficiency of 94\%. To our knowledge, this is the first AI model for turbulence that can capture small-scale eddies down to the dissipative range in three-dimensional turbulence at high Reynolds numbers.

Yin, Junqi [ORNL] (ORCID:0000000338435520)↗

DOE OSTI2025

Edge at the Pier: EPCAPE Software-Defined Sensing Field Campaign Report

The Eastern Pacific Cloud Aerosol Precipitation Experiment (EPCAPE) was aimed to enhance the understanding of cloud and aerosol properties in the region surrounding La Jolla, California. To address challenges in data collection and processing from various instruments, an edge computing device known as Waggle Sage Node (WSN) was deployed at the Ellen Browning Scripps Memorial Pier. WSN is a distributed-sensing platform designed to collect and analyze environmental data at the edge. Sage is a multi-agency-supported project that designs and builds a new kind of national-scale reusable cyberinfrastructure to enable artificial intelligence (AI) at the edge based on the Waggle platform. Sponsors include the U.S. Department of Energy (DOE) Advanced Scientific Computing Research (ASCR), DOE National Nuclear Security Administration (NNSA), DOE Biological and Environmental Research (BER) through DOE Artificial Intelligence for Earth System Predictability (AI4ESP), Argonne Laboratory-Directed Research and Development (LDRD). Sage (https://sagecontinuum.org/) is funded as a National Science Foundation Mid-Scale Research Infrastructure (MSRI) project (https://www.nsf.gov/awardsearch/showAward?AWD_ID=1935984). This robust, multi-architecture edge computing platform facilitated environmental monitoring during the campaign. This report details the scientific objectives, deployment process, and key results of integrating Waggle into the EPCAPE field campaign.

54 ENVIRONMENTAL SCIENCES↗

DOE OSTI2025

Data Centers and Digital Assurance Workshop 2 – Prioritizing Digital Assurance Challenges, Session 2

The second session of the TADA (Technical Assistance for Digital Assurance) Data Centers Cohort, held on November 10, 2025, focused on prioritizing digital assurance challenges at the intersection of data centers and the electric grid. Building on the foundational concepts introduced in Workshop 1, this session deepened the application of the Threat–Vulnerability–Consequence (TVC) framework and emphasized the urgency of addressing cybersecurity, supply chain integrity, and operational reliability. Participants explored the growing convergence of digital and physical systems, the expanding attack surface due to global supply chain dependencies, and the implications of AI-driven load behavior. Real-world incidents—including the Volt Typhoon campaign and vulnerabilities in Solarman and Deye platforms—were analyzed to illustrate the risks of unpatched systems, insecure APIs, and inadequate vendor oversight. Key themes included architecture and interface weaknesses, governance gaps, and human and procedural shortcomings. The workshop also examined the evolving regulatory landscape, highlighting new federal mandates around Foreign Entity of Concern (FEOC) compliance and large-load reliability standards. Through interactive exercises, stakeholders ranked and mapped digital assurance risks from their respective perspectives—utilities, operators, and vendors—laying the groundwork for mitigation strategies and shared accountability models to be developed in Workshop 3. Session 2 of 3.

24 - POWER TRANSMISSION AND DISTRIBUTION↗

DOE OSTI2025

Congestion Management Solutions for Enhanced Distribution System Operations with Aggregated Distribution Grid Resources Providing Grid Services and Market Participation

Microgrids and other aggregations of distribution grid resources (DGRs) are poised to actively participate in electricity markets and provide essential grid services in the coming years. In fact, DGRs already play such a role through behind-the-meter (BTM) demand response programs and small-scale BTM dispatchable generation initiatives. At the same time, the rapid growth of artificial intelligence (AI) and cryptocurrency datacenters imposes significant, often unpredictable, demands on the power distribution system. Aggregated DGRs can serve as flexible resources that help mitigate these pressures by using available transmission and distribution capacity more efficiently, supporting resource adequacy and other reliability services, and providing bridge strategies while long-term transmission infrastructure is being developed. The impacts this activity will have on distribution networks are not fully understood and could present significant challenges for distribution utilities due to capacity constraints and the need for congestion management. Technical issues include reverse power flow, variability and possible degradation of equipment integrity, voltage violations, and customer power quality concerns. These issues will likely intensify as electricity market operators across the United States implement Federal Energy Regulatory Commission Order 2222 over the next few years.

24 POWER TRANSMISSION AND DISTRIBUTION↗

DOE OSTI2024

The role of AI in detecting and mitigating human errors in safety-critical industries: A review

For safety-critical industries, human error (HE) presents continual risks to system productivity, reliability and safety. Artificial intelligence (AI) and machine learning (ML) methods have emerged as promising approaches to understand, categorize and mitigate the risk of HE in safety-critical industries. Furthermore, this review offers an examination of the current landscape regarding the utilization of AI/ML with regards to HE in safety-critical industries, categorizing literature into descriptive modeling, predictive modeling, prescriptive modeling, and generative modeling techniques. Additionally, the review aims to provide insights regarding themes in literature, challenges, and future research directions. Findings of the review suggest that AI/ML methods can prove useful in addressing the HE problem across safety-critical industries.

42 ENGINEERING↗

NASA NTRS2010

Modeling the Information Age Combat Model: An Agent-Based Simulation of Network Centric Operations

The Information Age Combat Model (IACM) was introduced by Cares in 2005 to contribute to the development of an understanding of the influence of connectivity on force effectiveness that can eventually lead to quantitative prediction and guidelines for design and employment. The structure of the IACM makes it clear that the Perron-Frobenius Eigenvalue is a quantifiable metric with which to measure the organization of a networked force. The results of recent experiments presented in Deller, et aI., (2009) indicate that the value of the Perron-Frobenius Eigenvalue is a significant measurement of the performance of an Information Age combat force. This was accomplished through the innovative use of an agent-based simulation to model the IACM and represents an initial contribution towards a new generation of combat models that are net-centric instead of using the current platform-centric approach. This paper describes the intent, challenges, design, and initial results of this agent-based simulation model.

Deller, Sean↗