Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “error budget”

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.

51 records · Page 3
All sourcesNASA NTRSDOE OSTI
NASA NTRSDate not supplied

Development and Validation of a High-Vacuum Thermal Conductivity Testbed for Aerospace Interface Materials

Spacecraft thermal margins depend on the temperature penalty of installed interfaces, yet catalog conductivity omits bondline thickness, mating surfaces, preload, and environment. The Testbed for Advanced Interface Materials in Vacuum (TAIMV) addresses this engineering-data gap by converting ambient/vacuum temperature fields from a four-coupon stack into quantities usable in spacecraft thermal models. Its 17-node steady-state model resolves axial conduction, parasitic fixture paths, grease-filled contact, radiation, and ambient convection. Four monolithic checks gave axial heat-rate ratios of 0.90–1.02, and Braycote calibration self-recovery gave 2.20% casewise mean absolute percentage error (MAPE) and 2.85% maximum difference. With transferable fixture terms frozen, Krytox LVP tested cross-material transfer against a manufacturer-derived external relation. The six Krytox cases gave 2.28% MAPE, 5.10% maximum difference, and full-field residual root-mean-square values of 0.553 °C ambient and 1.306 °C vacuum. Installed-joint resistance spanned 6.39–7.15 × 10⁻⁴ m²·K/W for Braycote and 4.09–4.49 × 10⁻⁴ m²·K/W for Krytox, corresponding to 2.33–6.66 K per modeled interface over the tested heat-flux range. TAIMV therefore supplies directly usable installed-joint resistance and conductance, plus apparent installed conductivity and explicitly model-conditioned grease conductivity/contact terms.

heat transfer↗
NASA NTRSDate not supplied

High-Fidelity Modeling Approach for Coupling Thermal, Fluid, and Neutronic Analysis in an NTP Engine

Nuclear thermal propulsion (NTP), with its increased efficiency compared to traditional rocket engines, is a potentially enabling technology for space missions of higher complexity, such as delivering heavy machinery or crew to the moon or other planets. Thus, exploring modeling approaches that can effectively couple the thermal, fluid, and neutronic behaviors of NTP reactors is essential to mitigate cost and schedule challenges with hardware development. This paper details one such approach which utilizes Cardinal to unify reactor physics analysis performed using OpenMC, heat transfer analysis performed using the MOOSE framework, and thermal hydraulic analysis performed using the MOOSE Thermal Hydraulic Module. This approach is demonstrated with a proof of concept that focuses on a legacy reactor geometry from the historic NERVA program. This preliminary model found an overprediction in, when compared to the reference data, axial power peaking and the temperatures of both solids and fluids by roughly 20%. It is clear, however, that the model conserved a number of broad trends, and a few model refinements should reduce the observed error. This approach has definite merit and should enable the production of informative results for more modern NTP systems. This work is a first step in creating a transient reactor model that can be updated across a sequence of time steps based on continually fluctuating, time-dependent boundary conditions.

Nuclear Thermal Propulsion↗
NASA NTRS2026

Improvement in the Thermal-to-Structural Model Mapping Process for Integrated Modeling for the Roman Space Telescope

Integrated Modeling has been a key component of verifying optical requirements for the Nancy Grace Roman Space Telescope (RST) that are either impossible or impractical to verify exclusively through ground testing. Two major areas for integrated Modeling are Jitter and Thermal Distortion that require the exchanges of model performance predictions across disciplines. In both cases, distortions are impressed on optical models to evaluate the impact on boresight alignment and wave front error. In the case of Jitter, the disturbances are driven by reactions to motions most often from actuators; however, in the case of thermal distortion, the motions are driven by thermal expansion or contraction as a result of changing temperatures. This then requires a link further upstream to the thermal model, which is used to predict the thermal performance and temperature gradients and stability. The process for mapping temperatures from a thermal model to a corresponding structural model has been performed numerous times through the RST project lifecycle, with improvements in the accuracy, verification, and effort sought throughout. This paper describes some of the recent improvements to the process, including: capture of the visualization parameters, automatic generation of the mapped images for both the thermal and structural model groupings, and reduction in the effort to assemble the full set of mapped temperatures. These upgrades have greatly reduced the manual effort associated with thermal mapping and allowed for faster turn-around of Integrated Modeling predictions.

Thermal Mapping↗
NASA NTRS1997

Future Aerospace Technology in the Service of the Alliance: Sustained Hypersonic Flight - Volume 3

Sustained Hypersonic Flight capability is envisioned for several future military and civilian applications, such as long range immediate reaction reconnaissance, high speed interception of air targets, long range precision strike against hardened or time critical targets, and access to space. The inherent reduction in time-to-target and low vulnerability will permit new operational tactics. The symposium outlined mission needs and operational scenarios for hypersonic vehicles. Addressed were: Technological issues and challenges in external hypersonic aerodynamics and design, propulsion and engine/airframe integration, military ramjet applications, overall system design including structures and materials development needs, and test facilities. Ground based test facilities cannot provide full simulation at Mach numbers above 5. Therefore, the use of Computational Fluid Dynamics design tools is essential. For routine use of the computational tools in analysis, design and optimization, it is necessary to reduce the time for the entire computational process by two orders of magnitude. Hypersonic boundary layer transition remains a critical design issue because of the important impact on engine drag and on heating, which can affect the choice of materials and thermal protection systems. In addition, reliable prediction of scramjet net thrust is an absolute must in resolving hypersonic air breathing vehicle design issues. Due to current facility and computational shortfalls, the development of future hypersonic flight systems requires research flight tests in the technology areas of boundary layer transition and air-breathing propulsion engine performance. For sustained hypersonic flight beyond Mach 6, the supersonic combustion ramjet (scramjet) engine is the only choice for the near future. Only this air-breathing concept offers a significant promise of large reductions in required propellant fractions, increased payload fractions, and reduced size vehicles, together with a foreseeable technological feasibility. Airframe/engine integration, combustor design and thermal management are the predominant engineering tasks. Fuels, hydrogen or hydrocarbon, must be matched to the operational needs of military or civil use. Experience in existing ramjet propelled missiles capable of speeds up to Mach 4 can support the development effort. The potential mission and cost benefits of sustained hypersonic flight to both military and civil applications are tremendous. From the budget point of view, the possibility of sharing development costs between military and civil programs offers a specific advantage.

Combustion chambers↗
NASA NTRSDate not supplied

Access to Space for NASA SmallSats: Current and Future Needs

Small spacecraft technology advancements have fundamentally shifted how NASA’s Science Mission Directorate (SMD) executes science investigations. To support this approach, the SMD Rideshare Office (SRO) was established in 2020 to lead the definition and implementation of a directorate-wide rideshare strategy. Serving as the central point of contact for coordinating compatible NASA payloads with launch opportunities, the SRO maximizes science, exploration, and technology return on investment by enabling rideshare or other access to space opportunities for small spacecraft on SMD primary mission launches, VADR commercial launch procurements, and other government agency launch opportunities. As NASA seeks to reduce costs and increase the rate of discovery, small satellites and multi manifest access to space have become integral to achieving the agency’s strategic vision. While NASA has created the above-mentioned mechanisms to expand access to space and achieve lower launch costs for its small satellites, many factors have limited full exploit of the opportunity these mechanisms can bring. NASA continues to evolve its mission cultures and technical requirements to adapt and take advantage of burgeoning commercial launch and rideshare advancements. To do so NASA requires collaboration with small satellite manufacturers, principal investigators, and commercial industry partners. Current needs include technical development and design of structurally robust spacecraft buses capable of withstanding varied launch loads, which will increase rideshare interchangeability and versatility. Further, instrument and spacecraft designs must also evolve to handle diverse launch environments and loads factors, while reducing reliance on complex purge and cleanliness constraints, sensitivities to silicones and hydrocarbons, and magnetic requirements. Continued maturation of small and medium launch providers in the near-term is also essential to drive down costs through competition. The current mission selection cadence often complicates the ability to synchronize multiple missions on a single launch. Future needs can include affordable space maneuverability options such as enhanced spacecraft propulsion systems and unique orbital maneuvering capabilities for our individual smallsats or constellations. These emerging capabilities offer a path to unique science orbits for NASA small satellites, but only under the condition that their cost remains affordable and competitive to accommodate inherently smaller mission budgets. Additionally, the projected surge of multiple SMD small satellites launching simultaneously and to unique deep space science orbits necessitates evaluation of expanding deep space communications capabilities. This presentation provides a comprehensive overview of NASA SMD’s access to space landscape and offers further unique insights and discussion, backed by NASA rideshare experiences and lessons learned, on the current and future developments required to unleash the full potential of rideshare opportunities.

Rideshare↗
NASA NTRSDate not supplied

Access to Space for NASA Small Sats: Current and Future Needs

Small spacecraft technology advancements have fundamentally shifted how NASA’s Science Mission Directorate (SMD) executes science investigations. To support this approach, the SMD Rideshare Office (SRO) was established in 2020 to lead the definition and implementation of a directorate-wide rideshare strategy. Serving as the central point of contact for coordinating compatible NASA payloads with launch opportunities, the SRO maximizes science, exploration, and technology return on investment by enabling rideshare or other access to space opportunities for small spacecraft on SMD primary mission launches, VADR commercial launch procurements, and other government agency launch opportunities. As NASA seeks to reduce costs and increase the rate of discovery, small satellites and multi manifest access to space have become integral to achieving the agency’s strategic vision. While NASA has created the above-mentioned mechanisms to expand access to space and achieve lower launch costs for its small satellites, many factors have limited full exploit of the opportunity these mechanisms can bring. NASA continues to evolve its mission cultures and technical requirements to adapt and take advantage of burgeoning commercial launch and rideshare advancements. To do so NASA requires collaboration with small satellite manufacturers, principal investigators, and commercial industry partners. Current needs include technical development and design of structurally robust spacecraft buses capable of withstanding varied launch loads, which will increase rideshare interchangeability and versatility. Further, instrument and spacecraft designs must also evolve to handle diverse launch environments and loads factors, while reducing reliance on complex purge and cleanliness constraints, sensitivities to silicones and hydrocarbons, and magnetic requirements. Continued maturation of small and medium launch providers in the near-term is also essential to drive down costs through competition. The current mission selection cadence often complicates the ability to synchronize multiple missions on a single launch. Future needs can include affordable space maneuverability options such as enhanced spacecraft propulsion systems and unique orbital maneuvering capabilities for our individual smallsats or constellations. These emerging capabilities offer a path to unique science orbits for NASA small satellites, but only under the condition that their cost remains affordable and competitive to accommodate inherently smaller mission budgets. Additionally, the projected surge of multiple SMD small satellites launching simultaneously and to unique deep space science orbits necessitates evaluation of expanding deep space communications capabilities. This presentation provides a comprehensive overview of NASA SMD’s access to space landscape and offers further unique insights and discussion, backed by NASA rideshare experiences and lessons learned, on the current and future developments required to unleash the full potential of rideshare opportunities.

Rideshare↗
NASA NTRSDate not supplied

Predicting Team Functioning in Long Term Space Missions Using Acoustic and Linguistic Measures

Maintaining optimal team functioning is critical for long-duration space exploration missions, yet traditional monitoring methods, such as self-reports and wearable sensors, often impose operational burdens or suffer from bias. This paper investigates a non-intrusive speech-based artificial intelligence (AI) framework to predict degradations in team functioning using data from the Human Exploration Research Analog (HERA) of the U.S. National Aeronautics and Space Administration (NASA). Using acoustic features, linguistic descriptors, and semantic embeddings, we evaluate static non-linear and temporal machine learning models to predict both objective (task accuracy) and subjective (self-reported efficacy and cohesion) team functioning outcomes. Results indicate that temporal models outperform static approaches, with prediction of objective task accuracy in Team Interaction Battery (TIB) improving from near chance to 71%. Self-reported outcomes, including team efficacy and cohesion, are predicted more reliably than task performance, achieving balanced accuracies of up to 85.56% and 78.12%, respectively, and are found to be most strongly associated with acoustic features. In a second interdependent task, the MMSEV–EVA, accuracies of up to 78% are achieved using temporal models with acoustic features. Furthermore, incorporating just 1–2 days of team-specific historical data systematically improved performance, and acoustic markers from informal pre-task interactions provided modest predictive gains. Finally, while automated preprocessing yielded viable accuracy, humancorrected data provided moderate performance gains, though transcription error rates did not significantly correlate with model performance. These findings highlight the potential of speech as a passive, high-fidelity monitoring tool for autonomous habitats.

Temporal modeling↗
NASA NTRS2026

Atacama Cosmology Telescope A Measurement of Galaxy Cluster Temperatures Through Relativistic Corrections to the Thermal Sunyaev-Zeldovich Effect

The high electron temperature in galaxy clusters (> 1 keV or > 107 K) leads to corrections at the level of a few percent in their thermal Sunyaev-Zeldovich effect signatures. Both the size and frequency dependence of these corrections, which are known as relativistic temperature corrections, depend upon the temperature of the objects. In this work we exploit this effect to measure the average temperature of a stack of Compton-y selected clusters. Specifically, we apply the “spectroscopic method” and search for the temperature that best fits the clusters’ signal measured at frequencies from 30 to 545 GHz by the Atacama Cosmology Telescope and Planck satellite. We measure the average temperature of clusters detected in the Atacama Cosmology Telescope maps to be 8.5 2.4 keV, with an additional systematic error of comparable amplitude dominated by passband uncertainty. Upcoming surveys, such as the Simons Observatory and CMB-S4, have the potential to dramatically improve upon these measurements and thereby enable precision studies of cluster temperatures with millimeter observations. The key challenge for future observations will be mitigating instrumental systematic effects, which already limit this analysis.

William R Coulton↗
NASA NTRS2026

Incremental Learning for Passive Microwave Precipitation Retrievals using Advanced Technology Microwave Sounder

Spaceborne passive microwave (PMW) radiometry is central to global precipitation monitoring, yet retrieval uncertainties remain substantial, particularly for cross-track sounders whose variable footprints and channel configurations are optimized for atmospheric temperature and moisture profiling rather than precipitation. Consequently, existing operational products often exhibit angular-dependent biases, limited effective swath utilization, unrealistic rainfall probability distributions, and systematic misclassification of precipitation phase. These limitations are further compounded by the scarcity of globally accurate and representative precipitation observations, as training data from the Dual-frequency Precipitation Radar (DPR) and the Cloud Profiling Radar (CPR) are spatially sparse, lack uniform global coverage, and exhibit heterogeneous error characteristics across precipitation regimes. To address these challenges, this study presents a supervised retrieval algorithm that incrementally trains an ensemble of extreme gradient-boosted decision trees by augmenting base learners with pre-training on reanalysis data and post-training on coincident DPR and CPR observations matched with the Advanced Technology Microwave Sounder (ATMS). By transferring prior information from reanalysis to posterior constraints from radar observations and adopting a sequential detection–estimation strategy for precipitation phase and rate retrieval, the proposed approach yields retrievals across the full ATMS swath that are largely free from persistent deficiencies in current Global Precipitation Measurement (GPM) passive microwave operational products. In particular, the method resolves bimodal artifacts in rainfall retrievals and mitigates systematic high-latitude snowfall biases, including overestimation across the Arctic and underestimation across the Antarctic. Validation against independent Multi-Radar Multi-Sensor (MRMS) data over the Contiguous United States (CONUS) further demonstrates improved performance in precipitation phase detection and rate estimation relative to both reanalysis and current GPM PMW products.

Mahyar Garshasbi↗
NASA NTRS2025

Improving Adhesive Bondline Time of Flight Predictions During Autoclave Cure Utilizing Machine Learning

Composite materials are increasingly being used in aerospace applications due to their superior strength-to-weight ratio compared to commonly used metals. A current limitation to widespread adoption is the certification of adhesively bonded joints. One approach to improving adhesive bonding in composites is accurately measuring the thickness of adhesive bondlines in composite laminates. Precise bondline thickness control is essential for aerospace applications where adhesive layer thickness directly affects joint fracture properties and structural performance. This study focused on implementing machine learning techniques to determine the ultrasonic time of flight (directly correlated to thickness) in adhesive bondlines throughout autoclave cure cycles. A high-temperature (use up to 180°C) ultrasonic scanning system was deployed in an autoclave to provide time of flight data through composite panels. Three experiments were conducted on the curing of 305 mm × 305 mm unidirectional composite panels. In the first experiment, a piecewise function was fit for the temperature correction factor to account for changing autoclave temperatures. Due to deficiencies in the first calibration experiment, a second experiment was run, and the results were used to train a machine learning model. The revised experiment, in combination with the machine learning model, significantly increased the accuracy of the bondline time of flight predictions (~14% error reduced to <1%). Data was processed using the Regression Learner Application in MATLAB®, with a Support Vector Machine selected for the model. The result was a machine learning algorithm capable of reliably quantifying ultrasonic time of flight through adhesive bondlines. The third experiment provided independent test data for the machine learning model, demonstrating that the model produces accurate predictions from data beyond its training set.

Machine Learning↗
NASA NTRS2026

Remote Sensing-Driven Hydrodynamic Modeling in Data-Scarce Regions: Integrating ICESat-2, Sentinel-2, SWOT and Re-analysis Models for Coastal Monitoring

Hydrodynamic models in coastal and estuarine systems are typically constrained by sparse bathymetry, boundary, and validation data, especially in regions where field campaigns are costly or impractical. Here we develop and test a fully satellite-driven framework for hydrodynamic modeling in South Africa’s Langebaan Lagoon without using any local in situ measurements. Bathymetry is derived by training multispectral Sentinel-2 reflectance against ICESat-2 ATL24 photon-derived depths using an XGBoost model optimized with Bayesian search. The final satellite-derived bathymetry reproduces independent ATL24 points with RMSE = 0.45 m and R 2 = 0.97. This bathymetry was used in a depth-averaged Delft3D Flexible Mesh model driven at the open boundary by TPXO tidal harmonics and by ERA5 winds. We validate modeled water surface elevation against 16 SWOT low-rate (250 m, unsmoothed) passes in 2023. SWOT–model comparisons yield an overall RMSE of 0.11 m and R 2 = 0.61, with typical point differences <0.10 m (∼7% of the 1.5 m tidal range), and showed consistent spatial gradients in water level from the offshore boundary, through Saldanha Bay, and into the lagoon. At the offshore boundary, TPXO and SWOT sea surface heights agree closely (R 2 = 0.86). A simple phase adjustment of ∼26,min between TPXO and SWOT lowers the RMSE from 0.18,m to 0.11,m, showing that phase offset accounts for some of the discrepancy, with additional errors likely linked to non-tidal signals. Our results demonstrate that combining passive optical, photon-counting LiDAR, radar interferometry, and global tidal/atmospheric models enables robust, transferrable hydrodynamic modeling in data-scarce coastal systems, offering a cost-effective pathway for monitoring.

ICESat-2↗
NASA NTRS1993

Enhanced Decoding for the Galileo S-Band Mission

A coding system under consideration for the Galileo S-band low-gain antenna mission is a concatenated system using a variable redundancy Reed-Solomon outer code and a (14,1/4) convolutional inner code. The 8-bit Reed-Solomon symbols are interleaved to depth 8, and the eight 255-symbol codewords in each interleaved block have redundancies 64, 20, 20, 20, 64, 20, 20, and 20, respectively (or equivalently, the codewords have 191, 235, 235, 235, 191, 235, 235, and 235 8-bit information symbols, respectively). This concatenated code is to be decoded by an enhanced decoder that utilizes a maximum likelihood (Viterbi) convolutional decoder; a Reed Solomon decoder capable of processing erasures; an algorithm for declaring erasures in undecoded codewords based on known erroneous symbols in neighboring decodable words; a second Viterbi decoding operation (redecoding) constrained to follow only paths consistent with the known symbols from previously decodable Reed-Solomon codewords; and a second Reed-Solomon decoding operation using the output from the Viterbi redecoder and additional erasure declarations to the extent possible. It is estimated that this code and decoder can achieve a decoded bit error rate of 1 x 10 -7 at a concatenated code signal-to-noise ratio of 0.76 dB. By comparison, a threshold of 1.17 dB is required for a baseline coding system consisting of the same (14,1/4) convolutional code, a (255,223) Reed-Solomon code with constant redundancy 32 also interleaved to depth 8, a one-pass Viterbi decoder, and a Reed Solomon decoder incapable of declaring or utilizing erasures. The relative gain of the enhanced system is thus 0.41 dB. It is predicted from analysis based on an assumption of infinite interleaving that the coding gain could be further improved by approximately 0.2 dB if four stages of Viterbi decoding and four levels of Reed-Solomon redundancy are permitted. Confirmation of this effect and specification of the optimum four-level redundancy profile for depth-8 interleaving is currently being done.

S Dolinar↗
NASA NTRS2026

A Modular Conjugate Heat Transfer Optimization Framework for Thermal Management of Electric Aircraft

Conjugate heat transfer (CHT) analysis and optimization is a powerful method for improving thermal management, as it simultaneously resolves the temperature distribution in both fluid and solid domains. This paper presents a modular, discrete adjoint-based CHT optimization capability integrated within the OpenMDAO/MPhys framework. A unique feature of the proposed framework is its flexibility to extend to multidisciplinary optimization, including aero-structural-thermal applications. The fluid domain is modeled using a finite-volume Computational Fluid Dynamics (CFD) solver, and the solid domain with a conduction heat transfer solver. A mixed Neumann-Dirichlet boundary condition is developed to enable full submersion of the solid geometry within the fluid domain, while ensuring consistent temperature and heat flux coupling at the CHT interface. Gradient-based optimization is performed; the gradients are efficiently computed using the discrete adjoint solvers implemented in DAFoam. To demonstrate the method, this paper considers two cases related to electric aircraft thermal management: a U-bend heat exchanger and an actively cooled battery pack. The U-bend case aims to minimize pressure loss while maximizing heat flux by changing the pipe geometry. The optimized design reduces pressure loss by 52.7% and increases total heat flux by 2.3%. In the battery pack case, a 3-by-3 cell configuration is cooled by ambient airflow, with constant heat generation prescribed in the cells. The battery casing shape serves as the design variable, and the objective function is a weighted sum of pressure loss and pack weight, subject to a maximum temperature constraint. The optimized design achieves a 44.6% reduction in pressure loss and a 1.5% reduction in weight, while satisfying the thermal constraint. To ensure the reliability of the optimized designs, this study validates coarse-mesh, steady-state predictions against fine-mesh unsteady simulations, demonstrating consistency within acceptable errors. This work demonstrates the potential of the developed framework to enable rapid, high-fidelity design of thermal management systems for electric aircraft.

heat transfer↗
NASA NTRS2010

High-Precision Shape Control of In-Space Deployable Large Membrane/Thin-Shell Reflectors

This innovation has been developed to improve the resolutions of future spacebased active and passive microwave antennas for earth-science remote sensing missions by maintaining surface figure precisions of large membrane/thin-shell reflectors during orbiting. The intention is for these sensing instruments to be deployable at orbit altitudes one or two orders of magnitude higher than Low Earth Orbit (LEO), but still being able to acquire measurements at spatial resolution and sensitivity similar to those of LEO. Because active and passive microwave remote sensors are able to penetrate through clouds to acquire vertical profile measurements of geophysical parameters, it is desirable to elevate them to the higher orbits to obtain orbital geometries that offer large spatial coverage and more frequent observations. This capability is essential for monitoring and for detailed understanding of the life cycles of natural hazards, such as hurricanes, tropical storms, flash floods, and tsunamis. Major components of this high-precision antenna-surface-control system include a membrane/thin shell reflector, a metrology sensor, a controller, actuators, and corresponding power amplifier and signal conditioning electronics (see figure). Actuators are attached to the back of the reflector to produce contraction/ expansion forces to adjust the shape of the thin-material reflector. The wavefront-sensing metrology system continuously measures the surface figure of the reflector, converts the surface figure to digital data and feeds the data to the controller. The controller determines the control parameters and generates commands to the actuator system. The flexible, piezoelectric polymer actuators are thus activated, providing the control forces needed to correct any distortions that exist in the reflector surface. Piezoelectric polymer actuators are very thin and flexible. They can be implemented on the back of the membrane/thin-shell reflector without introducing significant amounts of mass or stiffness to the reflector. They can be rolled up or folded to accommodate the packaging needed for launch. An analytical model of the system, which includes the membrane reflector, actuator, and controller has been developed to investigate the functionality of this control system on a 35-meter-diameter membrane reflector. The performance of this system under external disturbances such as in space thermal loads and W-error due to inflation has been investigated. A subscale breadboard has been developed, and the functionality of this control concept has been demonstrated by this breadboard.

Houfei Fang↗
NASA NTRS2026

Machine Learning for Predicting Team Functioning in HERA Missions

Team functioning is integral to success in future long term space exploration missions. Proactively detecting declines in team functioning can mitigate conflict and ensure mission success. This project developed a speech-based artificial intelligence (AI) system that unobtrusively predicts degradation in team functioning, including performance and cohesion, in the Human Exploration Research Analog (HERA) Campaigns 4 and 5. The AI system conducted automated analysis of the prosodic (tone of voice) and linguistic (language content) components of speech, modeling interpersonal dynamics at both the turn-taking and day-wide levels. We investigated team functioning via observing structured interactions (i.e., multi-mission space exploration vehicle-extra vehicular activity [MMSEV-EVA], team interaction battery [TIB]) and unstructured interactions before the MMSEV-EVA task. We developed machine learning models to predict team functioning (objective task accuracy, self reported team efficacy and self reported team cohesion) by analyzing OpenSmile acoustic features, linguistic descriptors extracted via the linguistic inquiry and word count (LIWC) dictionary, and semantic embeddings. In the TIB, static models using logistic regression and random forests were not able to predict task accuracy, but predicted team efficacy and cohesion during both the decision making and relational tasks to a moderate level (60-70%). Majority voting on the individual turns to predict day long team efficacy further increased accuracies (70-80%). Finally, long short-term memory (LSTM) models showed the best performance across all variables (80-91%), including task performance. In the MMSEV-EVA, static models achieved an accuracy of 60% with majority voting, which increased to 80% through the incorporation of mission day as a variable, accounting for the learning effect. A key finding across both tasks was the "team-dependent" nature of these interactions; models achieved much higher accuracy when trained on prior days of the same team's data rather than attempting to generalize across entirely different teams, with even 1-2 days of prior data per team achieving 5-15% improvement over team-independent models. In addition, the incorporation of pre-task data from the same team also improves model performance, e.g., incorporating data from the decision-making task of the TIB, which preceded the relational task, improved the prediction of team efficacy and cohesion during the latter. We compared model performance when trained on machine-generated data compared to data that had been further corrected by human annotators. Overall, models trained on human-corrected data exhibited a modest improvement in performance, particularly when acoustic features were used. We found no significant correlation between word error rate (WER) and model accuracy (r(55) = -0.08, p = 0.51), but model’s accuracy was significantly higher for medium/high quality transcription (0.74 (SD = 0.48)) compared to the low-quality group (0.64 (SD = 0.36)) (t(63)=2.82, p = 0.006). Based on these, several design recommendation emerge, that could inform Standards at NASA. Models predicting team functioning should incorporate at least one to two days of historical interaction data, include brief pre-task discussions, and explicitly model temporal learning effects, especially for longer operational tasks. Minimum quality standards for automated speech-processing pipelines are needed, given the performance gains observed with manually corrected acoustic data. Finally, systems should leverage both acoustic features and language embeddings in complementary ways, with modality choices and fusion strategies tailored to mission context, task demands, and data quality requirements.

Shrivatsa Mishra↗