Search NASA⌕ Search

SEARCH · Search NASA

Results for “Large language model”

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 775 records · Page 43

Neural Scaling Laws for Jet Generation

Recently observed empirical scaling laws describe the performance of foundation-type models as three independent key quantities -- dataset size, compute, and model parameters -- are modified. Extracting these scaling laws informs the training of large complex models for which the tuning of hyperparameters in traditional ways is not feasible. This work for the first time explores if scaling laws can also be observed for the task of particle jet generation -- both relevant as a pre-training objective for foundation models and as in-situ simulation by itself. We indeed replicate the key logarithmic scaling law behavior for model-size scaling. Beyond studying the next token prediction validation loss of the generative model, we also study the sliced Wasserstein distance of five physical quantities that are not immediately available to the model during training. Our study shows that this quantity is monotonically related to the next token prediction validation loss, meaning that this loss is indeed a good proxy for the physics performance. For the scaling with dataset size and compute, we observe substantially weaker scaling behavior of both the loss and the sliced Wasserstein distance. We analyze this behavior by introducing the concept of a learnable window, and argue that autoregressive next token prediction on jet constituents exhibits comparatively rapid saturation relative to language-model studies. We discuss possible origins of this behavior, including the stochastic nature of QCD radiation and differences between generative and supervised learning tasks in collider physics.

Amram, Oz [Fermilab]↗

End-to-End Trade-Space Analysis for Designing Constellation

Multipoint measurement missions can provide a significant advancement in science return and this science interest coupled with as many recent technological advances are driving a growing trend in exploring distributed architectures for future NASA missions. Distributed Spacecraft Missions (DSMs) leverage multiple spacecraft to achieve one or more common goals. In particular, a constellation is the most general form of DSM with two or more spacecraft placed into specific orbit(s) for the purpose of serving a common objective (e.g., CYGNSS). Because a DSM architectural trade-space includes both monolithic and distributed design variables, DSM optimization is a large and complex problem with multiple conflicting objectives. Over the last two years, our team has been developing a Trade-space Analysis Tool for Constellations (TAT-C), implemented in common programming languages for pre-Phase A constellation mission analysis. By evaluating alternative mission architectures, TAT-C seeks to minimize cost and maximize performance for pre-defined science goals. This presentation will describe the overall architecture of TAT-C including: a User Interface (UI) at several levels of details and user expertise; Trade-space Search Requests that are created from the Science requirements gathered by the UI and validated by a Knowledge Base; a Knowledge Base to compare the current requests to prior mission concepts to potentially prune the trade-space; a Trade-space Search Iterator which, with inputs from the Knowledge Base, and, in collaboration with the Orbit & Coverage, Reduction & Metrics, and Cost& Risk modules, generates multiple potential architectures and their associated characteristics. TAT-C leverages the use of the Goddard Mission Analysis Tool (GMAT) to compute coverage and ancillary data, modeling orbits to balance accuracy and performance. The current version includes uniform and non-uniform Walker constellations as well as Ad-Hoc and precessing constellations, and its cost model represents an aggregate model consisting of Cost Estimating Relationships (CERs) from widely accepted models. The current GUI automatically generates graphics representing metrics such as average revisit time or coverage as a function of cost. The end-to-end system will be demonstrated as part of the presentation.

Mission Desig↗

Retaining Systems Engineering Model Meaning Through Transformation: Demo 2

Digital engineering strategies typically assume that digital engineering models interoperate seamlessly across the multiple different engineering modeling software applications involved, such as model- based systems engineering (MBSE), mechanical computer-aided design (MCAD), electrical computer-aided design (ECAD), and other engineering modeling applications. The presumption is that the data schema in these modeling software applications are structured in the familiar flat- tabular schema like any other software application. Engineering domain-specific applications (e.g., systems, mechanical, electrical, simulation) are typically designed to solve domain-specific problems, necessarily excluding explicit representations of non-domain information to help the engineer focus on the domain problems (system definition, design, simulation). Such exclusions become problematic in inter-domain information exchange. The obvious assumptions of one domain might not be so obvious to experts in another domain. Ambiguity in domain-specific language can erode the ability to enable different domain modeling applications to interoperate, unless the underlying language is understood and used as the basis for translation from one application to another. The engineering modeling software application industry has struggled for decades to enable these applications to interoperate. Industry standards have been developed, but they have not unified the industry. Why is this? The authors assert that the industry has relied on traditional database integration methods. The basic issue prohibiting successful application integration then is that traditional database-driven integration does not consider the distinct languages of each domain. An engineering models meaning is expressed through the underlying language of that engineering domain. In essence, traditional integration methods do not retain the semantic context (meaning) of the model. The basis of this research stems from the widely held assumption that systems engineering models are (or can be) structured according to the underlying semantic ontology of the model. This assumption can be imagined from two thoughts. 1) Digital systems engineering models are often represented using graph theory (the graph of a complex systems model can contain millions of nodes and edges). When examining the nodes one at a time and following the outbound edges of each node one by one, one can end up with rudimentary statements about the model (i.e., node A relates to node B), as in a semantic graph. 2) Likewise, from the study of natural languages, a sentence can be structured into unambiguous triples of subject-predicate-object within formal and highly expressive semantic ontologies. The rudimentary statements about a systems model discerned with graph theory closely mimic the triples used in the ontologies that try to structure natural languages. In other words, a systems models semantic graph can be (or is) structured into an ontology. Additionally, it is well established in industry that through natural language processing (NLP), which provides the means to create language structures, that computers can interpret ontological graphs. Therefore, the authors hypothesized that if the integrity of the underlying semantic structure of a systems model is retained, the contextual meaning of the model is retained. By structuring system models into the triples of the underlying ontology during the transformation from one MBSE application to another, the authors have provided a proof of the concept that the meaning of a system model can be retained during transformation. The authors assert that this is the missing ingredient in effective systems model-to-model interoperability. ACKNOWLEDGEMENTS The authors would like to thank the FY19 Model Interoperability team members who provided a solid foundation for the FY20 team to leverage: John McCloud, for the work he did to guide us toward the right use of technology that will appropriately discover and manipulate ontologies. Carlos Tafoya, for the work he did to develop an application programming interface (API)/Adapter that would export ontology-based data from GENESYS. Peter Chandler, for the work he did to architect our overall integration solution, with an eye toward the future that would influence a large-scale federated production-level systems engineering digital model ecosystem.

42 ENGINEERING↗

Active Control Evaluation for Spacecraft (ACES)

The Air Force goal is to develop vibration control techniques for large flexible spacecraft by addressing sensor, actuator, and control hardware and dynamic testing. The Active Control Evaluation for Spacecraft (ACES) program will address the Air Force goal by looking at two leading control techniques and implementing them on a structural model of a flexible spacecraft under laboratory testing. The first phase in the ACES program is to review and to assess the High Authority Control/Low Authority Control (HAC/LAC) and Filter accomodated Model Error Sensitivity Suppression (FAMESS) control techniques for testing on the modified VCOSS structure. Appropriate sensors and actuators will be available for use with both techniques; locations will be the same for both techniques. The control actuators will be positioned at the midpoint and free end of the structure. The laser source for the optical sensor is mounted on the feed mast. The beam will be reflected from a mirror on the offset antenna onto the detectors mounted above the shaker table bay. The next phase is to develop an analysis simulation with the control algorithms implemented for dynamics verification. The third phase is to convert the control laws into high level computer language and test them in the NASA-MSFC facility. The final phase is to compile all analytical and test results for performance comparisons.

Pearson, J.↗

Improved Estimates of Pentad Precipitation through the Merging of Independent Precipitation Datasets

Three independent, quasi-global, gridded datasets of precipitation (a rain gauge-based dataset, the satellite-only component of the NASA Integrated Multi-satellitE Retrievals for Global Precipitation Measurement mission [IMERG] Final Run precipitation product, and precipitation estimates derived from NASA Soil Moisture Active Passive [SMAP] soil moisture retrievals), are objectively combined into a single pentad precipitation dataset at 36-km resolution using a unique approach based on extended triple collocation. The quality of each of the four datasets is then evaluated against independent observations. When a global land surface model at 36-km resolution is integrated four times, once utilizing the merged precipitation forcing and once with each of the three contributing datasets, the near-surface soil moisture variations produced with the merged forcing validate best against independent satellite-based soil moisture fields. In addition, the merged dataset is found to be more consistent, relative to each contributor, with estimates of air temperature variations across the globe. The merged dataset thus appears to draw successfully on the complementary strengths of each contributor: the particularly high quality of the rain gauge-based dataset in areas of high gauge density, the more uniform accuracy across the globe of the IMERG data, and the moderate accuracy, particularly in semi-arid regions, of the soil moisture retrieval-based data. Plain Language Summary Obtaining measurements of precipitation across the globe can be challenging. Rain gauges in some ways provide the most accurate measurements, but gauges are absent in many parts of the world, and even where they exist, they only measure precipitation at the gauge itself and therefore may not provide an accurate large-scale average. Satellite-based estimates of precipitation largely overcome these problems, but such data have their own issues, notably a “snapshot” (rather than a time-average) character of the measurements and difficulty associated with interpreting the measured radiances in the presence of complex land surfaces. In the present paper, we use a novel approach to generate a “merged” dataset, one that optimally combines the gauge precipitation information and the satellite-based precipitation information with a third set of estimates derived from soil moisture retrievals. The merged precipitation dataset and each of the three contributors (aggregated here to 5-day averages at a spatial resolution of about 36-km) are then evaluated for consistency with independent geophysical fields. The merged dataset is found to perform best, a clear indication that it takes proper advantage of the complementary strengths of each contributor and, accordingly, that the presented approach for merging the different contributors is indeed viable.

Precipitation↗

Intelligent Systems and Advanced User Interfaces for Design, Operation, and Maintenance of Command Management Systems

Historically Command Management Systems (CMS) have been large, expensive, spacecraft-specific software systems that were costly to build, operate, and maintain. Current and emerging hardware, software, and user interface technologies may offer an opportunity to facilitate the initial formulation and design of a spacecraft-specific CMS as well as a to develop a more generic or a set of core components for CMS systems. Current MOC (mission operations center) hardware and software include Unix workstations, the C/C++ and Java programming languages, and X and Java window interfaces representations. This configuration provides the power and flexibility to support sophisticated systems and intelligent user interfaces that exploit state-of-the-art technologies in human-machine systems engineering, decision making, artificial intelligence, and software engineering. One of the goals of this research is to explore the extent to which technologies developed in the research laboratory can be productively applied in a complex system such as spacecraft command management. Initial examination of some of the issues in CMS design and operation suggests that application of technologies such as intelligent planning, case-based reasoning, design and analysis tools from a human-machine systems engineering point of view (e.g., operator and designer models) and human-computer interaction tools, (e.g., graphics, visualization, and animation), may provide significant savings in the design, operation, and maintenance of a spacecraft-specific CMS as well as continuity for CMS design and development across spacecraft with varying needs. The savings in this case is in software reuse at all stages of the software engineering process.

Mitchell, Christine M.↗

Integrating planning and reactive control

Artificial intelligence research on planning is concerned with designing control systems that choose actions by manipulating explicit descriptions of the world state, the goal to be achieved, and the effects of elementary operations available to the system. Because planning shifts much of the burden of reasoning to the machine, it holds great appeal as a high-level programming method. Experience shows, however, that it cannot be used indiscriminately because even moderately rich languages for describing goals, states, and the elementary operators lead to computational inefficiencies that render the approach unsuitable for realistic applications. This inadequacy has spawned a recent wave of research on reactive control or situated activity in which control systems are modeled as reacting directly to the current situation rather than as reasoning about the future effects of alternative action sequences. While this research has confronted the issue of run-time tractability head on, in many cases it has done so by sacrificing the advantages of declarative planning techniques. Ways in which the two approaches can be unified are discussed. The authors begin by modeling reactive control systems as state machines that map a stream of sensory inputs to a stream of control outputs. These machines can be decomposed into two continuously active subsystems: the planner and the execution module. The planner computes a plan, which can be seen as a set of bits that control the behavior of the execution module. An important element of this work is the formulation of a precise semantic interpretation for the inputs and outputs of the planning system. They show that the distinction between planned and reactive behavior is largely in the eye of the beholder: systems that seem to compute explicit plans can be redescribed in situation-action terms and vice versa. They also discuss practical programming techniques that allow the advantages of declarative programming and guaranteed reactive response to be achieved simultaneously.

Rosenschein, Stanley J.↗

Development of neural network force fields for corrosion studies

To fully understand the chemistry and physics of corrosion, novel methods of simulation must be developed. One approach is designing machine learning (ML) algorithms integrated with density functional theory to develop adaptive force fields to gain insight into corrosion behavior namely at the surface of metal oxides. Current methods of modeling corrosion are slow due to the computational cost of resolving both reaction mechanics and mass transport processes. Machine learning methods can be implemented to obtain structure-activity relationships at both the molecular and bulk scale while still retaining the accuracy of density functional theory (DFT) and significantly decreasing the time needed for simulations of complex chemical processes in the various environments of corrosion. Multiscale models are needed for corrosion studies to fully understand its processes not only at the atomic length scale (chemical bonding, energies, and forces), but also at the nano and meso length scales (solid-state physics and material science processes). Current methods of study include DFT, molecular dynamics, and Monte Carlo. The limitation of DFT is that only a small number of atoms or molecules can be simulated at that level of theory. Density functional theory is used to study the electronic structure of atoms and molecules, and calculate the force component of each atom. However, these calculations are limited to about 1000 atoms. Custom periodic boundary conditions (PBC) can be used to describe the various environments and defects that affect the atomic forces to produce a large data set from which a training set can be derived. Machine learning can be utilized to overcome the barrier of modeling macroscopic and multi-scale processes from ab initio calculations through the development of adaptive force fields. Local environments determine the atomic forces of a given system, therefore adaptive force fields must be created to produce reliable quantum mechanical calculations. This can be achieved by developing a learning algorithm that uses the mapped atomic forces or fingerprint as an input to produce energies and magnetic moments as output. A systematic approach was used to begin to build a data set in order to accurately describe the atomic forces in various environments. In Figure 4 below, a simple PBC cell of Fe{sub 2}O{sub 3} was first optimized. A surface optimization was performed next, followed by a hydroxylated surface optimization. Once this calculation has converged, the adsorption of halide species to the hydroxylated surface will be investigated. TensorFlow is an open source platform for machine learning developed by Google. Using a high level application program interface (API) such as Keras allows for building and training ML models easily in a number of different environments and languages. For this project, a neural network was developed within Anaconda in Python. Future Work: Further development of reference data set; Refining neural network and learning algorithm; Fingerprinting atomic environment to enable mapping of atomic force components; Choosing appropriate training set from reference data; Learning from training set and enabling non-linear mapping of training set fingerprints and the atomic forces; Estimation of uncertainty to identify ranges of outside applicability; Testing and analysis of molecular dynamic simulations.

36 MATERIALS SCIENCE↗

Advanced information processing system: The Army Fault-Tolerant Architecture detailed design overview

The Army Avionics Research and Development Activity (AVRADA) is pursuing programs that would enable effective and efficient management of large amounts of situational data that occurs during tactical rotorcraft missions. The Computer Aided Low Altitude Night Helicopter Flight Program has identified automated Terrain Following/Terrain Avoidance, Nap of the Earth (TF/TA, NOE) operation as key enabling technology for advanced tactical rotorcraft to enhance mission survivability and mission effectiveness. The processing of critical information at low altitudes with short reaction times is life-critical and mission-critical necessitating an ultra-reliable/high throughput computing platform for dependable service for flight control, fusion of sensor data, route planning, near-field/far-field navigation, and obstacle avoidance operations. To address these needs the Army Fault Tolerant Architecture (AFTA) is being designed and developed. This computer system is based upon the Fault Tolerant Parallel Processor (FTPP) developed by Charles Stark Draper Labs (CSDL). AFTA is hard real-time, Byzantine, fault-tolerant parallel processor which is programmed in the ADA language. This document describes the results of the Detailed Design (Phase 2 and 3 of a 3-year project) of the AFTA development. This document contains detailed descriptions of the program objectives, the TF/TA NOE application requirements, architecture, hardware design, operating systems design, systems performance measurements and analytical models.

Harper, Richard E.↗

Intelligent systems and advanced user interfaces for design, operation, and maintenance of command management systems

Historically, command management systems (CMS) have been large and expensive spacecraft-specific software systems that were costly to build, operate, and maintain. Current and emerging hardware, software, and user interface technologies may offer an opportunity to facilitate the initial formulation and design of a spacecraft-specific CMS as well as to develop a more generic CMS system. New technologies, in addition to a core CMS common to a range of spacecraft, may facilitate the training and enhance the efficiency of CMS operations. Current mission operations center (MOC) hardware and software include Unix workstations, the C/C++ programming languages, and an X window interface. This configuration provides the power and flexibility to support sophisticated and intelligent user interfaces that exploit state-of-the-art technologies in human-machine interaction, artificial intelligence, and software engineering. One of the goals of this research is to explore the extent to which technologies developed in the research laboratory can be productively applied in a complex system such as spacecraft command management. Initial examination of some of these issues in CMS design and operation suggests that application of technologies such as intelligent planning, case-based reasoning, human-machine systems design and analysis tools (e.g., operator and designer models), and human-computer interaction tools (e.g., graphics, visualization, and animation) may provide significant savings in the design, operation, and maintenance of the CMS for a specific spacecraft as well as continuity for CMS design and development across spacecraft. The first six months of this research saw a broad investigation by Georgia Tech researchers into the function, design, and operation of current and planned command management systems at Goddard Space Flight Center. As the first step, the researchers attempted to understand the current and anticipated horizons of command management systems at Goddard. Preliminary results are given on CMS commonalities and causes of low re-use, and methods are proposed to facilitate increased re-use.

Potter, William J.↗

High Performance Parallel Computational Nanotechnology

At a recent press conference, NASA Administrator Dan Goldin encouraged NASA Ames Research Center to take a lead role in promoting research and development of advanced, high-performance computer technology, including nanotechnology. Manufacturers of leading-edge microprocessors currently perform large-scale simulations in the design and verification of semiconductor devices and microprocessors. Recently, the need for this intensive simulation and modeling analysis has greatly increased, due in part to the ever-increasing complexity of these devices, as well as the lessons of experiences such as the Pentium fiasco. Simulation, modeling, testing, and validation will be even more important for designing molecular computers because of the complex specification of millions of atoms, thousands of assembly steps, as well as the simulation and modeling needed to ensure reliable, robust and efficient fabrication of the molecular devices. The software for this capacity does not exist today, but it can be extrapolated from the software currently used in molecular modeling for other applications: semi-empirical methods, ab initio methods, self-consistent field methods, Hartree-Fock methods, molecular mechanics; and simulation methods for diamondoid structures. In as much as it seems clear that the application of such methods in nanotechnology will require powerful, highly powerful systems, this talk will discuss techniques and issues for performing these types of computations on parallel systems. We will describe system design issues (memory, I/O, mass storage, operating system requirements, special user interface issues, interconnects, bandwidths, and programming languages) involved in parallel methods for scalable classical, semiclassical, quantum, molecular mechanics, and continuum models; molecular nanotechnology computer-aided designs (NanoCAD) techniques; visualization using virtual reality techniques of structural models and assembly sequences; software required to control mini robotic manipulators for positional control; scalable numerical algorithms for reliability, verifications and testability. There appears no fundamental obstacle to simulating molecular compilers and molecular computers on high performance parallel computers, just as the Boeing 777 was simulated on a computer before manufacturing it.

Saini, Subhash↗

Plant-Level Modeling and Simulation of Used Nuclear Fuel Dissolution

Plant-level modeling and simulation of a used nuclear fuel prototype dissolver is presented. Emphasis is given in developing a modeling and simulation approach to be explored by other processes involved in the recycle of used fuel. The commonality concepts presented in a previous communication were used to create a model and realize its software module. An initial model was established based on a theory of chemical thermomechanical network transport outlined previously. A software module prototype was developed with the required external behavior and internal mathematical structure. Results obtained demonstrate the generality of the design approach and establish an extensible mathematical model with its corresponding software module for a wide range of dissolvers. Scale up numerical tests were made varying the type of used fuel (breeder and light-water reactors) and the capacity of dissolution (0.5 t/d to 1.7 t/d). These tests were motivated by user requirements in the area of nuclear materials safeguards. A computer module written in high-level programing languages (MATLAB and Octave) was developed, tested, and provided as open-source code (MATLAB) for integration into the Separations and Safeguards Performance Model application in development at Sandia National Laboratories. The modeling approach presented here is intended to serve as a template for a rational modeling of all plant-level modules. This will facilitate the practical application of the commonality features underlying the unifying network transport theory proposed recently. In addition, by example, this model describes, explicitly, the needed data from sub-scale models, and logical extensions for future model development. For example, from thermodynamics, an off-line simulation of molecular dynamics could quantify partial molar volumes for the species in the liquid phase; this simulation is currently at reach for high-performance computing. From fluid mechanics, a hold-up capacity function is needed for the dissolver device; this simulation is currently at reach for computational fluid mechanics given the existing CAD geometry. From chemical transport phenomena, a simulation of the particle-scale dissolution front is needed to derive an improved solid dissolution kinetics law by predicting the local surface area change; an example was provided in this report. In addition, the associated reaction mechanisms for dissolution are presently largely untested and simplified, hence even a parallel experimental program in reaction kinetics is needed to support modeling and simulation efforts. Last but not least, a simple account of finite rates of solid feed and transfer can be readily introduced via a coupled delayed model. These are some of the theoretical benefits of a rational plant-level modeling approach which guides the development of smaller length and time scale modeling. Practical, and other theoretical benefits have been presented on a previous report.

11 NUCLEAR FUEL CYCLE AND FUEL MATERIALS↗

An Algorithm to Atmospherically Correct Visible and Thermal Airborne Imagery

The program Watts implements a system of physically based models developed by the authors, described elsewhere, for the removal of atmospheric effects in multispectral imagery. The band range we treat covers the visible, near IR and the thermal IR. Input to the program begins with atmospheric pal red models specifying transmittance and path radiance. The system also requires the sensor's spectral response curves and knowledge of the scanner's geometric definition. Radiometric characterization of the sensor during data acquisition is also necessary. While the authors contend that active calibration is critical for serious analytical efforts, we recognize that most remote sensing systems, either airborne or space borne, do not as yet attain that minimal level of sophistication. Therefore, Watts will also use semi-active calibration where necessary and available. All of the input is then reduced to common terms, in terms of the physical units. From this it Is then practical to convert raw sensor readings into geophysically meaningful units. There are a large number of intricate details necessary to bring an algorithm or this type to fruition and to even use the program. Further, at this stage of development the authors are uncertain as to the optimal presentation or minimal analytical techniques which users of this type of software must have. Therefore, Watts permits users to break out and analyze the input in various ways. Implemented in REXX under OS/2 the program is designed with attention to the probability that it will be ported to other systems and other languages. Further, as it is in REXX, it is relatively simple for anyone that is literate in any computer language to open the code and modify to meet their needs. The authors have employed Watts in their research addressing precision agriculture and urban heat island.

Rickman, Doug L.↗

Earth Independent Medical Operations (EIMO) Datascope: Challenges and Potential Solutions

Data flows and storage/retrieval capacity are severely constrained during missions in space and challenges will become even greater during exploration class missions. There is a need for an artificial intelligence (AI)-based clinical decision support system (CDSS) to monitor and analyze data to provide real-time consultative support for crew medical officer (CMO) decision-making. EIMO is defined as the gradual transition of medical care and decision making from terrestrial to space-based assets, enabling support of astronaut health and performance and reducing overall mission risk. While a hallmark of this paradigm shift from low-earth orbit is that on-board care will increasingly become the responsibility of the astronauts for primary management and decision making, terrestrial assets will continue to be paramount in pre-mission screening and planning, as well as prevention, health maintenance and long-term care contingencies. New capabilities and systems that enable progressively more robust and resilient systems and crews will be necessary to reduce risk and increase probability of deep space exploration mission success. An aspiration for EIMO is to develop AI-enhanced solutions for analysis of crew health & performance data and to facilitate clinical decision support for autonomous medical operations. A “system of systems” approach is envisioned whereby EIMO will deploy AI-supported natural language processing and machine learning (ML) techniques to utilize embedded reference databases and real-time data streams [input vectors] from multiple data sources. Constituent input vectors may include environmental controls, countermeasures data, behavioral data, physiologic wearables, point-of-care laboratory tests, personalized medical records, inventory trade space risk assessments, COTS medical databases, and ground support inputs. An ideal AI capability would possess trained fusion algorithms to cross reference input vectors with medical ‘knowledge’ [cultivated database] to stratify relevant data streams for predictive and actionable capabilities. In addition, EIMO will feature mobility, in that it can be accessed and can push/pull data within and between multiple vehicles/habitats. Large amounts and variable sources of data can be leveraged to diagnose, inform treatment strategies, and potentially predict medical events and performance decrements. Inclusion of advanced training tools using extended reality will enable increasingly autonomous medical care to aid a CMO when ground support is unavailable or time-delayed beyond required action window, e.g., emergent medical situations. EIMO CDSS would require very large datasets to train pre-flight and significant amounts of data are needed to support ML via in-flight CDSS operations. An additional challenge will be to find sufficient data to train a model relevant to astronaut demographics. The rapid, accelerating evolution of this field creates a propitious solution space to leverage multi-modal AI through public-private partnership(s). The status of multi-modal AI systems today would preclude their use for long duration missions as they remain unreliable and are subject to “digital hallucinations” and other errors that could pose operational risk. A federated labs structure is being considered to test and optimize data flow from the multiple input vectors leading to field testing in suitable ground/flight analogs. Critical to the success of an EIMO CDSS will be integration and interoperability and success will be defined by a system that can serve as an in-flight medical consult for the CMO providing critical support during medical contingencies. Benefits to terrestrial medicine may be significant as an outflow of the EIMO medical system, particularly for remote areas and communities lacking significant infrastructure, personnel and resources.

J Lemery↗

Earth Independent Medical Operations (EIMO) Datascope: Challenges and Potential Solutions

Data flows and storage/retrieval capacity are severely constrained during missions in space and challenges will become even greater during exploration class missions. There is a need for an artificial intelligence (AI)-based clinical decision support system (CDSS) to monitor and analyze data to provide real-time consultative support for crew medical officer (CMO) decision-making. EIMO is defined as the gradual transition of medical care and decision making from terrestrial to space-based assets, enabling support of astronaut health and performance and reducing overall mission risk. While a hallmark of this paradigm shift from low-earth orbit is that on-board care will increasingly become the responsibility of the astronauts for primary management and decision making, terrestrial assets will continue to be paramount in pre-mission screening and planning, as well as prevention, health maintenance and long-term care contingencies. New capabilities and systems that enable progressively more robust and resilient systems and crews will be necessary to reduce risk and increase probability of deep space exploration mission success. An aspiration for EIMO is to develop AI-enhanced solutions for analysis of crew health & performance data and to facilitate clinical decision support for autonomous medical operations. A “system of systems” approach is envisioned whereby EIMO will deploy AI-supported natural language processing and machine learning (ML) techniques to utilize embedded reference databases and real-time data streams [input vectors] from multiple data sources. Constituent input vectors may include environmental controls, countermeasures data, behavioral data, physiologic wearables, point-of-care laboratory tests, personalized medical records, inventory trade space risk assessments, COTS medical databases, and ground support inputs. An ideal AI capability would possess trained fusion algorithms to cross reference input vectors with medical ‘knowledge’ [cultivated database] to stratify relevant data streams for predictive and actionable capabilities. In addition, EIMO will feature mobility, in that it can be accessed and can push/pull data within and between multiple vehicles/habitats. Large amounts and variable sources of data can be leveraged to diagnose, inform treatment strategies, and potentially predict medical events and performance decrements. Inclusion of advanced training tools using extended reality will enable increasingly autonomous medical care to aid a CMO when ground support is unavailable or time-delayed beyond required action window, e.g., emergent medical situations. EIMO CDSS would require very large datasets to train pre-flight and significant amounts of data are needed to support ML via in-flight CDSS operations. An additional challenge will be to find sufficient data to train a model relevant to astronaut demographics. The rapid, accelerating evolution of this field creates a propitious solution space to leverage multi-modal AI through public-private partnership(s). The status of multi-modal AI systems today would preclude their use for long duration missions as they remain unreliable and are subject to “digital hallucinations” and other errors that could pose operational risk. A federated labs structure is being considered to test and optimize data flow from the multiple input vectors leading to field testing in suitable ground/flight analogs. Critical to the success of an EIMO CDSS will be integration and interoperability and success will be defined by a system that can serve as an in-flight medical consult for the CMO providing critical support during medical contingencies. Benefits to terrestrial medicine may be significant as an outflow of the EIMO medical system, particularly for remote areas and communities lacking significant infrastructure, personnel and resources.

Medical Operations↗

Status on the Component Models Developed in the Modelica Framework: High-Temperature Steam Electrolysis Plant & Gas Turbine Power Plant

This report has been prepared as part of an effort to design and build a modeling and simulation (M&S) framework to assess the economic viability of a nuclear-renewable hybrid energy system (N-R HES). In order to facilitate dynamic M&S of such an integrated system, research groups in multiple national laboratories have been developing various subsystems as dynamic physics-based components using the Modelica programming language. In fiscal year (FY) 2015, Idaho National Laboratory (INL) performed a dynamic analysis of two region-specific N-R HES configurations, including the gas-to-liquid (natural gas to Fischer-Tropsch synthetic fuel) and brackish water reverse osmosis desalination plants as industrial processes. In FY 2016, INL has developed two additional subsystems in the Modelica framework: a high-temperature steam electrolysis (HTSE) plant and a gas turbine power plant (GTPP). HTSE has been proposed as a high priority industrial process to be integrated with a light water reactor (LWR) in an N-R HES. This integrated energy system would be capable of dynamically apportioning thermal and electrical energy (1) to provide responsive generation to the power grid and (2) to produce alternative industrial products (i.e., hydrogen and oxygen) without generating any greenhouse gases. A dynamic performance analysis of the LWR/HTSE integration case was carried out to evaluate the technical feasibility (load-following capability) and safety of such a system operating under highly variable conditions requiring flexible output. To support the dynamic analysis, the detailed dynamic model and control design of the HTSE process, which employs solid oxide electrolysis cells, have been developed to predict the process behavior over a large range of operating conditions. As first-generation N-R HES technology will be based on LWRs, which provide thermal energy at a relatively low temperature, complementary temperature-boosting technology was suggested for integration with the HTSE process that requires higher temperature input. Simulation results involving several case studies show that the suggested control scheme could maintain the controlled variables (including the steam utilization factor, cathode stream inlet composition, and temperatures of the process streams at various locations) within desired limits under various plant operating conditions. The results also indicate that the proposed HTSE plant could provide operational flexibility to participate in energy management at the utility scale by dynamically optimizing the use of excess plant capacity within an N-R HES. A natural-gas fired GTPP has been proposed as a secondary energy supply to be included in an N-R HES. This auxiliary generator could be used to cover rapid dynamics in grid demand that cannot be met by the remainder of the N-R HES. To evaluate the operability and controllability of the proposed process during transients between load (demand) levels, the dynamic model and control design were developed. Special attention was given to the design of feedback controllers to regulate the power frequency, and exhaust gas and turbine firing temperatures. Several case studies were performed to investigate the system responses to the major disturbance (power load demand) in such a control system. The simulation results show that the performance of the proposed control strategies was satisfactory under each test when the GTPP experienced high rapid variations in the load.

08 HYDROGEN↗

A Hybrid Approach to Labeling Datasets in Earth Science Publications

NASA Data Centers provide the public with thousands of datasets that result in published papers, reports, and conference proceedings. Collecting accurate metrics on usage of these datasets is key to connecting different areas of knowledge and evaluating the datasets’ impact. While most of the datasets have Digital Object Identifiers (DOIs) assigned, most publications do not cite them hampering the automated search of these publications. Instead, articles mention attributes like organization, instrument, mission, variable, or a publication describing the dataset. Often only domain experts can deduce the dataset that was used in the publication text. The lack of a citation slows the spread of information and reduces the research’s impact. With thousands of papers produced each year, an automated means of labeling datasets is critical. This paper explores a hybrid approach of heuristics and a Natural Language Processing (NLP) Named Entity Recognition (NER) model to find and label the datasets used within Earth Science papers. Heuristics are used to produce the labelled sentences and any potential dataset candidates that can be derived from a sentence. The heuristic labels the sentences with the names of mission, instrument, re-analysis models, and science keywords taken from the Global Change Master Directory (GCMD) ontology. Additionally, it uses those labels to generate the dataset citation candidates. If the mission, instrument, and variable are sufficient to create the citation for the dataset the citation and the label the domain expert reviews the output without going through the NLP model. If the extracted label is not sufficient to label the dataset on its own, the sentence and its associated dataset labels will be inputted into the NER model. The model outputs the labeled sentence and the potential dataset candidates with their associated probabilities. The domain expert then reviews the NER model’s output and the correct labels are determined. The newly labelled papers can then be used as additional training data. This creates an iterative process for the approach to continuously improve. Because all the possible mentions are gathered by the model, the domain expert can quickly and easily label the papers resulting in large time savings.

Jacob Atkins↗

General Mission Analysis Tool (GMAT) Architectural Specification. Draft

Early in 2002, Goddard Space Flight Center (GSFC) began to identify requirements for the flight dynamics software needed to fly upcoming missions that use formations of spacecraft to collect data. These requirements ranged from low level modeling features to large scale interoperability requirements. In 2003 we began work on a system designed to meet these requirement; this system is GMAT. The General Mission Analysis Tool (GMAT) is a general purpose flight dynamics modeling tool built on open source principles. The GMAT code is written in C++, and uses modern C++ constructs extensively. GMAT can be run through either a fully functional Graphical User Interface (GUI) or as a command line program with minimal user feedback. The system is built and runs on Microsoft Windows, Linux, and Macintosh OS X platforms. The GMAT GUI is written using wxWidgets, a cross platform library of components that streamlines the development and extension of the user interface Flight dynamics modeling is performed in GMAT by building components that represent the players in the analysis problem that is being modeled. These components interact through the sequential execution of instructions, embodied in the GMAT Mission Sequence. A typical Mission Sequence will model the trajectories of a set of spacecraft evolving over time, calculating relevant parameters during this propagation, and maneuvering individual spacecraft to maintain a set of mission constraints as established by the mission analyst. All of the elements used in GMAT for mission analysis can be viewed in the GMAT GUI or through a custom scripting language. Analysis problems modeled in GMAT are saved as script files, and these files can be read into GMAT. When a script is read into the GMAT GUI, the corresponding user interface elements are constructed in the GMAT GUI. The GMAT system was developed from the ground up to run in a platform agnostic environment. The source code compiles on numerous different platforms, and is regularly exercised running on Windows, Linux and Macintosh computers by the development and analysis teams working on the project. The system can be run using either a graphical user interface, written using the open source wxWidgets framework, or from a text console. The GMAT source code was written using open source tools. GSFC has released the code using the NASA open source license.

Hughes, Steven P.↗