Search NASA⌕ Search

SEARCH · Search NASA

Results for “agent based modeling”

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 631 records · Page 35
All sourcesNASA NTRSDOE OSTI
NASA NTRS1993

Applications of artificial intelligence 1993: Knowledge-based systems in aerospace and industry; Proceedings of the Meeting, Orlando, FL, Apr. 13-15, 1993

The present volume on applications of artificial intelligence with regard to knowledge-based systems in aerospace and industry discusses machine learning and clustering, expert systems and optimization techniques, monitoring and diagnosis, and automated design and expert systems. Attention is given to the integration of AI reasoning systems and hardware description languages, care-based reasoning, knowledge, retrieval, and training systems, and scheduling and planning. Topics addressed include the preprocessing of remotely sensed data for efficient analysis and classification, autonomous agents as air combat simulation adversaries, intelligent data presentation for real-time spacecraft monitoring, and an integrated reasoner for diagnosis in satellite control. Also discussed are a knowledge-based system for the design of heat exchangers, reuse of design information for model-based diagnosis, automatic compilation of expert systems, and a case-based approach to handling aircraft malfunctions.

Fayyad, Usama M.↗
DOE OSTI2025

Distributed fiber-optic sensing in a subscale high-temperature superconducting dipole magnet

High-temperature superconductors, such as REBa2Cu3O7−x (REBCO, RE = rare earth), are becoming pivotal for high-field magnet technology for future circular colliders and compact fusion reactors. The U.S. Magnet Development Program, in collaboration with industry, is developing REBCO magnet technology using round conductors consisting of multiple REBCO tapes. For these multi-tape cables, traditional instrumentation, such as voltage taps and resistive strain gauges, become insufficient to help measure and understand the performance-limiting factors in these model magnets. Distributed fiber-optic sensing (DFOS) is a potential solution to address this challenge. Although DFOS is well established for various applications, measuring temperature and strain in high-temperature superconducting magnets is in its infancy. Here we report the detailed implementation and test results of DFOS based on Rayleigh scattering in a subscale canted cosθ (CCT) dipole magnet using high-temperature superconducting CORC® wires. We co-wound optical fibers in each layer of the CCT magnet and compared different types of commercial fibers and mold-release agents to reduce the power attenuation in the fibers. The DFOS allowed us to measure mechanical deformation and temperature along the conductor during tests at 77 and 4.2 K. The measured strain agreed quantitively with a finite-element mechanical model of the subscale magnet. Our results indicate that DFOS can effectively identify locations of strain and temperature changes, offering unique insight into magnet performance that can advance our understanding and development of the REBCO magnet technology for high-energy physics and fusion applications.

Luo, Linqing↗
DOE OSTI2026

GridCoPilot for Thermal Events: An LLM-Based Platform for Power Grid Reliability Analysis

Large Language Models show promise for translating natural language into database queries, but deploying such systems in safety-critical domains requires high reliability. We present an application of GridCoPilot to thermal event analysis (heatwaves and coldwaves) that affect power grid reliability. Our approach uses a LangChain SQL Agent to translate natural language queries into auditable SQL statements, with deterministic visualization routines that parse the structured query results. We introduce structural framing as a design principle, we integrate a NERC-region-level event library with county-level meteorology and decompose the combined data into three relational tables (event metadata, county-level event details, and a county-to-NERC subregion mapping), using prompt-guided joins to direct the model toward correct multi-table queries. For two core analytical patterns (identifying worst events by region and by region-year), the system achieved 100% SQL accuracy across all 16 NERC subregions and both event types (64 queries total). These results validate the approach for target use cases, though performance on diverse natural language formulations requires further investigation. We discuss design trade-offs, failure modes including JSON output truncation, and pathways for extending this approach to other hazard domains.

24 POWER TRANSMISSION AND DISTRIBUTION↗
NASA NTRS2024

Aera-Mip: Emission Pathways, Remaining Budgets, and Carbon Cycle Dynamics Compatible With 1.5 and 2 °C Global Warming Stabilization

While international climate policies now focus on limiting global warming to well below 2 °C or pursuing a 1.5 °C level of global warming, the climate modelling community has not provided an experimental design in which all Earth system models (ESMs) converge and stabilize at the same prescribed global warming levels. This gap hampers accurate estimations based on comprehensive ESMs of the carbon emission pathways and budgets needed to meet such agreed warming levels and of the associated climate impacts under temperature stabilization. Here, we apply the Adaptive Emission Reduction Approach (AERA) with ESMs to provide such simulations in which all models converge at 1.5 and 2.0 °C warming levels by adjusting their emissions over time. These emission-driven simulations provide a wide range of emission pathways and resulting atmospheric CO 2 projections for a given warming level, uncovering uncertainty ranges that were previously missing in the traditional Coupled Model Intercomparison Project (CMIP) scenarios with prescribed greenhouse gas concentration pathways. Meeting the 1.5 °C warming level requires a 40 % (full model range: 7 % to 76 %) reduction in multi-model mean CO 2 -forcing-equivalent (CO 2 -fe) emissions from 2025 to 2030, a 98 % (57 % to 127 %) reduction from 2025 to 2050, and a stabilization at 1.0 (−1.7 to 2.9) PgC yr−1 from 2100 onward after the 1.5 °C global warming level is reached. Meeting the 2.0 °C warming level requires a 47 % (8 % to 92 %) reduction in multi-model mean CO 2 -fe emissions until 2050 and a stabilization at 1.7 (−1.5 to 2.7) PgC yr−1 from 2100 onward. The on-average positive emissions under stabilized global temperatures are the result of a decreasing transient climate response to cumulative CO 2 -fe emissions over time under stabilized global warming. This evolution is consistent with a slightly negative zero emissions commitment – initially assumed to be zero – and leads to an increase in the post-2025 CO 2 -fe emission budget by a factor of 2.2 (−0.8 to 6.9) by 2150 for the 1.5 °C warming level and a factor of 1.4 (0.9 to 2.4) for the 2.0 °C warming level compared to its first estimate in 2025. The median CO 2 -only carbon budget by 2150, relative to 2020, is 800 GtCO 2 for the 1.5 °C warming level and 2250 GtCO 2 for the 2.0 °C warming level. These median values exceed the median IPCC AR6 estimates by 60 % for the 1.5 °C warming level and 67 % for 2.0 °C. Some of the differences may be explained by the choice of the mitigation scenario for non-CO 2 radiative agents. Our simulations highlight shifts in carbon uptake dynamics under stabilized temperature, such as a cessation of the carbon sinks in the North Atlantic and in tropical forests. On the other hand, the Southern Ocean remains a carbon sink centuries after temperatures stabilize. Overall, this new type of warming-level-based emission-driven simulation offers a more coherent assessment across climate models and opens up a wide range of possibilities for studying both the carbon cycle and climate impacts, such as extreme events, under climate stabilization.

Adaptive Emission Reduction Approach↗
DOE OSTI2020

Transactive Energy Systems: The Market-based Coordination of Distributed Energy Resources

This paper synthesizes a unifying framework that captures a large class of transactive energy systems studied in the literature. The framework consists of four key elements: agent preferences, control decisions, information structure, and solution concept. Among them, agent preference specifies the preferred outcome by each agent and models the conflict of interest in decision making. Control decision specifies the set of decisions for each agent to maximize its payoff. Information structure describes the information available to each agent before it makes a decision. Solution concept encodes the rationality assumptions of each agent in the system. These elements are important in identifying and distinguishing different transactive energy systems. In this paper, we use them to analyze a number of important ones, including the competitive equilibrium, Stackelberg game, reverse Stackelberg game, and mechanism design. Each class of these problems is formulated as a special case of the proposed transactive energy systems. Their connections and differences are discussed. Available tools and results for each category of problems are surveyed.

Li, Sen↗
DOE OSTI2023

Inverse reinforcement learning control for building energy management

Reinforcement learning (RL) based control is widely considered a promising approach in building automation and control as it has demonstrated the potential to deal with complex objectives in adjacent domains like robotics, autonomous vehicles, gaming applications, and advertisement recommendations. When applied to any environment, model-free RL learns to improve its control performance over time without requiring a control model, by receiving and then analyzing feedback from the building environment after each control action. Operational objectives are becoming increasingly complex through the simultaneous consideration of thermal comfort, carbon emissions, grid services, and indoor air quality. In this context, conventional rule-based control approaches are proving sub-optimal, mostly heuristic, and inadequate. The model-free and self learning nature of RL appears promising and attractive as it may address the scalability issues associated with advanced control approaches. However, it suffers from long training times and unstable control behavior during the early stages of its learning process, which makes it unsuitable to be applied directly to buildings. This paper addresses these issues using an inverse reinforcement learning approach (IRL), a technique utilized to learn the objective of a controller agent which is considered an expert in its respective domain. Here, we consider a rule-based control as the expert demonstrator. IRL is different from a direct imitation (i.e., direct mapping of states to actions) of control actions as it tries to find the underlying intent of an expert's policy, providing the controller with a better-generalized policy for unseen states or environments with slightly different dynamics. This approach propels the RL controller's policy to levels similar to or better than that of a rule-based policy before it starts learning by interacting with the building. This makes RL for building energy management applications more practical as it prevents the erratic and exploratory behavior in the initial training period, simultaneously speeding up the learning process when compared to applying an untrained RL agent directly to a building environment.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗
DOE OSTI2020

OpenABLext: An automatic code generation framework for agent-based simulations on CPU-GPU-FPGA heterogeneous platforms

The execution of agent-based simulations (ABSs) on hardware accelerator devices such as graphics processing units (GPUs) has been shown to offer great performance potentials. However, in heterogeneous hardware environments, it can become increasingly difficult to find viable partitions of the simulation and provide implementations for different hardware devices. To automate this process, we present OpenABLext, an extension to OpenABL, a model specification language for ABSs. By providing a device-aware OpenCL backend, OpenABLext enables the co-execution of ABS on heterogeneous hardware platforms consisting of central processing units, GPUs, and field programmable gate arrays (FPGAs).We present a novel online dispatching method that efficiently profiles partitions of the simulation during run-time to optimize the hardware assignment while using the profiling results to advance the simulation itself. In addition, OpenABLext features automated conflict resolution based on user-specified rules, supports graph-based simulation spaces, and utilizes an efficient neighbor search algorithm. We show the improved performance of OpenABLext and demonstrate the potential of FPGAs in the context of ABS. We illustrate how co-execution can be used to further lower execution times. OpenABLext can be seen as an enabler to tap the computing power of heterogeneous hardware platforms for ABS.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2025

Spatial Impacts of Electric Vehicle Charging on Power Grid Stability: A Downtown Atlanta Case Study

The rapid increase in electric vehicle (EV) charging demand poses a potential risk to power grid stability, particularly as the spatial distribution of this demand remains underexplored. Existing research often focuses on technical optimization models while overlooking the geographic and human dynamics that affect energy consumption. This study addresses this gap by incorporating mobility data to estimate both building energy use and EV charging demand while also considering geographic factors for a better understanding of grid load. Using agent-based simulations and the Open-Source Distribution System Simulator, the study evaluates the effect of various EV penetration scenarios on grid voltage and unbalance. The results show that, although voltage remains within acceptable limits at lower EV penetration rates, significant voltage drop and unbalance occur as EV penetration exceeds 40%, particularly in residential areas with high charging demand. This study offers a framework for integrating spatial analysis and mobility data in power network simulations, providing insights for future EV infrastructure planning.

Pan, Melrose [ORNL] (ORCID:000000031627448X)↗
DOE OSTI2023

3D_MolGNN_RL

3D-MolGNNRL, couples reinforcement learning (RL) to a deep generative model based on 3D-Scaffold to generate target candidates specific to a protein pocket building up atom by atom from the core scaffold. 3D-MolGNNRL provides an efficient way to optimize key features within a protein pocket using a parallel graph neural network model. The agent learns to build molecules in 3D space while optimizing the binding affinity, potency, and synthetic accessibility of the candidates generated for the SARS-CoV-2 Main protease

Kumar, Neeraj↗
NASA NTRS1984

Abrasion by aeolian particles: Earth and Mars

Estimation of the rate of aeolian abrasion of rocks on Mars requires knowledge of: (1) particle flux, (2) susceptibilities to abrasion of various rocks, and (3) wind frequencies on Mars. Fluxes and susceptibilities for a wide range of conditions were obtained in the laboratory and combined with wind data from the Viking meteorology experiment. Assuming an abundant supply of sand-sized particles, estimated rates range up to 2.1 x 10 to the minus 2 power cm of abrasion per year in the vicinity of Viking Lander 1. This rate is orders of magnitude too great to be in agreement with the inferred age of the surface based on models of impact crater flux. The discrepancy in the estimated rate of abrasion and the presumed old age of the surface cannot be explained easily by changes in climate or exhumation of ancient surfaces. The primary reason is thought to be related to the agents of abrasion. At least some sand-sized (approx. 100 micrometers) grains appear to be present, as inferred from both lander and orbiter observations. High rates of abrasion occur for all experimental cases involving sands of quartz, basalt, or ash. However, previous studies have shown that sand is quickly comminuted to silt- and clay-sized grains in the martian aeolian regime. Experiments also show that these fine grains are electrostatically charged and bond together as sand-sized aggregates. Laboratory simulations of wind abrasion involving aggregates show that at impact velocities capable of destroying sand, aggregates from a protective veneer on the target surface and can give rise to extremely low abrasion rates.

Greeley, R.↗
DOE OSTI2025

HEPTAPOD: Orchestrating High Energy Physics Workflows Towards Autonomous Agency

Many workflows in high-energy-physics (HEP) stand to benefit from recent advances in transformer-based large language models (LLMs). While early applications of LLMs focused on text generation and code completion, modern LLMs now support orchestrated agency: the coordinated execution of complex, multi-step tasks through tool use, structured context, and iterative reasoning. We introduce the HEP Toolkit for Agentic Planning, Orchestration, and Deployment (HEPTAPOD), an orchestration framework designed to bring this emerging paradigm to HEP pipelines. The framework enables LLMs to interface with domain-specific tools, construct and manage simulation workflows, and assist in common utility and data analysis tasks through schema-validated operations and run-card-driven configuration. To demonstrate these capabilities, we consider a representative Beyond the Standard Model (BSM) Monte Carlo validation pipeline that spans model generation, event simulation, and downstream analysis within a unified, reproducible workflow. HEPTAPOD provides a structured and auditable layer between human researchers, LLMs, and computational infrastructure, establishing a foundation for transparent, human-in-the-loop systems.

Menzo, Tony [Alabama U.; Fermilab] (ORCID:00000002↗
DOE OSTI2018

A game theory approach for assessing risk value and deploying search-and-rescue resources after devastating tsunamis

Highlights: • Two game theoretic models are designed for search-and-rescue resource allocation. • A simulation based upon 2011 Japan tsunami data. • Shapley value division is more efficient than the proportional division. The current early-warning system and tsunami protection measures tend to fall short because they always underestimate the level of destruction, and it is difficult to predict the level of damage by a devastating tsunami on uncertain targets. As we know, the key to minimizing the total number of fatalities after a disaster is the deployment of search and rescue efforts in the first few hours. However, the resources available to the affected districts for emergency response may be limited. This study proposes two game theoretic models that are designed for search-and-rescue resource allocation. First, the interactions between a compounded disaster and a response agent in the affected district are modelled as a non-cooperative game, after which the risk value is derived for each district from the Nash equilibrium. The risk value represents the threat, vulnerability, and consequence of a specific disaster for the affected district. Second, the risk values for fifteen districts are collected for calculation of each district's Shapley value. Then an acceptable plan for resource deployment among all districts is made based on their expected marginal contribution. The model is verified in a simulation based upon 2011 tsunami data. The experimental results show the proposed approach to be more efficient than the proportional division of rescue resources, for dealing with compounded disaster, and is feasible as a method for planning the mobilization of resources and to improve relief efforts against devastating tsunamis.

54 ENVIRONMENTAL SCIENCES↗
NASA NTRSDate not supplied

Design, Formalization, and Verification of Decision Making for Intelligent Systems

The development of autonomous systems requires a rigorous process that can guarantee a system’s reliability in critical applications. At its core, an autonomous system bases its behavior on a well-defined decision making system. In this paper, we present a methodological basis for the design, formalization and formal verification of Decision Making systems for autonomous agents. The approach is generally applicable to operational objectives that can be functionally decomposed and subsequently represented as Hierarchical Finite State Machines. As a case study, we present the application of this method to implement a Decision Making model in Simulink. Furthermore, we present how we use NASA’s FRET tool to write requirements in structured natural language and generate formal specifications that can be automatically digested by NASA’s CoCoSim tool. Finally, we present how, by leveraging CoCoSim, we perform formal verification against the Simulink model and present analysis results.

Model-based development↗
NASA NTRSDate not supplied

Design, Formalization, and Verification of Decision Making for Intelligent Systems

The development of autonomous systems requires a rigorous process that can guarantee a system’s reliability in critical applications. At its core, an autonomous system bases its behavior on a well-defined decision making system. In this paper, we present a methodological basis for the design, formalization and formal verification of Decision Making systems for autonomous agents. The approach is generally applicable to operational objectives that can be functionally decomposed and subsequently represented as Hierarchical Finite State Machines. As a case study, we present the application of this method to implement a Decision Making model in Simulink. Furthermore, we present how we use NASA’s FRET tool to write requirements in structured natural language and generate formal specifications that can be automatically digested by NASA’s CoCoSim tool. Finally, we present how, by leveraging CoCoSim, we perform formal verification against the Simulink model and present analysis results.

Model-based development↗
DOE OSTI2018

Natural Product Micheliolide (MCL) Irreversibly Activates Pyruvate Kinase M2 and Suppresses Leukemia

Metabolic reprogramming of cancer cells is essential for tumorigenesis in which pyruvate kinase M2 (PKM2), the low activity isoform of pyruvate kinase, plays a critical role. Herein, we describe the identification of a nature-product-derived micheliolide (MCL) that selectively activates PKM2 through the covalent binding at residue cysteine424 (C424), which is not contained in PKM1. This interaction promotes more tetramer formation, inhibits the lysine433 (K433) acetylation, and influences the translocation of PKM2 into the nucleus. In addition, the pro-drug dimethylaminomicheliolide (DMAMCL) with similar properties as MCL significantly suppresses the growth of leukemia cells and tumorigenesis in a zebrafish xenograft model. Cell-based assay with knock down PKM2 expression verifies that the effects of MCL are dependent on PKM2 expression. DMAMCL is currently in clinical trials in Australia. Our discovery may provide a valuable pharmacological mechanism for clinical treatment and benefit the development of new anticancer agents.

60 APPLIED LIFE SCIENCES↗
DOE OSTI2022

Thermal and concentration effects on 1 H NMR relaxation of Gd 3+ -aqua using MD simulations and measurements

We report gadolinium-based contrast agents are key in clinical MRI for enhancing the longitudinal NMR relativity (r 1 ) of hydrogen nuclei ( 1 H) in water and improving the contrast among different tissues. The importance of MRI in clinical practice cannot be gainsaid, yet the interpretation of MRI relies on models with severe assumptions, reflecting a poor understanding of the molecular-scale relaxation processes. In a step towards building a clearer understanding of the relaxation processes, here we investigate thermal and concentration effects on r 1 of the Gd 3+ -aqua complex using both semi-classical molecular dynamics (MD) simulations and measurements. We follow the MD simulation approach recently introduced by [Singer et al., Phys. Chem. Chem. Phys., 2021, 23, 20974], in which no NMR relaxation model or free-parameter is assumed to predict r 1 , thereby bringing new insights into the physics of r 1 on a molecular scale. We expand the autocorrelation function G(t) in terms of molecular modes and determine the thermal activation energies of the two largest modes, both of which are consistent with the range of literature values for rotational diffusion. We also determine the activation energies for translational diffusion and low-field electron-spin relaxation, both of which are consistent with the literature. Furthermore, we validate the MD simulations at human body temperature and concentrations of the paramagnetic ion used in clinical MRI, and we quantify the uncertainties in both simulations and measurements.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2019

Modeling Coupled Durability and Performance in Polymer-Electrolyte Fuel Cells: Membrane Effects

During operation, proton-exchange-membrane fuel cells (PEMFCs) are subjected to mechanical and chemical stressors that contribute to membrane degradation, performance loss, and eventual failure. Together, synergistic effects between mechanical and chemical degradation mechanisms lead to accelerated degradation. A physics-based model is developed to understand the synergistic effects of chemical and mechanical degradation and the coupled nature of performance and durability in PEMFCs. The model includes pinhole existence and growth in the membrane, which increases crossover of reactant gases as well as subsequent formation of chemical degradation agents that impact both transport and mechanical properties of the membrane. The fuel-cell model is fully coupled with a mechanical model to determine the stresses on the membrane and subsequent growth of pinholes during transient operation. Simulation results demonstrate pinhole growth under relative-humidity cycling and the resultant increased gas-crossover fluxes and decrease in polarization performance. Furthermore, the model results highlight nonlinearities and the importance of coupling mechanical and chemical degradation models in order to explain membrane degradation under various cycles, and serves as a foundation for examining coupled durability and performance.

25 ENERGY STORAGE↗
DOE OSTI2022

Sequential Decision Making (SDM) for Mesh Refinement and Model Selection in Multiscale, Multi-Physics Applications

Intelligent automation and decision support are needed to enhance computational efficiency and robustness in multiscale and multi-physics problems, including materials science, manufacturing, and climate and weather modeling. Current scientific computing approaches for enabling decisions by scientists fail to explore the role of learning, reasoning, and probabilistic planning. Often these decisions are not performed in real-time during the computation but are made prior to the start of the computation, which must be interrupted in order to make changes to the prior choices. Such interruptions at different stages of the computation increase the total computing time and the need for a human expert to frequently monitor the results. State of art scientific computing methods consist of rule-based algorithms that cannot automatically adapt to a dynamically changing computing environment. The development of a Sequential Decision Making (SDM) framework will automate scientific computing by optimizing the policies for mesh refinement, time-stepping, model and algorithm selection, resource allocation, and pre and post-processing. Our agent SDM framework for scientific computing will consist of data-driven learning (Classifier), automated reasoning (contextual knowledge), and probabilistic planning (Reinforcement Learning). In this project, we focused on three problems to demonstrate our SDM framework on a set of ordinary and partial differential equations. Classification of Lorenz system regions using Feed-Forward Neural Networks examined learning in the SDM framework. On the other hand, reasoning and planning in the SDM framework were used in two problems: adaptive time-stepping for nonlinear ODEs using on-policy RL algorithms, and adaptive mesh refinement for 2-D PDEs using off-policy RL algorithms.

97 MATHEMATICS AND COMPUTING↗