Search NASA⌕ Search

SEARCH · Search NASA

Results for “AI Agent”

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.

178 records · Page 10

PRIMED for the Future: Purposing Raw Intake for Machine Learning-Enabled Detection (Final Report)

The COVID-19 pandemic demonstrated how a novel, elusive, and diffuse biological threat can engender uncertainty and misinformation, and it underscored the need for flexible analytical modalities agnostic to the identity of biological material. Yet even before the pandemic, recognition of the limitations of the current, list-based approach, which focuses on known pathogens and biotoxins, and of the importance of agent-agnostic biodetection was growing within the biosecurity community. In a 2018 report on “Biodefense in the Age of Synthetic Biology,” for example, the National Academy of Sciences stated that “an overreliance on the Select Agent List is a systematic weakness affecting many aspects of the United States’ current biodefense mitigation capability”. More recently, a group of biodefense researchers proposed the identification and adoption of “bioagent-agnostic signatures (BASs)” as a way of detecting and characterizing not only existing agents but also novel ones, an approach they believe will “enable a more flexible and resilient biodefense posture”. Indeed, the future of biodetection requires us to begin developing novel analytics that can identify anomalies and/or characteristics that indicate a potential threat, whether known or unknown, without looking for a specific signature that has been identified previously. To assess potential threats more rapidly, it is critical to develop agnostic artificial intelligence (AI)/machine learning (ML) systems that can be employed for real-time assessment of the nature and source of a perturbation. Such systems should be multi scale and multi-dimensional, integrating sensor data from a range of biological, chemical, and physical application spaces. Emerging deep learning (DL) models demonstrate exceptional promise for identification of discriminatory features within multi-dimensional datasets. DL models have the capacity to recognize and encode highly complex patterns in a wide range of input data modalities, including images, text, and biological/chemical/physical spectra. As such, they can execute a wide range of assessments and determinations that have traditionally required a human operator. The promise of advances in DL is apparent in the realm of human health and medicine. DL models have been validated for evaluating a variety of clinical threats to human health in a range of contexts, including infection and cancer, and they demonstrated improved performance in predicting stroke relative to human neurologists in some categories of data. Continuously evolving advances in AI/ML are expected to support more efficient evaluation of raw sequence, spectroscopy, and spectrometry data. For instance, recent advances and deployment of large language models (LLM) such as Generative Pre training Transformer (GPT) and Bidirectional Encoder Representations from Transformers (BERT) have already motivated application of these models for biological function prediction. As frameworks such as LLMs become larger and more complex in their representations, their capacity to serve as pre-trained models that can be fine-tuned for biological/biodetection purposes will similarly be amplified. While existing and emerging AI/ML have found broad applicability and use cases in the clinical sciences, development for environmental evaluation and biodetection has been limited. Functionalizing such capabilities for this purpose requires an understanding of the existing technical landscape and how the respective tools and algorithms are currently being employed. This landscape awareness then allows an assessment of the current practical capabilities of existing models and the anticipated requirements and development efforts that will be needed to adapt available algorithms for biodetection applications relevant to DHS. Leveraging expertise in biodetection, ML, and operational biodetection, the effort described in this report is comprised of a systematic landscape assessment (Subtask 2.1), comparative evaluation (Subtask 2.2), and formulation of a value proposition (Subtask 2.3) for the prospect of ML-enabled, agnostic biodetection from raw, or minimally-processed, datasets.

59 BASIC BIOLOGICAL SCIENCES↗

PRIMED for the Future: Purposing Raw Intake for Machine Learning-Enabled Detection

The COVID-19 pandemic demonstrated how a novel, elusive, and diffuse biological threat can engender uncertainty and misinformation, and it underscored the need for flexible analytical modalities agnostic to the identity of biological material. Yet even before the pandemic recognition of the limitations of the current, list-based approach, which focuses on known pathogens and biotoxins, and of the importance of agent-agnostic biodetection, was growing within the biosecurity community. In a 2018 report on “Biodefense in the Age of Synthetic Biology,” for example, the National Academy of Sciences stated that “an overreliance on the Select Agent List is a systematic weakness affecting many aspects of the United States’ current biodefense mitigation capability." More recently, a group of biodefense researchers proposed the identification and adoption of “bioagent-agnostic signatures (BASs)” as a way of detecting and characterizing not only existing agents but also novel ones, an approach they believe will “enable a more flexible and resilient biodefense posture." Indeed, the future of biodetection requires us to begin developing novel analytics that can identify anomalies and/or characteristics that indicate a potential threat, whether known or unknown, without looking for a specific signature that has been identified previously. To assess potential threats more rapidly, it is critical to develop agnostic artificial intelligence (AI)/machine learning (ML) systems that can be employed for real-time assessment of the nature and source of a perturbation. Such systems should be multiscale and multi-dimensional, integrating sensor data from a range of biological, chemical, and physical application spaces. Emerging deep learning (DL) models demonstrate exceptional promise for identification of discriminatory features within multi-dimensional datasets. DL models have the capacity to recognize and encode highly complex patterns in a wide range of input data modalities, including images, text, and biological/chemical/physical spectra. As such, they can execute a wide range of assessments and determinations that have traditionally required a human operator.

59 BASIC BIOLOGICAL SCIENCES↗

Tradeoffs When Considering Deep Reinforcement Learning for Contingency Management in Advanced Air Mobility

Air transportation is undergoing a rapid evolution globally with the introduction of Advanced Air Mobility (AAM) and with it comes novel challenges and opportunities for transforming aviation. As AAM operations introduce increasing heterogeneity in vehicle capabilities and density, increased levels of automation are likely necessary to achieve operational safety and efficiency goals. This paper focuses on one example where increased automation has been suggested. Autonomous operations will need contingency management systems that can monitor evolving risk across a span of interrelated (or interdependent) hazards and, if necessary, execute appropriate control interventions via supervised or automated decision making. Accommodating this complex environment may require automated functions (autonomy) that apply artificial intelligence (AI) techniques that can adapt and respond to a quickly changing environment. This paper explores the use of Deep Reinforcement Learning (DRL) which has shown promising performance in complex and high-dimensional environments where the objective can be constructed as a sequential decision-making problem. An extension of a prior formulation of the contingency management problem as a Markov Decision Process (MDP) is presented and uses a DRL framework to train agents that mitigate hazards present in the simulation environment. A comparison of these learning-based agents and classical techniques is presented in terms of their performance, verification difficulties, and development process.

machine learningautonomous systems; flight simulat↗

Tradeoffs When Considering Deep Reinforcement Learning for Contingency Management in Advanced Air Mobility

Air transportation is undergoing a rapid evolution globally with the introduction of Advanced Air Mobility (AAM) and with it comes novel challenges and opportunities for transforming aviation. As AAM operations introduce increasing heterogeneity in vehicle capabilities and density, increased levels of automation are likely necessary to achieve operational safety and efficiency goals. This paper focuses on one example where increased automation has been suggested. Autonomous operations will need contingency management systems that can monitor evolving risk across a span of interrelated (or interdependent) hazards and, if necessary, execute appropriate control interventions via supervised or automated decision making. Accommodating this complex environment may require automated functions (autonomy) that apply artificial intelligence (AI) techniques that can adapt and respond to a quickly changing environment. This paper explores the use of Deep Reinforcement Learning (DRL) which has shown promising performance in complex and high-dimensional environments where the objective can be constructed as a sequential decision-making problem. An extension of a prior formulation of the contingency management problem as a Markov Decision Process (MDP) is presented and uses a DRL framework to train agents that mitigate hazards present in the simulation environment. A comparison of these learning-based agents and classical techniques is presented in terms of their performance, verification difficulties, and development process.

machine learning↗

Antiviral discovery using sparse datasets by integrating experiments, molecular simulations, and machine learning

Computational methods have demonstrated success in identifying virucidal agents, effectively contributing to the discovery of novel virucidal molecules. In this study, we developed a machine learning (ML) model, trained on a small dataset, to predict inhibitors of human enterovirus 71 (EV71), a pathological agent that causes severe disease in children and immunocompromised adults. Despite the dataset’s limitation, comprising of only 36 compounds tested, our ML framework demonstrated significant predictive capability. Notably, experimental validation revealed that five out of the eight compounds predicted by our model from the Chinese cosmetic material list exhibited virucidal activity. The inhibitor effects displayed by the main active compounds were further confirmed by molecular dynamics simulation. This underscores the potential of our AI-driven approach to bypass data constraints in identifying active molecules against viral pathogens.

60 APPLIED LIFE SCIENCES↗

REDI – Readiness Engine for Data Integration

The Readiness Engine for Data Integration (REDI) is an open-source framework for automating, standardizing, and assessing the process of preparing scientific data for AI training. REDI implements a five-stage pipeline (ingest, preprocess, transform, structure, output) with per-stage provenance instrumentation via Flowcept, domain-aware transformation logic (PII anonymization, regridding, graph encoding, and more), and built-in readiness assessment and validation modes. REDI has been evaluated across climate, proteomics, materials science, and nuclear fusion datasets, demonstrating near-ideal parallel scaling to 100 nodes on OLCF's Frontier system. REDI is deployable as an agent-callable skill in coding environments such as Claude Code and OpenAI Codex, and is complemented by SetGo for FAIR compliance and catalog publication.

Brewer, Wesley [Oak Ridge National Laboratory (ORN↗

From Rules to Reasoning: A Survey of Large Language Model-Based Approaches to Scientific Hypothesis and Idea Generation

Scientific hypothesis generation represents a fundamental challenge in contemporary research due to exponentially expanding literature volumes and increasing disciplinary specialization. Large language models (LLMs) have emerged as transformative tools for automated scientific discovery, moving beyond traditional rule-based and literature-mining approaches. Four paradigmatic approaches define current LLM-driven hypothesis generation: direct prompting and fine-tuning methods, knowledge-enhanced frameworks integrating retrieval-augmented generation (RAG), multi-agent collaborative systems simulating research teams, and reasoning-focused approaches implementing cognitive architectures. Domain-specific applications demonstrate statistical equivalence to human expert performance in social psychology, experimental validation in biomedical research, and near-expert quality in astronomy. Evaluation methodologies encompass human expert assessment, LLM-as-judge frameworks, and comprehensive benchmarking systems. Technical challenges include hallucination management, knowledge integration limitations, and balancing novelty with feasibility. Future directions emphasize hybrid neural-symbolic architectures and sophisticated human-AI collaboration models for responsible scientific discovery acceleration.

AI-driven discovery↗

COX-2/sEH Dual Inhibitor PTUPB Potentiates the Antitumor Efficacy of Cisplatin

Cisplatin-based therapy is highly toxic, but moderately effective in most cancers. Concurrent inhibition of cyclooxygenase-2 (COX-2) and soluble epoxide hydrolase (sEH) results in antitumor activity and has organ-protective effects. The goal of this paper was to determine the antitumor activity of PTUPB, an orally bioavailable COX-2/sEH dual inhibitor, in combination with cisplatin and gemcitabine (GC) therapy. NSG mice bearing bladder cancer patient-derived xenografts were treated with vehicle, PTUPB, cisplatin, GC, or combinations thereof. Mouse experiments were performed with two different PDX models. PTUPB potentiated cisplatin and GC therapy, resulting in significantly reduced tumor growth and prolonged survival. PTUPB plus cisplatin was no more toxic than cisplatin single-agent treatment as assessed by body weight, histochemical staining of major organs, blood counts, and chemistry. The combination of PTUPB and cisplatin increased apoptosis and decreased phosphorylation in the MAPK/ERK and PI3K/AKT/mTOR pathways compared with controls. PTUPB treatment did not alter platinum–DNA adduct levels, which is the most critical step in platinum-induced cell death. The in vitro study using the combination index method showed modest synergy between PTUPB and platinum agents only in 5637 cell line among several cell lines examined. However, PTUPB is very active in vivo by inhibiting angiogenesis. Finally, PTUPB potentiated the antitumor activity of cisplatin-based treatment without increasing toxicity in vivo and has potential for further development as a combination chemotherapy partner.

60 APPLIED LIFE SCIENCES↗

Deep Reinforcement Learning for Residential HVAC Control with Consideration of Human Occupancy

The Artificial Intelligence (AI) development described herein uses model-free Deep Reinforcement Learning (DRL) to minimize energy cost during residential heating, ventilation, and air conditioning (HVAC) operation. Building cooling loads and HVAC operation are difficult to accurately model due to complexity, lack of measurements and data, and model specific performance, so online machine learning is used to allow for real-time readjustment in performance. Energy costs for the multi-zone cooling unit shown in this work are minimized by scheduling on/off commands around dynamic prices. By taking advantage of precooling events that take place when the price is low, the agent is able to reduce operational cost without violating user comfort. The DRL controller was tested in simulation where the learner achieved a 43.89% cost reduction when compared to traditional, fixed-setpoint operation. The system is now ready for the next phase of testing in a live, real-time home environment.

Mckee, Evan↗

Enhancing Cyber Resilience of Networked Microgrids using Vertical Federated Reinforcement Learning

This paper presents a novel federated reinforcement learning (Fed-RL) methodology to inject sufficient resiliency into the operations of the network of microgrids. We consider adversarial actions to the voltage and power control loop reference signals at the grid forming (GFM) inverters in the microgrids which are essential to integrate renewable resources. Therefore, we formulate a resilient reinforcement learning training setup that uses these adversarial injections to generate episodic trajectories and train the RL agents to alleviate their impact on performance. To circumvent the concerns about data-sharing and privacy for different owners of the microgrids in the networked setting, we bring in the aspects of the federated operation to propose novel Fed-RL algorithms. As the dynamics of each microgrid are coupled due to electrical interlinks, the conventional federated RL approaches using decoupled independent environments are not applicable, which leads us to propose a multi-agent vertically federated variation of actor-critic algorithms, namely federated soft actor-critic (FedSAC). We have performed numerical simulations on an IEEE 123-bus benchmark test feeder with three microgrids by creating a customized simulation setup by encapsulating the microgrid dynamic simulations in GridLAB-D/HELICS co-simulation platform with the OpenAI Gym environment and validated the proposed resilient and secured learning methodology.

Artificial Intelligence (AI), reinforcement learni↗

A Scoping Review of Mixed Initiative Visual Analytics in the Automation Renaissance

Artificial agents are increasingly integrated into data analysis workflows, carrying out tasks that were primarily done by humans. Our research explores how the introduction of automation recalibrates the dynamic between humans and automating technology. To explore this question, we conducted a scoping review encompassing twenty years of mixed-initiative visual analytic systems. To describe and contrast the relationship between humans and automation, we developed an integrated taxonomy to delineate the objectives of these mixed-initiative visual analytics tools, how much automation they support, and the assumed roles of humans. Here, we describe our qualitative approach of integrating existing theoretical frameworks with new codes we developed. Our analysis shows that the visualization research literature lacks consensus on the definition of mixed-initiative systems and explores a limited potential of the collaborative interaction landscape between people and automation. Our research provides a scaffold to advance the discussion of human-AI collaboration during visual data analysis. Our integrated taxonomy is available in the form of a web application on https://smonadjemi.github.io/miva.

Monadjemi, Shayan [ORNL] (ORCID:0000000293855969)↗

MSD CoP Webinar: "Generative agents: A new frontier for representing human actors and their behavior in MSD models"

Context: This webinar was hosted by the MultiSector Dynamics Community of Practice (MSD CoP; https://multisectordynamics.org). Talk #1: Behavioral Generative Agents for Energy Operations Presenter: Dr. Cong Chen (Thayer School of Engineering, Dartmouth College) Abstract: Accurately modeling consumer behavior in energy operations remains challenging due to inherent uncertainties, behavioral complexities, and limited empirical data. This talk introduces a novel approach leveraging generative agents--artificial agents powered by large language models--to realistically simulate customer decision-making in dynamic energy operations. Talk #2: Simulating multiple human perspectives in socio-ecological systems using large language models Presenter: Dr. Yongchao Zeng (Institute of Meteorology and Climate Research, Atmospheric Environmental Research (IMK-IFU) of the Karlsruhe Institute of Technology in Germany) Abstract: Understanding socio-ecological systems requires insights from diverse stakeholder perspectives. This talk describes a novel simulation system called HoPeS (Human-oriented Perspective Shifting). HoPeS enables model users to not only explore simulated socio-ecological systems (SESs) from a third-person observer's perspective but also take any of the simulated stakeholder roles, like playing an RPG game. By shifting multiple perspectives, model users can reflect and integrate the situated knowledge learned through the participatory simulation, approximating a more holistic and less biased understanding of SESs. Moderators: Jim Yoon (MSD CoP Human Systems Modeling Working Group Co-Chair); Stefano Galelli (MSD CoP Using AI to Enhance MSD Research Working Group Co-Chair); Patrick M. Reed (MSD CoP Facilitation Team) This webinar was held on: November 13th, 2025 from 12-1 PM EST.

Artificial Intelligence↗

New imidazolidinedione derivatives as antimalarial agents

A series of new N-alky- and N-alkoxy-imidazolidinediones was prepared and assessed for prophylactic and radical curative activities in mouse and Rhesus monkey models. New compounds are generally metabolically stable, weakly active in vitro against Plasmodium falciparum clones (D6 and W2) and in mice infected with Plasmodium berghei sporozoites. Representative compounds 8e and 9c showed good causal prophylactic activity in Rhesus monkeys dosed 30 mg/kg/day for 3 consecutive days by IM, delayed patency for 19-21 days and 54-86 days, respectively, as compared to the untreated control. By oral, 9c showed only marginal activity in causal prophylactic and radical curative tests at 50 mg/kg/day x 3 and 30 mg/kg/day x 7 plus chloroquine 10 mg/kg for 7 days, respectively.

59 BASIC BIOLOGICAL SCIENCES↗

Investigating the Impact of Irrigation on Malaria Vector Larval Habitats and Transmission Using a Hydrology‐Based Model

Abstract A combination of accelerated population growth and severe droughts has created pressure on food security and driven the development of irrigation schemes across sub‐Saharan Africa. Irrigation has been associated with increased malaria risk, but risk prediction remains difficult due to the heterogeneity of irrigation and the environment. While investigating transmission dynamics is helpful, malaria models cannot be applied directly in irrigated regions as they typically rely only on rainfall as a source of water to quantify larval habitats. By coupling a hydrologic model with an agent‐based malaria model for a sugarcane plantation site in Arjo, Ethiopia, we demonstrated how incorporating hydrologic processes to estimate larval habitats can affect malaria transmission. Using the coupled model, we then examined the impact of an existing irrigation scheme on malaria transmission dynamics. The inclusion of hydrologic processes increased the variability of larval habitat area by around two‐fold and resulted in reduction in malaria transmission by 60%. In addition, irrigation increased all habitat types in the dry season by up to 7.4 times. It converted temporary and semi‐permanent habitats to permanent habitats during the rainy season, which grew by about 24%. Consequently, malaria transmission was sustained all‐year round and intensified during the main transmission season, with the peak shifted forward by around 1 month. Lastly, we evaluated the spatiotemporal distribution of adult vectors under the effect of irrigation by resolving habitat heterogeneity. These findings could help larval source management by identifying transmission hotspots and prioritizing resources for malaria elimination planning.

60 APPLIED LIFE SCIENCES↗

Distributed Spacecraft Autonomy - Development of Swarm Autonomy Capability and Scalability for Spacecraft

The Distributed Spacecraft Autonomy project is developing a suite of software tools that enable an operator to command and receive data from a swarm as a single entity, enable a swarm to autonomously coordinate its actions via distributed decision making and reactive closed-loop control, and model swarm behavior in the presence of anomalies or failures. Our use case is the mapping of the electron density of the ionosphere using radio tomography by coordinating the selection of appropriate GPS channels, and by recording Total Electron Count (TEC) measurements. DSA will be demonstrated onboard the NASA Ames Starling mission – a swarm of four small, LEO spacecraft, scheduled to launch in 2021. We will also perform a ground demonstration with simulated and hardware-in-the-loop elements, to validate the tools for controlling swarms of up to 100 assets. The capability to communicate autonomously between the swarm satellites is demonstrated via a sophisticated simulation architecture. Historical Plasmasphere TEC data obtained via dual-band Novatel GPS Receivers are utilized as a representative input dataset for the swarm. The representative TEC data and GPS satellite observability information is fed to the autonomous software package in place of a true real-time ground data collection process. The swarm satellites actively share status updates amongst one another and utilize multi-agent decision making to optimally identify regions of interest in the TEC distribution. The software, aware of the bandwidth limitations of the swarm satellites, prioritizes explorative measurements, which define the range of observability for the satellites, as well as exploitative measurements, which focus on maximizing the observance potential of regions with prolonged, elevated TEC density. The science of this study can ultimately be used to determine the dynamics and coupling of Earth’s magnetosphere, ionosphere, and atmosphere and their response to solar and terrestrial inputs. The findings can be applied to the imaging of critical, transient phenomena in the magnetosphere in later missions. Meanwhile, the swarm autonomy capabilities have far reaching potential in future satellite missions. As an experimental demonstration of the autonomous capabilities of the network, a message is first printed within a core Flight Executive (cFE) application. Two cFE applications that communicate with one another within the same core Flight System (cFS) are shown. Communication between mission applications on the internal cFE bus is extended to utilize Data Distribution Service (DDS) for vehicle-to-vehicle networking. The DDS middleware provides reliable delivery, routing, and topic subscription features over User Datagram Protocol (UDP). Leveraging Linux containerization, a networked set of satellite instances are generated by script to simulate swarm behavior. Swarm commanding and synchronization through the network is demonstrated under various topologies and data-loss conditions. Finally, autonomous swarm scalability from 2 satellites to 100 satellites is shown.

Distributed Autonomy↗

Fenitrothion action at the endocannabinoid system leading to spermatotoxicity in Wistar rats

Organophosphate (OP) compounds as anticholinesterase agents may secondarily act on diverse serine hydrolase targets, revealing unfavorable physiological effects including male reproductive toxicity. The present investigation proposes that fenitrothion (FNT, a major OP compound) acts on the endocannabinoid signaling system in male reproductive organs, thereby leading to spermatotoxicity (sperm deformity, underdevelopment, and reduced motility) in rats. FNT oxon (bioactive metabolite of FNT) preferentially inhibited the fatty acid amide hydrolase (FAAH), an endocannabinoid anandamide (AEA) hydrolase, in the rat cellular membrane preparation from the testis in vitro. Subsequently, male Wistar rats were treated orally with 5 or 10 mg/kg FNT for 9 weeks and the subchronic exposure unambiguously deteriorated sperm motility and morphology. The activity-based protein profiling analysis with a phosphonofluoridate fluorescent probe revealed that FAAH was selectively inhibited among the FNT-treated cellular membrane proteome in testis. Intriguingly, testicular AEA (endogenous substrate of FAAH) levels were elevated along with the FAAH inhibition caused by the subchronic exposure. More importantly, linear regression analyses for the FNT-elicited spermatotoxicity reveal a good correlation between the testicular FAAH activity and morphological indices or sperm motility. Accordingly, the present study proposes that the FNT-elicited spermatotoxicity appears to be related to inhibition of FAAH leading to overstimulation of the endocannabinoid signaling system, which plays crucial roles in spermatogenesis and sperm motility acquirement. - Highlights: • Subchronic exposure to fenitrothion induces spermatotoxicity in rats. • The fatty acid amide hydrolase is a potential target for the spermatotoxicity. • Overstimulation of the endocannabinoid signal possibly leads to the spermatotoxicity.

60 APPLIED LIFE SCIENCES↗