Results for “Training Time” — Page 72

NASA NTRS1994

Neural Network Classifies Teleoperation Data

Prototype artificial neural network, implemented in software, identifies phases of telemanipulator tasks in real time by analyzing feedback signals from force sensors on manipulator hand. Prototype is early, subsystem-level product of continuing effort to develop automated system that assists in training and supervising human control operator: provides symbolic feedback (e.g., warnings of impending collisions or evaluations of performance) to operator in real time during successive executions of same task. Also simplifies transition between teleoperation and autonomous modes of telerobotic system.

Fiorini, Paolo↗

NASA NTRSDate not supplied

Crew Time Requirements in Future Space Greenhouses - What Can We Infer from Current Analog and Space Missions?

Efficient crop production will be required to advance humanity’s presence in space, and for this, accurate predictions of crew time in future space greenhouse modules will be crucial to design and operate these plant growth systems, and schedule crop production. Crew time estimates will also be critical for deciding priorities of automating different aspects of space crop production. Because it is difficult to capture in operational environments, crew time for plant cultivation has only been sporadically recorded in past analog and space missions. We propose a methodology for efficient categorizing and reporting of crew time in space plant growth systems: first identify the different tasks needed to operate the greenhouse module, second define a representative time period for data collection, third accurately report crew time for individual tasks - and their occurrence, and fourth use collected data to improve greenhouse modules and plant growth system designs. Using data from various analog facilities and from the Veggie hardware on ISS, and assumptions for different mission scenarios, we discuss how crew time for plant cultivation can be reduced with adequate choices of crops, automation, artificial intelligence (AI) and virtual assistants, and sufficient crew training. This has major implications for the design of future space greenhouse modules. For example, missions on future space stations or during interplanetary travel would save significant crew time by including leafy greens and microgreens for astronaut’s diet supplement, with automated watering, health and environmental checks, as well as AI managing maintenance schedules, and a virtual assistant for repair activities. This work was funded by NASA Space Biology through NASA postdoctoral program / USRA, by NASA’s Space Biology and Human Research Programs, and by the European Union Horizon 2020 program via the COMPET-07-2014 - Space exploration – Life-support subprogram (reference number: 636501).

Lucie Poulet↗

NASA NTRSDate not supplied

Crew Time Requirements in Future Space Greenhouses: What Can We Infer from Current Analog and Space Missions?

Efficient crop production will be required to advance humanity’s presence in space, and for this, accurate predictions of crew time in future space greenhouse modules will be crucial to design and operate these plant growth systems, and schedule crop production. Crew time estimates will also be critical for deciding priorities of automating different aspects of space crop production. Because it is difficult to capture in operational environments, crew time for plant cultivation has only been sporadically recorded in past analog and space missions. We propose a methodology for efficient categorizing and reporting of crew time in space plant growth systems: first identify the different tasks needed to operate the greenhouse module, second define a representative time period for data collection, third accurately report crew time for individual tasks - and their occurrence, and fourth use collected data to improve greenhouse modules and plant growth system designs. Using data from various analog facilities and from the Veggie hardware on ISS, and assumptions for different mission scenarios, we discuss how crew time for plant cultivation can be reduced with adequate choices of crops, automation, artificial intelligence (AI) and virtual assistants, and sufficient crew training. This has major implications for the design of future space greenhouse modules. For example, missions on future space stations or during interplanetary travel would save significant crew time by including leafy greens and microgreens for astronaut’s diet supplement, with automated watering, health and environmental checks, as well as AI managing maintenance schedules, and a virtual assistant for repair activities. This work was funded by NASA Space Biology through NASA postdoctoral program / USRA, by NASA’s Space Biology and Human Research Programs, and by the European Union Horizon 2020 program via the COMPET-07-2014 - Space exploration – Life-support subprogram (reference number: 636501).

Veggie↗

NASA NTRSDate not supplied

Achieving Resilient In-Flight Performance for Advanced Air Mobility through Simplified Vehicle Operations

A research and development (R&D) approach is proposed for developing and validating concepts and technologies to achieve vehicle autonomy goals of Advanced Air Mobility (AAM) through Simplified Vehicle Operations (SVO). The approach applies resilience-engineering and human-automation teaming (HAT) principles to a framework for defining vehicle-based functions for the management of missions and flight trajectories, focusing initially on the en route flight domain. To achieve the SVO goal of reducing pilot training requirements and thereby increasing the pilot pool for AAM, while at the same time promoting ever-safer operations, a framework for identifying essential functions is proposed. In this framework, functions are first categorized by high-level functional purpose (mission management, flightpath management, tactical operations, and vehicle control) and then subcategorized by attributes of resilient-performing systems (abilities to monitor, respond, learn, and anticipate). The categorization by functional purpose provides structure within which HAT designs can be holistically explored and total levels of human vs. automation responsibility can be varied. The subcategorization by resilient-system attributes provides a mechanism for capturing safety-critical functions that may not be codified in current operational procedures and training curricula, particularly those where humans proactively enhance safety in currently undocumented ways. An R&D approach consisting of seven strategies is proposed in which automation engineering and human-factors communities can collaborate in the research, development, and design of an SVO roadmap to enable the ambitious objectives of AAM.

AAM↗

DOE OSTI2026

Machine learning approach for vibronically renormalized electronic band structures

Here, we present a machine learning (ML) method for efficient computation of vibrational thermal expectation values of physical properties from first principles. Our approach is based on the nonperturbative frozen phonon formulation in which stochastic Monte Carlo algorithm is employed to sample configurations of nuclei in a supercell at finite temperatures based on a first-principles phonon model. A deep-learning neural network is trained to accurately predict physical properties associated with sampled phonon configurations, thus bypassing the time-consuming ab initio calculations. To incorporate the point-group symmetry of the electronic system into the ML model, group-theoretical methods are used to develop a symmetry-invariant descriptor for phonon configurations in the supercell. We apply our ML approach to compute the temperature dependent electronic energy gap of silicon based on density functional theory (DFT). We show that, with less than a hundred DFT calculations for training the neural network model, an order of magnitude larger number of sampling can be achieved for the computation of the vibrational thermal expectation values. Our work highlights the promising potential of ML techniques for finite temperature first-principles electronic structure methods.

75 CONDENSED MATTER PHYSICS, SUPERCONDUCTIVITY AND↗

DOE OSTI2020

Machine Learning-Based PV Reserve Determination Strategy for Frequency Control on the WECC System

Frequency control from photovoltaic (PV) power plants has great potential to address the frequency response challenge of the power system with high penetrations of renewable generation. Using model-based approaches to determine the optimal PV headroom reserve, however, requires significant online computation and is intractable for an interconnection level system. This paper proposes a machine learning based strategy, that is suitable for real-time operation, to determine the optimal PV reserve for frequency control. The proposed machine learning algorithm is trained and tested on 1,987 offline simulations of a 60% renewable penetration Western Electricity Coordinating Council (WECC) system. Furthermore, the proposed reserve determination strategy is applied on a realistic 1-day operation profile of the WECC system and demonstrates a savings of more than 40% PV headroom compared to a conservative approach. It is evident that the proposed strategy can efficiently and effectively determine the optimal PV frequency control reserve for realistic interconnection systems.

frequency control↗

DOE OSTI2022

Data-Driven and Multiscale Modeling of DNA-Templated Dye Aggregates

Dye aggregates are of interest for excitonic applications, including biomedical imaging, organic photovoltaics, and quantum information systems. Dyes with large transition dipole moments (μ) are necessary to optimize coupling within dye aggregates. Extinction coefficients (ε) can be used to determine the μ of dyes, and so dyes with a large ε (>150,000 M –1 cm –1 ) should be engineered or identified. However, dye properties leading to a large ε are not fully understood, and low-throughput methods of dye screening, such as experimental measurements or density functional theory (DFT) calculations, can be time-consuming. In order to screen large datasets of molecules for desirable properties (i.e., large ε and μ), a computational workflow was established using machine learning (ML), DFT, time-dependent (TD-) DFT, and molecular dynamics (MD). ML models were developed through training and validation on a dataset of 8802 dyes using structural features. A Classifier was developed with an accuracy of 97% and a Regressor was constructed with an R2 of above 0.9, comparing between experiment and ML prediction. Using the Regressor, the ε values of over 18,000 dyes were predicted. The top 100 dyes were further screened using DFT and TD-DFT to identify 15 dyes with a μ relative to a reference dye, pentamethine indocyanine dye Cy5. Two benchmark MD simulations were performed on Cy5 and Cy5.5 dimers, and it was found that MD could accurately capture experimental results. The results of this study exhibit that our computational workflow for identifying dyes with a large μ for excitonic applications is effective and can be used as a tool to develop new dyes for excitonic applications.

77 NANOSCIENCE AND NANOTECHNOLOGY↗

DOE OSTI2025

A physics-constrained neural ordinary differential equations approach for robust learning of stiff chemical kinetics

The high computational cost associated with solving for detailed chemistry poses a significant challenge for predictive computational fluid dynamics (CFD) simulations of turbulent reacting flows. While deep learning techniques have been explored to develop faster surrogate models, they often fail to integrate reliably with CFD solvers. This instability arises because traditional deep learning approaches optimize for training error without ensuring compatibility with ordinary differential equation (ODE) solvers, resulting in accumulation of errors over time. Recently, neuralODE (NODE) based approaches have been shown to be a promising technique to emulate and accelerate detailed chemistry computations. Here, in the present work, we extend this NODE framework for stiff chemical kinetics by incorporating mass conservation constraints directly into the loss function during training. This ensures that the total mass as well as the individual elemental species masses are conserved in an a-posteriori manner. Proof-of-concept studies are performed with the novel physics-constrained NODE (PC-NODE) approach for homogeneous autoignition of hydrogen-air mixture over a range of composition and thermodynamic conditions. It is demonstrated that the PC-NODE framework not only improves the physical consistency of the resulting data-driven model with respect to mass conservation criteria, but also improves training efficiency. PC-NODE is shown to achieve 2–100× speedup relative to the hydrogen-air detailed chemical mechanism depending on the type of the ODE solver (implicit or explicit) used during autoregressive inference tests. Lastly, a-posteriori studies are performed wherein the trained PC-NODE model is coupled with a CFD solver. It is shown that higher accuracy is achieved with PC-NODE relative to the purely data-driven NODE approach. Moreover, PC-NODE also exhibits robustness and generalizability to unseen initial conditions from within (interpolative capability) as well as outside (extrapolative capability) the training regime.

computational combustion↗

NASA NTRS2014

Virtual Reality as a Medium for Sensorimotor Adaptation Training and Spaceflight Countermeasures

Astronauts experience a profound sensorimotor adaptation during transition to and from the microgravity environment of space. With the upcoming shift to extra‐long duration missions (upwards of 1 year) aboard the International Space Station, the immediate risks to astronauts during these transitory periods become more important than ever to understand and prepare for. Recent advances in virtual reality technology enable everyday adoption of these tools for entertainment and use in training. Embedding an individual in a virtual environment (VE) allows the ability to change the perception of visual flow, elicit automatic motor behavior and produce sensorimotor adaptation, not unlike those required during long duration microgravity exposure. The overall goal of this study is to determine the feasibility of present head mounted display technology (HMD) to produce reliable visual flow information and the expected adaptation associated with virtual environment manipulation to be used in future sensorimotor adaptability countermeasures. To further understand the influence of visual flow on gait adaptation during treadmill walking, a series of discordant visual flow manipulations in a virtual environment are proposed. Six healthy participants (3 male and 3 female) will observe visual flow information via HMD (Oculus Rift DK2) while walking on an instrumented treadmill at their preferred walking speed. Participants will be immersed in a series of VE's resembling infinite hallways with different visual characteristics: an office hallway, a hallway with pillars and the hallway of a fictional spacecraft. Participants will perform three trials of 10 min. each, which include walking on the treadmill while receiving congruent or incongruent visual information via the HMD. In the first trial, participants will experience congruent visual information (baseline) where the hallway is perceived to move at the same rate as their walking speed. The final two trials will be randomized among participants where the hallway is perceived to move at either half (0.5x) or twice (2.0x) their preferred walking speed. Participants will remain on the treadmill between trials and will not be warned of the upcoming change to visual flow to minimize preparatory adjustments. Stride length, step frequency and dual‐support time will be quantified during each trial. We hypothesize that participants will experience a rapid modification in gait performance during periods of adaptive change, expressed as a decrease in step length, an increase in step frequency and an increase in dual‐support time, followed by a period of adaptation where these movement parameters will return to near‐baseline levels. As stride length, step frequency and dual support times return to baseline values, an adaptation time constant will be derived to establish individual time‐to‐adapt (TTA). HMD technology represents a paradigm shift in sensorimotor adaptation training where gait adaptability can be stressed using off‐the‐shelf consumer products and minimal experimental equipment, allowing for greater training flexibility in astronaut and terrestrial applications alike.

Madansingh, S.↗

NASA NTRS2008

Vertical Jump Height is more Strongly Associated with Velocity and Work Performed Prior to Take-off

Vertical jump (VJ) height is commonly used as a measure of athletic capability in strength and power sports. Although VJ has been shown to be a predictor of athletic performance, it is not clear which kinetic ground reaction force (GRF) variables, such as peak force (PF), peak power (PP), peak velocity (PV), total work (TW) or impulse (Imp) are the best correlates. To determine which kinetic variables (PF, PP, PV, TW, and Imp) best correlate with VJ height. Twenty subjects (14 males, 6 females) performed three maximal countermovement VJs on a force platform (Advanced Mechanical Technology, Inc., Watertown, MA, USA). VJ jump height was calculated as the difference between standing reach and the highest reach point measured using a Vertec. PF, PP, PV, TW, and Imp were calculated using the vertical GRF data sampled at 1000 Hz from the lowest point in the countermovement through the concentric portion until take-off. GRF data were normalized to body mass measured using a standard scale (Detecto, Webb City, MO, USA). Correlation coefficients were computed between each GRF variable and VJ height using a Pearson correlation. VJ height (43.4 plus or minus 9.1 cm) was significantly correlated (p less than 0.001) with PF (998 plus or minus 321 N; r=0.51), PP (1997 plus or minus 772 W; r=0.69), PV (2.66 plus or minus 0.40 m (raised dot) s(sup -1); r=0.85), TW (259 plus or minus 93.0 kJ; r=0.82), and Imp (204 plus or minus 51.1 N(raised dot)s; r=0.67). Although all variables were correlated to VJ height, PV and TW were more strongly correlated to VJ height than PF, PP, and Imp. Therefore, since TW is equal to force times displacement, the relative displacement of the center of mass along with the forces applied during the upward movement of the jump are critical determinants of VJ height. PV and TW are key determinants of VJ height, and therefore successful training programs to increase VJ height should focus on rapid movement (PV) and TW by increasing power over time rather than focusing on PF alone.

Bentley, J. R.↗

DOE OSTI2026

A data-driven approach to real-time vertical position estimation for NSTX-U vertical stability control

In this paper, a database of 77 996 plasma equilibrium reconstructions from 727 discharges during the initial operation of the NSTX-U spherical tokamak is analyzed to develop a statistically robust model of the plasma vertical position for real-time control. A variety of regression models are developed and tested, ranging in complexity from linear models to deep neural networks, and including input signals ranging from the four pairs of flux loops used historically on NSTX-U up to the full set of 389 real-time signals available to the plasma control system. A linear model based on 140 real-time magnetics signals is found to offer excellent accuracy, with a coefficient of determination R 2 = 0.906. The robustness of this model to limited training data, new operating scenarios, and signal errors is tested, and a procedure is demonstrated to tune the model parameters to optimize its robustness. A time-dependent plasma equilibrium solver, TokaMaker, is used to simulate vertical stability control in NSTX-U, demonstrating that it should be possible to iteratively tune the parameters of a linear vertical position model to stabilize both positive and negative triangularity plasmas in future experiments.

magnetic diagnostics↗

DOE OSTI2023

A Hardware and Software Co-design Framework for Energy Efficient Neuromorphic Systems

Neuromorphic systems can be realized by a variety of algorithms and architectures. A common understanding is that spiking neuromorphic designs, which encode information into spatio-temporal spiking events, are both a biologically-accurate and efficient way of processing information. However, representing the information through timing relationships induces sophisticated circuit designs in traditional CMOS-based implementations. In recent years, high-capacity resistive memory (RRAM, aka, memristor) has demonstrated great potential in mimicking synaptic behaviors. Several RRAM-based spiking neuromorphic designs exist, most of which focus on rate coding schemes. These designs simplify circuit implementations of neuron models and explore challenges such as unsatisfactory speed, resolution, and performance. As an alternative, we will explore temporal coding spiking neuromorphic systems that encode information as the relative timing of neuron activations (spikes), which have been proven to be more adaptive and energy-efficient. Developing a neuromorphic system for spiking neural network (SNN) inference and online training, however, faces some major technical challenges: (1) It lacks circuit implementation support for temporal-coding SNN to achieve satisfying power efficiency and accuracy; (2) Although existing research works have investigated memristive synapse and neuron designs for spike-timing-dependent plasticity, the non-ideal conditions in implementation, such as device variations and signal degradation, degrade online learning accuracy of large scale systems; and (3) Non-optimized, inter-layer data traffic in SNNs, leads to unnecessary data communication costs. In this project, we plan to address these challenges by a hardware and software co-design framework that incorporates solutions at the circuit, architecture, and algorithm levels. At the circuit-level, we will elaborate on the in-situ SNN processing element designs for supporting both inference and online training modes. Variation-aware schemes will be studied to improve reliability. At the architecture level, we propose a pipelined, asynchronous architecture to retain the timing resolution of spikes. At the algorithm level, we will investigate an innovative SNN training algorithm for enabling activation sparsification and reducing unnecessary data communication costs. This neuromorphic system will provide an effective solution to real-life energy-constrained applications and significantly contribute to the exploration of next-generation high-performance computing systems under the DOE context.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2022

Dynamic calibration of differential equations using machine learning, with application to turbulence models

We present a methodology for calibration of parametric ordinary and partial differential equation models, using off-the-shelf software for back-propagation in Neural Networks (NN). As a prototypical example, we consider calibration of a Reynolds-averaged Navier-Stokes (RANS) turbulence closure model, against ground truth data from direct numerical simulations (DNS) of two different turbulent flows. Numerical time integration is represented as a custom NN, where only the RANS model parameters are trainable. A loss function is defined to quantify the mismatch between the NN prediction and the ground truth over a predefined, finite time integration window. This loss function is then minimized using a gradient descent method utilizing the back-propagation algorithm. Furthermore, this dynamic approach to training is to be contrasted with a static approach, wherein a least square regression estimate for parameters is obtained in the limit of an infinitesimal time integration window. In a first test of static and dynamic approaches against ground truth data generated by the model, the former proves to be significantly faster and more accurate than the latter at recovering the parameters. When both calibration approaches are tested against DNS data, for which it is known that the model cannot achieve a perfect fit, the static approach yields a good prediction only for short times, while the dynamic approach results in physical and stable predictions over the entire integration window. After optimization of the dynamic approach for time step, spatial resolution, stability, and physics-based constraints, we obtain a 50% improvement of outcomes over those obtained from the existing, manually calibrated set of parameters, demonstrating the merits of this systematic and automated procedure.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2024

Cropland abandonment between 1986 and 2018 across the United States: spatiotemporal patterns and current land uses

Knowing where and when croplands have been abandoned or otherwise removed from cultivation is fundamental to evaluating future uses of these areas, e.g. as sites for ecological restoration, recultivation, bioenergy production, or other uses. However, large uncertainties remain about the location and time of cropland abandonment and how this process and the availability of associated lands vary spatially and temporally across the United States. Here, we present a nationwide, 30 m resolution map of croplands abandoned throughout the period of 1986–2018 for the conterminous United States (CONUS). We mapped the location and time of abandonment from annual cropland layers we created in Google Earth Engine from 30 m resolution Landsat imagery using an automated classification method and training data from the U.S. Department of Agriculture Cropland Data Layer. Our abandonment map has overall accuracies of 0.91 and 0.65 for the location and time of abandonment, respectively. From 1986 to 2018, 12.3 (±2.87) million hectares (Mha) of croplands were abandoned across CONUS, with areas of greatest change over the Ogallala Aquifer, the southern Mississippi Alluvial Plain, the Atlantic Coast, North Dakota, northern Montana, and eastern Washington state. The average annual nationwide abandoned area across our study period was 0.51 Mha per year. Annual abandonment peaked between 1997 and 1999 at a rate of 0.63 Mha year –1 , followed by a continuous decrease to 0.41 Mha year –1 in 2009–2011. Among the abandoned croplands, 53% (6.5 Mha) changed to grassland and pasture, 18.6% (2.28 Mha) to shrubland and forest, 8.4% (1.03 Mha) to wetlands, and 4.6% (0.56 Mha) to non-vegetated lands. Of the areas that we mapped as abandoned, 19.6% (2.41 Mha) were enrolled in the Conservation Reserve Program as of 2020. Our new map highlights the long-term dynamic nature of agricultural land use and its relation to various competitive pressures and land use policies in the United States.

54 ENVIRONMENTAL SCIENCES↗

DOE OSTI2023

Accelerating discrete dislocation dynamics simulations with graph neural networks

Discrete dislocation dynamics (DDD) is a widely employed computational method to study plasticity at the mesoscale that connects the motion of dislocation lines to the macroscopic response of crystalline materials. However, the computational cost of DDD simulations remains a bottleneck that limits its range of applicability. Here, we introduce a new DDD-GNN framework in which the expensive time-integration of dislocation motion is entirely substituted by a graph neural network (GNN) model trained on DDD trajectories. As a first application, we demonstrate the feasibility and potential of our method on a simple yet relevant model of a dislocation line gliding through an array of obstacles. We show that the DDD-GNN model is stable and reproduces very well unseen ground-truth DDD simulation responses for a range of straining rates and obstacle densities, without the need to explicitly compute nodal forces or dislocation mobilities during time-integration. Our approach opens new promising avenues to accelerate DDD simulations and to incorporate more complex dislocation motion behaviors.

36 MATERIALS SCIENCE↗

NASA NTRSDate not supplied

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↗

NASA NTRS2024

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↗

NASA NTRS2010

Developing Collective Training for Small Unmanned Aerial Systems Employment

The projected use of small unmanned aerial systems (SUAS) in military operations will produce training requirements which go beyond current capabilities. The paper describes the development of prototype training procedures and accompanying research simulations to address this need. We initially constructed a testbed to develop simulation-based training for an SUAS operator equipped with a simulated vertical-lift and land SUAS. However, the required training will go beyond merely training an operator how to pilot an SUAS. In addition to tactics, techniques, and procedures for employment of SUASs, collective training methods must be trained. Moreover, the leader of a unit equipped with SUAS will need to learn how to plan missions which incorporate the SUAS, and take into account air space and frequency management considerations. The demands of the task require the leader to allocate personnel to the SUAS mission, communicate and coordinate with those personnel during the mission, and make use of the information provided. To help address these training issues, we expanded our research testbed to include a command and control node (C2 node), to enable communications between a leader and the SUAS operator. In addition, we added a virtual environment in which dismounted infantry missions can be conducted. This virtual environment provides the opportunity for interactions among human-controlled avatars and non-player characters (NPCs), plus authoring tools to construct scenarios. Using these NPCs, a collective exercise involving friendly, enemy, and civilian personnel can be conducted without the need for a human role-player for every entity. We will describe the results of our first experiment, which examined the ability of players to negotiate use of the C2 node and the virtual environment at the same time, in order to see if this is a feasible combination of tools for training development.

Durlach, Paula J.↗