Search NASA⌕ Search

SEARCH · Search NASA

Results for “AI Risks”

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 55 records · Page 3
All sourcesNASA NTRSDOE OSTI
DOE OSTI2024

LUCID Thrust 1 - Dataset Identification and Biodata Catalog Creation

The LUCID DOE consortium, part of the Department of Energy’s Biological and Environmental Research (BER) program, advances Low Dose Radiation (LDR) research through multidisciplinary efforts across seven key thrusts. This document focuses on Thrust 1, which centers on the creation of curated multimodal population health datasets and supports broader efforts within the LUCID program, including AI-based hypothesis generation, experimental design, and the study of LDR-induced health risks. Specifically, it describes the identification and cataloging of Thrust 1’s curated LDR datasets and biodata, emphasizing their critical role in supporting various research thrusts within the consortium, with potential applications in healthcare and public policy. In addition, the document includes an evaluation of three Large Language Models (LLMs)—GPT-4, SOLAR-10B, and Mixtral-8x7B—based on their ability to extract features from 25 LDR studies. The results indicate that GPT-4 performed the best, while Mixtral-8x7B demonstrated limited knowledge. Overall, this work advances understanding in radiation protection, risk assessment, and medical treatments, while providing valuable resources for researchers, educators, and policymakers.

63 RADIATION, THERMAL, AND OTHER ENVIRON. POLLUTAN↗
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

Reimagining How Flood Warnings Can Inform Decision‐Making and Community Actions

Society faces increasingly severe flood hazards, intensifying demand for flood early warning systems (FEWS) that deliver accurate and actionable information. However, most existing FEWS remain prediction‐centric, treating decision‐making as a downstream consumer of hazard forecasts while offering limited support for uncertainty interpretation, risk communication, and real‐world response. This Perspective presents a vision and blueprint for a novel inland FEWS‐decision‐making (FEWS‐DM) framework that repositions decision‐making as an equal partner in the forecasting process—not a passive recipient of its outputs. The framework is built on three tightly coupled, co‐evolving thrusts: Physical Science (T1), which advances flood prediction with quantified uncertainty informed by decision relevance; Human Science (T2), which incorporates psychology, behavior, and cultural and institutional context; and Decision Science (T3), which unifies physical predictions and human factors through principled, utility‐based decision support with end‐to‐end uncertainty management. Rather than treating T1 as a solved problem, FEWS‐DM recognizes that forecast development itself must be shaped by decision needs through continuous bidirectional feedback. We identify key scientific, behavioral, and operational challenges limiting such integration and discuss the enabling role of AI, while emphasizing human‐centered design and community feedback as essential for building trust and improving flood risk management.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2025

Employing MACS/ViBRANT as a Surrogate MARVEL Reactor for Startup Reactivity Tuning and Supervisory Control Processes

Advanced nuclear reactors are a key part of the future of nuclear energy both in the United States and globally. They offer unique benefits for various energy-demanding applications, including use in remote locations, compact size, modular manufacturing, remote monitoring, low and/or variable power rating operation, and reliance on novel technologies to enhance operational safety. To achieve economic feasibility, advanced reactors must significantly reduce their workforces in comparison with the current fleet. Achieving this reduction will occur through reducing staff workloads using technology to achieve autonomous or semi-autonomous operations, demonstrated by comprehensive testing and validation activities. These operations will require both software and hardware platforms during the design and testing phases. While simulations are useful during the design phase, their performance can significantly deviate during actual deployment on hardware. This report presents the outcomes of a collaborative technical initiative between the U.S. Department of Energy (DOE) Microreactor Program (MRP) and Advanced Sensors and Instrumentation (ASI) Program. The collaboration utilized the Microreactor Automated Control System (MACS) hardware platform to bridge the gap between theoretical reactor design and actual startup and control operations. Two key use cases were investigated: facilitating the startup testing period and demonstrating supervisory control. The first use case details the key Microreactor Applications Research Validation and Evaluation (MARVEL) reactor startup physics testing activities conducted using the MACS platform. These activities included drum worth measurements, shutdown margin assessment, temperature feedback analysis, and scram time evaluation, as well as unique testing that would apply to the MARVEL reactor to demonstrate the testing methodologies in a low-risk environment. The MACS platform, serving as a surrogate representation of the MARVEL reactor, proved instrumental in performing these tests. The exercise revealed aspects that led to optimized processes, refined hardware design, and enhanced base software capabilities. By maturing methods and technologies in this manner, the initiative promises to reduce wasted time in the actual on-site reactor deployment effort, thereby saving significant time and resources. The second use case focuses on the development and implementation of supervisory control methods aimed at managing core tilt, which can result from asymmetrical operations or manufacturing imperfections in fuel rods or reactivity control devices. A key objective was to assess and compare the use of artificial intelligence (AI) for supervisory control. The effort aimed to define the role of supervisory control to enhance performance without risking control instability. This effort explored three distinct approaches: rules-based (RB) methods, optimization techniques, and reinforcement learning (RL) algorithms. Each approach was evaluated for its ease of implementation, its usability, and its effectiveness in responding to asymmetries in neutron flux. Comparative analysis of these approaches provided valuable insights into their applicability and effectiveness, offering a robust framework for advanced reactor operations. Together, these two use cases highlight the potential of hardware test beds to help streamline the design, operation, and control of advanced nuclear reactors. This collaborative effort underscores the importance of continued innovation and experimentation in achieving the next generation of safe, reliable, and economically viable nuclear energy solutions.

22 - GENERAL STUDIES OF NUCLEAR REACTORS↗
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 OSTI2024

Advanced Data Science Model for Detecting Intelligent Malware

This study focused on developing a robust artificial intelligence (AI) model capable of detecting and characterizing advanced malware in Internet of Things (IoT) devices using network data. By analyzing network traffic with various machine learning (ML) models, our AI model can identify and characterize malicious activities to significantly improve malware detection accuracy and reliability as compared to traditional methods. The developed AI/ML model was trained using network data from IoT devices, leveraging classifiers such as Random Forest, Gradient Boosting, AdaBoost, and others to optimize detection performance. This project demonstrates a scalable framework for real-time malware detection and characterization in IoT networks, capable of identifying infected devices and facilitating the necessary steps to remove or isolate them, thereby preventing further infections. Although digital twin (DT) integration is not yet implemented in the current model, it represents a promising future enhancement. By creating a virtual replica of physical IoT devices, DT technology would allow for real-time monitoring and analysis without directly accessing operational technology, thus reducing the risk of compromising or reducing the performance of actual devices. This integration would further enhance the security of IoT ecosystems, combining AI technology to better flag and detect indications of malware-infected devices within a nuclear system environment.

42 ENGINEERING↗
DOE OSTI2024

Utah FORGE 6-3629: Application of Machine Learning, Geomechanics, and Seismology for Real-Time Decision Making Tools During Stimulation - 2024 Annual Workshop Presentation

This is a presentation on the Cutting Edge Application of Machine Learning, Geomechanics, and Seismology for Real-Time Decision Making Tools During Stimulation by the University of Utah, presented by No'am Zach Dvory. This video slide presentation, by the University of Utah, discussed the technical objectives of developing a real-time decision-making platform to enhance seismic monitoring and risk management during stimulation activities. This presentation was featured in the Utah FORGE R&D Annual Workshop on August 15, 2024.

15 GEOTHERMAL ENERGY↗
DOE OSTI2025

MLCommons Science Benchmarks

Benchmarks are a cornerstone of modern machine learning practice, providing standardized eval- uations that enable reproducibility, comparison, and scientific progress. Yet, as AI systems particularly deep learning models become increasingly dynamic, traditional static benchmarking approaches are losing their relevance. Models rapidly evolve in architecture, scale, and capability; datasets shift; and deployment contexts continuously change, creating a moving target for evaluation. Without adaptive benchmarking frame- works, both scientific assessment and real-world de- ployment risk becoming misaligned with actual system behavior. Drawing on our experience from MLCommons, educa- tional initiatives, and government programs such as the DOE s Million Parameter Consortium, we identify key barriers that hinder the broader adoption and utility of benchmarking in AI. These include substantial resource demands, limited access to specialized hardware, lack of expertise in benchmark design, and uncertainty among practitioners about how to relate benchmark results to their own application domains. Moreover, current benchmarks often emphasize peak performance on leadership-class hardware, offering limited guidance for more diverse, real-world deployment scenarios. We argue that benchmarking itself must become dy- namic in order to incorporate evolving models, updated data, and heterogeneous computational platforms while maintaining transparency, reproducibility, and inter- pretability. Democratizing this process requires not only technical innovation, but also systematic educational efforts spanning undergraduate to professional levels to develop sustained expertise in benchmark design and use. Finally, benchmarks should be framed and com- municated to support application-relevant comparisons, enabling both developers and users to make informed, context-sensitive decisions. Advancing dynamic and inclusive benchmarking practices will be essential to ensure that evaluation keeps pace with the evolving AI landscape and supports responsible, reproducible, and accessible AI deployment.

Hawks, Benjamin G. [Fermilab]↗
DOE OSTI2024

Evaluating the Effectiveness of Retrieval-Augmented Large Language Models in Scientific Document Reasoning

Despite the dramatic progress in Large Language Model (LLM) development, LLMs often provide seemingly plausible but not factual information, often referred as hallucinations. Retrieval-augmented LLMs provide a non-parametric approach to solve these issues by retrieving relevant information from external data sources and augment the training process. These models helps to trace evidence from an externally provided knowledge base allowing the model predictions to be better interpreted and verified. In this work, we critically evaluate these models in their ability to perform in scientific document reasoning tasks. To this end, we tuned multiple such model variants with science-focused instructions and evaluated them on a scientific document reasoning benchmark for the usefulness of the retrieved document passages. Our findings suggest that models justify predictions in science tasks with fabricated evidence and leveraging scientific corpus as pretraining data does not alleviate the risk of evidence fabrication.

• Artificial intelligence (AI) / machine learning ↗
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 OSTI2024

Hardware-in-the-Loop Evaluation for Potential High Limit Estimation-Based PV Plant Active Control

This paper validates the efficacy of an artificial intelligence (AI)-based photovoltaic (PV) plant control and optimization approach in enabling PV plants as accountable grid reliability service providers. The validation is performed in a realistic laboratory controller-hardware-in-the-loop environment, leveraging accurate PV plant modeling and standard industrial communication protocols. Through simulations that account for diverse weather conditions and active control scenarios, the results highlight the superior performance of the AI-based solution in comparison to a state-of-the-art reference-control grouping-based approach. Such a finding contributes to mitigating the risk of overcurtailment and uninstructed deviations of active PV plant controls, and offers practical guidance for its field deployment. Furthermore, it establishes a standardized testing framework for comparing various PV active control strategies.

hardware-in-the-loop↗
DOE OSTI2025

Risk-informed Graded Approach for Reliability and Performance Assessment of Machine Learning and Artificial Intelligence for Advanced Condition Monitoring Techniques

With the shift away from time-based maintenance and toward condition-based maintenance, and to reduce overall maintenance costs, there has been an upsurge in the usage and development of advanced condition monitoring (ACM) techniques for real-time monitoring of nuclear power plant (NPP) components. ACM is particularly useful in the development of digital twins, which are designed to predict the failure or degradation of plant components. Successful implementation of ACM requires an assessment to inform the development of a risk-informed approach to evaluate the use of ACM to meet Nuclear Regulatory Committee (NRC) regulations for in-service testing (IST) programs. This includes the monitoring and diagnostics of reactor components and systems in current, new, and advanced reactors. A key component in ACM is the usage of machine learning (ML) and artificial intelligence (AI) algorithms that can employ real-time data from instrumentation and sensors to detect and predict reactor component degradations. Such predictive capabilities enable early detection of component degradation so as to help plant personnel plan and execute necessary maintenance. For successful implementation of ML/AI in ACM such that regulatory requirements are met, a risk-informed graded approach is needed to assess the reliability and performance of ML/AI for ACM. The American Society for Mechanical Engineers (ASME) developed their Operations and Maintenance (O&M) Code to provide guidance on safe, reliable O&M of NPPs. The IST section of the O&M Code specifically establishes requirements for IST and examination to gauge operational readiness of components in water-cooled NPPs. This paper presents a state-of-the-art review of how reliability and risk assessment can be integrated with ACM to assess component performance by non-nuclear industries. This is followed by different methodologies and approaches for conducting performance and reliability assessments so as to meet IST requirements for NPP components.

97 - MATHEMATICS AND COMPUTING↗
DOE OSTI2025

Risk-informed Graded Approach for Reliability and Performance Assessment for Advanced Condition Monitoring Techniques

With the shift away from time-based maintenance and toward condition-based maintenance, and to reduce overall maintenance costs, there has been an upsurge in the usage and development of advanced condition monitoring (ACM) techniques for real-time monitoring of nuclear power plant (NPP) components. ACM is particularly useful in the development of digital twins, which are designed to predict the failure or degradation of plant components. Successful implementation of ACM requires an assessment to inform the development of a risk-informed approach to evaluate the use of ACM to meet Nuclear Regulatory Committee (NRC) regulations for in-service testing (IST) programs. This includes the monitoring and diagnostics of reactor components and systems in current, new, and advanced reactors. A key component in ACM is the usage of machine learning (ML) and artificial intelligence (AI) algorithms that can employ real-time data from instrumentation and sensors to detect and predict reactor component degradations. Such predictive capabilities enable early detection of component degradation so as to help plant personnel plan and execute necessary maintenance. For successful implementation of ML/AI in ACM such that regulatory requirements are met, a risk-informed graded approach is needed to assess the reliability and performance of ML/AI for ACM. The American Society for Mechanical Engineers (ASME) developed their Operations and Maintenance (O&M) Code to provide guidance on safe, reliable O&M of NPPs. The IST section of the O&M Code specifically establishes requirements for IST and examination to gauge operational readiness of components in water-cooled NPPs. This paper presents a state-of-the-art review of how reliability and risk assessment can be integrated with ACM to assess component performance by non-nuclear industries. This is followed by different methodologies and approaches for conducting performance and reliability assessments so as to meet IST requirements for NPP components.

99 - GENERAL AND MISCELLANEOUS↗
DOE OSTI2026

MSD CoP Webinar: Modeling the Operations of Reservoir Systems with LLMs and Inverse Reinforcement Learning

Context: This panel featured three presentations centered on the common theme of applying LLMs and inverse reinforcement learning (IRL) to capture the complex human-environment interactions that are central to the operation of reservoir systems. Dr. Wyatt Arnold will kick off the webinar with a talk on how analyzing LLM chain-of-thought reasoning reveals sophisticated quantitative justification and risk awareness, showing promise as a bridge between quantitative models and value-driven water management decisions. Next, Dr. Matteo Giuliani will build on this with a discussion demonstrating that AI- and IRL-driven approaches can infer the trade-offs between flood control and water supply using historical observations. Finally, Dr. Rohan Singh Wilkho will close the webinar with a talk establishing IRL as a generalizable diagnostic tool for decoding decision-making in managed hydrologic and human-infrastructure systems. Across the three presentations, the application of LLMs and IRL opens new possibilities for the development of adaptive, transparent, and human-aware models supporting water management in an increasingly uncertain future. Presenters: Wyatt Arnold (Politecnico di Milano); Matteo Giuliani (Politecnico di Milano); Rohan Singh Wilkho (Cornell University) Moderator: Patrick M. Reed (MSD CoP Facilitation Team); Stefano Galelli (MSD CoP AI Working Group Co-Chair); David Gold (MSD CoP AI Working Group Co-Chair) This webinar was held on: June 23rd, 2026 from 12-1 PM EST.

Arnold, Wyatt [Politecnico di Milano]↗
DOE OSTI2026

Commercial integration of advanced nuclear energy with Artificial Intelligence (AI): Possible implications

The integration of advanced nuclear technologies (both fission and fusion) with artificial intelligence (AI) presents unprecedented national security challenges and opportunities. As fusion energy approaches commercial viability alongside advanced Small Modular Reactors (SMRs), their integration with AI and Artificial General Intelligence (AGI) systems could fundamentally transform the global energy and AI landscapes — two pillars of national security. This document briefly examines how AI could accelerate nuclear energy development and deployment while altering existing power structures, a lot could be done to deepen the discussions. Simultaneously, it observes how nuclear-powered AI may expedite advances toward AGI and beyond. These issues are deeply interconnected and thus need to be examined as a whole and more comprehensively than what’s being summarized here. For instance, AI-powered autonomous operation of nuclear facilities could reduce human error but introduce new cybersecurity vulnerabilities and uncertainties. Further investigation would also address how AI-enhanced nuclear technologies might complicate proliferation concerns through advanced fuel cycle management, nuclear materials production and safeguard. The strategic advantage gained by first entities achieving successful AI-nuclear integration could reshape global and national security framework. Timely analysis of these implications may be crucial for policymakers seeking to harness these technologies' benefits while effectively mitigating their potential risks.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗
DOE OSTI2025

Engineering Out Industry 4.0 Cyber Risk

The increasing complexity and business requirements of operational technology (OT) devices is beginning to break the normal segmentation between information technology (IT) and OT networks. The introduction of industry 4.0 devices such as industrial internet of things (IIoT) and other intelligent industrial devices (IID), virtualized OT systems, OT cloud integration, and artificial intelligence (AI)-driven industrial control systems (ICS) has challenged traditional IT/OT cybersecurity strategies. Industry 4.0 devices are analyzed through the lens of well-regarded models such as the PERA model and confidentiality, integrity, and availability (CIA) security objectives, showing the division between what is needed and traditional cybersecurity countermeasures. In this paper, the practice of Cyber-Informed Engineering (CIE) is proposed to bridge the gap between IT/OT security, enhance the practice of cybersecurity in this modern age, and reduce the impacts of consequential events in OT.

42 - ENGINEERING↗
DOE OSTI2025

Geospatial Diffusion for Land Cover Imperviousness Change Forecasting

Land-use and land-cover (LULC) has a significant effect on several Earth system processes. For example, impervious surfaces reduce infiltration and speed water flow, impacting regional hydrology and flood risk. While Earth System models have improved forecasting hydrologic and atmospheric processes at higher resolutions, the ability to forecast LULC change has lagged behind. In this paper, we propose a new paradigm exploiting Generative AI (GenAI) for land cover change forecasting by framing it as a data synthesis problem conditioned on historical and auxiliary data-sources. To demonstrate the feasibility of our methodology, we perform experiments where a diffusion model is trained for decadal forecasting of imperviousness change across the entire United States. We find that our model yields MAE lower than a no-change baseline for resolutions ≥ 0.7 X 0.7km2 on average, demonstrating its ability to capture and project accurate spatiotemporal patterns. Finally, we discuss future research to incorporate Earth's physical properties and enabling scenario simulations via driver variables.

Varshney, Debvrat [ORNL] (ORCID:0000000188981736)↗
DOE OSTI2026

Opportunities in AI/ML for the Rubin LSST Dark Energy Science Collaboration

The Vera C. Rubin Observatory's Legacy Survey of Space and Time (LSST) will produce unprecedented volumes of heterogeneous astronomical data (images, catalogs, and alerts) that challenge traditional analysis pipelines. The LSST Dark Energy Science Collaboration (DESC) aims to derive robust constraints on dark energy and dark matter from these data, requiring methods that are statistically powerful, scalable, and operationally reliable. Artificial intelligence and machine learning (AI/ML) are already embedded across DESC science workflows, from photometric redshifts and transient classification to weak lensing inference and cosmological simulations. Yet their utility for precision cosmology hinges on trustworthy uncertainty quantification, robustness to covariate shift and model misspecification, and reproducible integration within scientific pipelines. This white paper surveys the current landscape of AI/ML across DESC's primary cosmological probes and cross-cutting analyses, revealing that the same core methodologies and fundamental challenges recur across disparate science cases. Since progress on these cross-cutting challenges would benefit multiple probes simultaneously, we identify key methodological research priorities, including Bayesian inference at scale, physics-informed methods, validation frameworks, and active learning for discovery. With an eye on emerging techniques, we also explore the potential of the latest foundation model methodologies and LLM-driven agentic AI systems to reshape DESC workflows, provided their deployment is coupled with rigorous evaluation and governance. Finally, we discuss critical software, computing, data infrastructure, and human capital requirements for the successful deployment of these new methodologies, and consider associated risks and opportunities for broader coordination with external actors.

Aubourg, Eric [APC, Paris] (ORCID:000000025592023X↗