Search NASA⌕ Search

SEARCH · Search NASA

Results for “Traditional Machine Learning Models”

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 811 records · Page 45

Using the concordance of in vitro and in vivo data to evaluate extrapolation assumptions

Linking in vitro bioactivity and in vivo toxicity on a dose basis enables the use of highthroughput in vitro assays as an alternative to traditional animal studies. In this study, we evaluated assumptions in the use of a high-throughput, physiologically based toxicokinetic (PBTK) model to relate in vitro bioactivity and rat in vivo toxicity data. The fraction unbound in plasma (fup) and intrinsic hepatic clearance (Clint) were measured for rats (for 67 and 77 chemicals, respectively), combined with fup and Clint literature data for 97 chemicals, and incorporated in the PBTK model. Of these chemicals, 84 had corresponding in vitro ToxCast bioactivity data and in vivo toxicity data. For each possible comparison of in vitro and in vivo endpoint, the concordance between the in vivo and in vitro data was evaluated by a regression analysis. For a base set of assumptions, the PBTK results were more frequently better associated than either the results from a “random” model parameterization or direct comparison of the “untransformed” values of AC50 and dose (performed best in 51%, 28%, and 21% of cases, respectively). We also investigated several assumptions in the application of PBTK for IVIVE, including clearance and internal dose selection. One of the better assumptions sets–restrictive clearance and comparing free in vivo venous plasma concentration with free in vitro concentration–outperformed the random and untransformed results in 71% of the in vitro-in vivo endpoint comparisons. These results demonstrate that applying PBTK improves our ability to observe the association between in vitro bioactivity and in vivo toxicity data in general. This suggests that potency values from in vitro screening should be transformed using in vitro-in vivo extrapolation (IVIVE) to build potentially better machine learning and other statistical models for predicting in vivo toxicity in humans

59 BASIC BIOLOGICAL SCIENCES↗

Machine learning for single-ended event reconstruction in PROSPECT experiment

The Precision Reactor Oscillation and Spectrum Experiment, PROSPECT, was a segmented antineutrino detector that successfully operated at the High Flux Isotope Reactor in Oak Ridge, TN, during its 2018 run. Despite challenges with photomultiplier tube base failures affecting some segments, innovative machine learning approaches were employed to perform position and energy reconstruction, and particle classification. This work highlights the effectiveness of convolutional neural networks and graph convolutional networks in enhancing data analysis. By leveraging these techniques, a 3.3% increase in effective statistics was achieved compared to traditional methods, showcasing their potential to improve analysis performance. Furthermore, these machine learning methodologies offer promising applications for other segmented particle detectors, underscoring their versatility and impact.

47 OTHER INSTRUMENTATION↗

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

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

59 BASIC BIOLOGICAL SCIENCES↗

Quantifying the robustness of deep multispectral segmentation models against natural perturbations and data poisoning

In overhead image segmentation tasks, including additional spectral bands beyond the traditional RGB channels can improve model performance. However, it is still unclear how incorporating this additional data impacts model robustness to adversarial attacks and natural perturbations. For adversarial robustness, the additional in-formation could improve the model’s ability to distinguish malicious inputs, or simply provide new attack avenues and vulnerabilities. For natural perturbations, the additional information could better inform model decisions and weaken perturbation effects or have no significant influence at all. In this work, we seek to characterize the performance and robustness of a multispectral (RGB and near infrared) image segmentation model subjected to adversarial attacks and natural perturbations. While existing adversarial and natural robustness research has focused primarily on digital perturbations, we prioritize on creating realistic perturbations designed with physical world conditions in mind. For adversarial robustness, we focus on data poisoning attacks whereas for natural robustness, we focus on extending ImageNet-C common corruptions for fog and snow that coherently and self-consistently perturbs the input data. Overall, we find both RGB and multispectral models are vulnerable to data poisoning attacks regardless of input or fusion architectures and that while physically-realizable natural perturbations still degrade model performance, the impact differs based on fusion architecture and input data.

Deep learning, multispectral images, multimodal fu↗

Data-Driven RANS Turbulence Closures for Forced Convection Flow in Reactor Downcomer Geometry

Recent progress in data-driven turbulence modeling has shown its potential to enhance or replace traditional equation-based Reynolds-averaged Navier-Stokes (RANS) turbulence models. Here, this work utilizes invariant neural network (NN) architectures to model Reynolds stresses and turbulent heat fluxes in forced convection flows (when the models can be decoupled). As the considered flow is statistically one dimensional, the invariant NN architecture for the Reynolds stress model reduces to the linear eddy viscosity model. To develop the data-driven models, direct numerical and RANS simulations in vertical planar channel geometry mimicking a part of the reactor downcomer are performed. Different conditions and fluids relevant to advanced reactors (sodium, lead, unitary-Prandtl-number fluid, and molten salt) constitute the training database. The models enabled accurate predictions of velocity and temperature, and compared to the baseline k–τ turbulence model with the simple gradient diffusion hypothesis, do not require tuning of the turbulent Prandtl number. The data-driven framework is implemented in the open-source graphics processing unit–accelerated spectral element solver nekRS and has shown the potential for future developments and consideration of more complex mixed convection flows.

21 SPECIFIC NUCLEAR REACTORS AND ASSOCIATED PLANTS↗

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

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

59 BASIC BIOLOGICAL SCIENCES↗

Characterization of mechanical discontinuities based on data-driven classification of compressional-wave travel times

Wave propagation and diffusive transport phenomena are influenced by the mechanical discontinuities in material. Here this study shows that certain bulk properties of the network of low-velocity mechanical discontinuities (e.g. air-filled cracks) in a material can be characterized by processing compressional-wave travel times using traditional data-driven classification techniques. To that end, we perform three tasks in chronological order: (1) use the discrete fracture network (DFN) method to create two-dimensional (2D) numerical models of crack-bearing material embedded with various types of low-velocity mechanical discontinuities, (2) use the fast marching method (FMM) to simulate the propagation of the wave/diffusion front from a single source through the 2D crack-bearing material to multiple receivers placed on the boundary of the material, and (3) train 9 data-driven classifiers to characterize the crack-bearing materials (i.e. bulk properties of the network of mechanical discontinuities in the crack-bearing material) by learning from the simulations of travel times detected by multiple receivers placed around the crack-bearing material. The classifiers identified the orientation, spatial distribution, and dispersion of the low-velocity mechanical discontinuities. Voting classifier performs the best among the 9 classifiers. For the characterization of bulk dispersion and distribution of discontinuities, the sensors located on the adjacent boundaries are more important; whereas for the characterization of bulk orientation of discontinuities, the sensors located on the opposite side are more important.

42 ENGINEERING↗

Measurement of a radial flow profile with eddy current flow meters and deep neural networks

Eddy current flow meters (ECFMs) measure flows of conductive fluids. Recent interest in ECFMs has increased due to applications in advanced nuclear reactors. ECFMs are well suited for such applications, as they can provide non-invasive measurements of flow in fluids that are often difficult to measure. Traditionally, ECFMs are operated using an alternating current at a single frequency, limiting ECFMs to measure average fluid velocities, blockages, or voids. Here, we expand the capabilities of ECFMs by measuring the fluid radial velocity profile of liquid mercury. To accomplish this, we made several ECFM sensitivity measurements at a range of frequencies. Different frequencies vary the electromagnetic skin depth of the device. By adjusting frequencies, we probed the fluid velocity at various radial locations and constructed a flow-velocity profile. The relationship between the ECFM measurements and velocity profile is nonlinear and requires solving an inverse problem. Using electromagnetic finite-element simulations to train a deep neural network (DNN), we created a model that provides a stable general relationship between the sensitivity measurements of an ECFM and the fluid velocity profile. Using ECFM measurements of liquid mercury, our DNN model calculates a flow profile that agrees well with computational fluid dynamics (CFD) simulations. This technique has potential to improve flow monitoring for optimization, safe operation of conductive fluid loops, and/or validating complex CFD models.

47 OTHER INSTRUMENTATION↗

Developing Deep Learning Models for System Remaining Useful Life Predictions: Application to Aircraft Engines

Prognostics and health management (PHM) is an important part of ensuring reliable operations of complex safety- critical systems. System-level remaining useful life (RUL) estimation is a much more complex problem than making estimations at the component level, and system-level RUL methodologies remain sparse in the literature. Model-based approaches have traditionally worked in the past for components such as capacitors, MOSFETs, batteries, or hard-drives (to name a few examples), but developing high fidelity dynamics models of cyber physical systems that can be used to study the effects of multiple degrading components in the system remains a challenging task. Some initial work on model-based System RUL predictions was demonstrated in Khorasgani, et al [1], but, to generalize the system-level prognostics problem, we have to resort to pure data driven and hybrid approaches. In this work, we propose an end-to-end data- driven framework for developing deep learning models to predict remaining useful life of cyber physical systems operating under unknown faulty conditions. The raw data is organized with a data schema that improves the model development process and down stream data analysis tasks. Due to the unknown faulty conditions, the raw sensor data is transformed into signals that expose the underlying degradation processes, which are then used for model development. Bayesian Optimization is used to tune the model parameters prior to training and validation. We show that this approach results in accurate predictions within 3 cycles to end of life (EOL). We demonstrate the effectiveness of our approach by applying it to the N-CMAPSS turbofan engine dataset recently released by NASA, which includes high fidelity degradation modeling, real world operating conditions, and a large set of fault operating modes.

Prognostics↗

Classification of Cloud Particle Imagery from Aircraft Platforms Using Convolutional Neural Networks

Abstract A vast amount of ice crystal imagery exists from a variety of field campaign initiatives that can be utilized for cloud microphysical research. Here, nine convolutional neural networks are used to classify particles into nine regimes on over 10 million images from the Cloud Particle Imager probe, including liquid and frozen states and particles with evidence of riming. A transfer learning approach proves that the Visual Geometry Group (VGG-16) network best classifies imagery with respect to multiple performance metrics. Classification accuracies on a validation dataset reach 97% and surpass traditional automated classification. Furthermore, after initial model training and preprocessing, 10 000 images can be classified in approximately 35 s using 20 central processing unit cores and two graphics processing units, which reaches real-time classification capabilities. Statistical analysis of the classified images indicates that a large portion (57%) of the dataset is unusable, meaning the images are too blurry or represent indistinguishable small fragments. In addition, 19% of the dataset is classified as liquid drops. After removal of fragments, blurry images, and cloud drops, 38% of the remaining ice particles are largely intersecting the image border (≥10% cutoff) and therefore are considered unusable because of the inability to properly classify and dimensionalize. After this filtering, an unprecedented database of 1 560 364 images across all campaigns is available for parameter extraction and bulk statistics on specific particle types in a wide variety of storm systems, which can act to improve the current state of microphysical parameterizations.

54 ENVIRONMENTAL SCIENCES↗

Analysis of an optical imaging system prototype for autonomously monitoring zooplankton in an aquaculture facility

Traditional approaches to biomonitoring in aquatic systems, such as sample collection, sorting, and identification, require significant time and effort, thereby limiting the spatiotemporal resolution of sample collection. Additionally, collection and preservation of samples for subsequent taxonomic identification and enumeration leads to mortality of organisms. Recent advances in technologies that utilize optical imaging and machine learning have provided new opportunities to expedite biomonitoring and lead to significant cost savings. These technologies can be advantageous to scientists or managers that conduct routine biomonitoring to inform operations, as in the case of aquaculture facilities. The Small Aquatic Organism optical imaging system (SAO) is a high-throughput optical imaging and classification prototype system that relies on computer vision and machine learning (Support Vector Machines, or SVMs) to autonomously identify and enumerate aquatic organisms. The SAO provides a more sustainable method of collecting large volumes of data and has the benefit of being used in situ. In this study, we tested the performance of the SAO in providing comparable results to manual zooplankton community monitoring in ten ponds at an aquaculture facility. We performed a side-by-side study comparing the sampling methods of plankton tow nets, where major zooplankton taxonomic classes were manually identified and enumerated, to sampling with the SAO. Vouchered samples were used to develop a training library for the SAO, where classes consisted of water boatman and zooplankton groups: cladocerans, copepod adults, copepod nauplii, and rotifers. SAO imagery was manually classified and compared with predicted results for validation. Accuracy for the SVM classifier of the SAO was 37.4 %. Convolutional Neural Networks (CNN) and Random Forest classifiers were also applied to SAO imagery and image features for comparison. The best CNN model and our Random Forest model had accuracies of 80.4 % and 46.6 % respectively. Challenges faced included the small size of copepod nauplii and rotifers and the limited resolution of the imaging camera, although there are tradeoffs between imaging resolution and the sample processing rate. Furthermore, our comparison shows that advancement in both optical imaging and ML are needed in order for the SAO prototype to yield comparable results to manual community monitoring in an aquaculture facility.

54 ENVIRONMENTAL SCIENCES↗

Global disease monitoring and forecasting with Wikipedia

Infectious disease is a leading threat to public health, economic stability, and other key social structures. Efforts to mitigate these impacts depend on accurate and timely monitoring to measure the risk and progress of disease. Traditional, biologically-focused monitoring techniques are accurate but costly and slow; in response, new techniques based on social internet data, such as social media and search queries, are emerging. These efforts are promising, but important challenges in the areas of scientific peer review, breadth of diseases and countries, and forecasting hamper their operational usefulness. We examine a freely available, open data source for this use: access logs from the online encyclopedia Wikipedia. Using linear models, language as a proxy for location, and a systematic yet simple article selection procedure, we tested 14 location-disease combinations and demonstrate that these data feasibly support an approach that overcomes these challenges. Specifically, our proof-of-concept yields models with up to 0.92, forecasting value up to the 28 days tested, and several pairs of models similar enough to suggest that transferring models from one location to another without re-training is feasible. Based on these preliminary results, we close with a research agenda designed to overcome these challenges and produce a disease monitoring and forecasting system that is significantly more effective, robust, and globally comprehensive than the current state of the art.

59 BASIC BIOLOGICAL SCIENCES↗

Investigation of Intelligent Resource Management for Aviation Communications

The emergence of new aerial vehicles into the airspace as part of new initiatives, such as Advanced Air Mobility (AAM), will place growing demand for spectrum resources to support airspace operations. The traditional approach of using fixed channel allocations within standard service volumes will not allow for dynamic and efficient distribution of resources based on airspace demand; consequently, a new approach to aviation spectrum management will be required to meet the anticipated needs of airspace users. The National Aeronautics and Space Administration (NASA) is investigating the application of advanced concepts to implement a novel spectrum management approach that allows for the intelligent utilization of aviation spectrum throughout the airspace while maintaining the quality of service prescribed by aeronautical standards. This technical investigation evaluates the dynamic assignment of resources for both air-ground and air-air communication links applicable to both the emerging AAM initiative as well as the existing air traffic management system. The performance of the proposed spectrum management concepts will be evaluated using a custom modeling and simulation capability that is currently under development. The implementation of these approaches is anticipated to facilitate increased spectrum utilization efficiency and enhanced airspace capacity, which will better serve the needs of future applications.

Aeronautics↗

Developing Methods for Exercise System Kinematics Tracking

BACKGROUND How to quantify the load and forces produced by exercise equipment and their Vibration Isolation and Stabilization (VIS) platforms in-flight is an active area of investigation. Kinematic tracking paired with system modeling can provide insights as well as verification and validation of simulations used for system design and development. Traditional motion capture methods can require significant cost in equipment procurement and crew-time, but newer lessons learned can be leveraged [1]. The VIS systems of current and future exercise hardware on the International Space Station (ISS) such as the Cycle Ergometer with Vibration Isolation System (CEVIS) and the European Enhanced Exploration Exercise Device (E4D) are not currently outfitted with IMUs or similar measurement devices. Video-based methods would enable use of multi-purpose, crew-familiar flight equipment. An initial exploration of video-based solutions was performed utilizing 2-camera video from crew cycling on Teal-CEVIS on the ISS. METHODS AND RESULTS Our group has scoped a variety of video-based object tracking methods. To date, we have primarily investigated computer vision toolkits such as openCV. Techniques explored include key-point detection, background subtraction, region-of interest tracking, color-based tracking, tag masking and tracking, and corner detection. Although object-tracking and 6D pose estimation is a rich field, space applications are a unique problem that are challenging for existing software and toolkits. The majority of the existing object-tracking applications involve vehicles/pedestrians and household objects with simple backgrounds. We have identified the following features which pose particular challenges for on-station exercise equipment tracking: Busy and visually cluttered background Low-textured tracking object with relatively small motions Occlusions and motion by human subject and loose, floating objects Limited number of video cameras with no fixed global references Limited ability to add tags, markers, or visual references to the tracking object Lack of training data for Machine Learning (ML) algorithms CONCLUSION We will summarize the efficacy of techniques tested for a ground mock-trial and the on-station exercise trial. It is likely that human-in-loop feedback or a conglomerate of methods is required. ML-based methods, like those implemented for human body tracking [2], may still be a viable option, but more training data and validation is needed.

L B Nilsson↗

Automated Waterbox Inspection for Nuclear Power Plants Using Computer Vision - Based Change Detection

Nuclear power plant waterboxes require regular inspection for leaks, missing components, and structural damage during maintenance outages. Traditional manual inspection is time-consuming and poses safety risks from confined space entry. We developed an automated computer vision system for drone-based waterbox inspection in partnership with Florida Light and Power. Our approach uses feature detection and matching to identify critical changes between baseline and current inspection images, automatically flagging additions (leaks/debris), removals (missing plugs), and translations (displaced components) while compensating for drone movement and environmental variations. We systematically evaluated six feature matching methods, from classical approaches (SIFT+BF) to state-of-the-art neural networks (SuperPoint+SuperGlue), using both standard benchmarks (HPatches) and waterbox-specific validation with real-world augmentations. SuperPoint+SuperGlue achieved superior performance with 7.82 pixels RMSE and 100% success rate—2.8x better accuracy than our baseline. While the pre-trained model has commercial licensing restrictions for nuclear deployment, our findings validate this architecture for custom training. We implemented a real-time GUI demonstrating the SIFT+BF approach for immediate deployment, processing drone feeds at 30 FPS with color-coded change visualization. Future work includes training a custom SuperPoint+SuperGlue model on waterbox data and integrating Vision-Language Models for automated reporting and maintenance guidance.

46 - INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AN↗

Interacting dust grains in complex plasmas: Ion wake formation and the electric potential

Dust grains have been used as minimally invasive probes to determine plasma parameters including the plasma density, temperature, and electric field in a plasma discharge. However, the dust grains in a plasma generate local potential disturbances due to the collection of charge and the subsequent electrostatic interactions between the dust and charged plasma particles. Dust grains in close proximity to one another exhibit interesting non-reciprocal interactions and self-organize into structures such as one-dimensional filamentary chains, two-dimensional “zigzags,” and three-dimensional helices, among others. The formation of these structures suggests that although the dust grains may be less invasive than traditional plasma probes, the disturbance to the local plasma environment introduced by dust grains is non-trivial. Commonly used analytic forms of the electric potential describing complex plasmas have failed to resolve the near-dust region, and as a result are insufficient to provide insight about the formation of complex dust structures. Here, we use an N-body simulation to compute the electric potential from ion densities near various dust grain configurations. We provide an alternative description to the standard analytic model for the electric potential of dust and ion wakes based on a Gaussian shaped cloud of ions. The electric potential obtained from simulations is used to identify minimum energy configurations for two and three dust grains. It is further demonstrated that the minimum potential region identified for N dust grains and their associated ion wakes does not predict the minimum-energy configuration of N + 1 dust grains.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗

PRIME: An evaluation framework for protein representation inference and generalization in viral mutation space

Background Protein language models (PLMs) have revolutionized protein fitness prediction, yet their application to rapidly evolving viral pathogens is often confounded by extreme sequence homology. This homology leads to “data leakage” in standard random validation splits, yielding inflated performance metrics that fail to translate into real-world biosurveillance utility. Results We present Protein Representation Inference for Mutation Evaluation (PRIME), a framework that integrates domain-specific fine-tuning with a rigorous position-stratified validation protocol to evaluate viral threats. Using a dataset of 347,432 SARS-CoV-2 receptor binding domain (RBD) sequences, we demonstrate that while random training data split yields deceptive R 2 values (> 0.90), they fail to generalize to novel mutational sites. By benchmarking models up to 650 M parameters, we show that domain-specific fine-tuning of the ESM-C 600 M model with correctly stratified data provides an initial demonstration of predictive signal for binding affinity and expression at unseen mutational sites of binding affinity and expression on unseen sites (R 2 ~0.23), a significant advancement over base foundation models which exhibit no predictive power (R 2 <0). PRIME’s embedding-based clustering identified 3.03% of bat coronavirus sequences as candidates for further experimental prioritization based on their functional similarity to human-infective strains in embedding space, offering a perspective complementary to traditional phylogenetic methods. Conclusion PRIME establishes a new benchmark for the application of PLMs in pathogen surveillance. Our findings demonstrate that state-of-the-art models and fine-tuning, when paired with stratified validation, provide biologically meaningful insights into pathogen evolution and zoonotic risk.

59 BASIC BIOLOGICAL SCIENCES↗

Developing Methods for Exercise System Kinematic Tracking

BACKGROUND How to quantify the load and forces produced by exercise equipment and their Vibration Isolation and Stabilization (VIS) platforms in-flight is an active area of investigation. Kinematic tracking paired with system modeling can provide insights as well as verification and validation of simulations used for system design and development. Traditional motion capture methods can require significant cost in equipment procurement and crew-time, but newer lessons learned can be leveraged [1]. The VIS systems of current and future exercise hardware on the International Space Station (ISS) such as the Cycle Ergometer with Vibration Isolation System (CEVIS) and the European Enhanced Exploration Exercise Device (E4D) are not currently outfitted with IMUs or similar measurement devices. Video-based methods would enable use of multi-purpose, crew-familiar flight equipment. An initial exploration of video-based solutions was performed utilizing 2-camera video from crew cycling on Teal-CEVIS on the ISS. METHODS AND RESULTS Our group has scoped a variety of video-based object tracking methods. To date, we have primarily investigated computer vision toolkits such as open CV. Techniques explored include key-point detection, background subtraction, region-of interest tracking, color-based tracking, tag masking and tracking, and corner detection. Although object-tracking and 6D pose estimation is a rich field, space applications are a unique problem that are challenging for existing software and toolkits. The majority of the existing object-tracking applications involve vehicles/pedestrians and household objects with simple backgrounds. We have identified the following features which pose particular challenges for on-station exercise equipment tracking: 1. Busy and visually cluttered background 2. Low-textured tracking object with relatively small motions 3. Occlusions and motion by human subject and loose, floating objects 4. Limited number of video cameras with no fixed global references 5. Limited ability to add tags, markers, or visual references to the tracking object 6. Lack of training data for Machine Learning (ML) algorithms CONCLUSION We will summarize the efficacy of techniques tested for a ground mock-trial and the on-station exercise trial. It is likely that human-in-loop feedback or a conglomerate of methods is required. ML-based methods, like those implemented for human body tracking [2], may still be a viable option, but more training data and validation is needed.

L Nilsson↗