Search NASA⌕ Search

SEARCH · Search NASA

Results for “algorithm selection”

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 307 records · Page 17
All sourcesNASA NTRSDOE OSTI
DOE OSTI2020

Benders Cut Classification via Support Vector Machines for Solving Two-Stage Stochastic Programs

In this work, we consider Benders decomposition for solving two-stage stochastic programs with complete recourse based on finite samples of the uncertain parameters. We define the Benders cuts binding at the final optimal solution or the ones significantly improving bounds over iterations as valuable cuts. We propose a learning-enhanced Benders decomposition (LearnBD) algorithm, which adds a cut classification step in each iteration to selectively generate cuts that are more likely to be valuable cuts. The LearnBD algorithm includes two phases: (i) sampling cuts and collecting information from training problems and (ii) solving testing problems with a support vector machine (SVM) cut classifier. We run the LearnBD algorithm on instances of capacitated facility location and multicommodity network design under uncertain demand. Our results show that SVM cut classifier works effectively for identifying valuable cuts, and the LearnBD algorithm reduces the total solving time of all instances for different problems with various sizes and complexities.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2021

Calorimetric classification of track-like signatures in liquid argon TPCs using MicroBooNE data

The MicroBooNE liquid argon time projection chamber located at Fermilab is a neutrino experiment dedicated to the study of short-baseline oscillations, the measurements of neutrino cross sections in liquid argon, and to the research and development of this novel detector technology. Accurate and precise measurements of calorimetry are essential to the event reconstruction and are achieved by leveraging the TPC to measure deposited energy per unit length along the particle trajectory, with mm resolution. We describe the non-uniform calorimetric reconstruction performance in the detector, showing dependence on the angle of the particle trajectory. Such non-uniform reconstruction directly affects the performance of the particle identification algorithms which infer particle type from calorimetric measurements. This work presents a new particle identification method which accounts for and effectively addresses such non-uniformity. The newly developed method shows improved performance compared to previous algorithms, illustrated by a 93.7% proton selection efficiency and a 10% muon mis-identification rate, with a fairly loose selection of tracks performed on beam data. The performance is further demonstrated by identifying exclusive final states in ν μ CC interactions. While developed using MicroBooNE data and simulation, this method is easily applicable to future LArTPC experiments, such as SBND, ICARUS, and DUNE.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗
DOE OSTI2021

Z-Sequence: photometric redshift predictions for galaxy clusters with sequential random k-nearest neighbours

ABSTRACT We introduce Z-Sequence, a novel empirical model that utilizes photometric measurements of observed galaxies within a specified search radius to estimate the photometric redshift of galaxy clusters. Z-Sequence itself is composed of a machine learning ensemble based on the k-nearest neighbours algorithm. We implement an automated feature selection strategy that iteratively determines appropriate combinations of filters and colours to minimize photometric redshift prediction error. We intend for Z-Sequence to be a standalone technique but it can be combined with cluster finders that do not intrinsically predict redshift, such as our own DEEP-CEE. In this proof-of-concept study, we train, fine-tune, and test Z-Sequence on publicly available cluster catalogues derived from the Sloan Digital Sky Survey. We determine the photometric redshift prediction error of Z-Sequence via the median value of |Δ$z$|/(1 + $z$) (across a photometric redshift range of 0.05 ≤ $z$ ≤ 0.6) to be ∼0.01 when applying a small search radius. The photometric redshift prediction error for test samples increases by 30–50 per cent when the search radius is enlarged, likely due to line-of-sight interloping galaxies. Eventually, we aim to apply Z-Sequence to upcoming imaging surveys such as the Legacy Survey of Space and Time to provide photometric redshift estimates for large samples of as yet undiscovered and distant clusters.

Chan, Matthew C.↗
DOE OSTI2021

Examination of Semi-Analytical Solution Methods in the Coarse Operator of Parareal Algorithm for Power System Simulation

With continuing advances in high-performance parallel computing platforms, parallel algorithms have become powerful tools for development of faster than real-time power system dynamic simulations. In particular, it has been demonstrated in recent years that parallel-in-time (Parareal) algorithms have the potential to achieve such an ambitious goal. Here, the selection of a fast and reasonably accurate coarse operator of the Parareal algorithm is crucial for its effective utilization and performance. This paper examines semi-analytical solution (SAS) methods as the coarse operators of the Parareal algorithm and explores performance of the SAS methods to the standard numerical time integration methods. Two promising time-power series-based SAS methods were considered; Adomian decomposition method and Homotopy analysis method with a windowing approach for improving the convergence. Numerical performance case studies on 10-generator 39-bus system and 327-generator 2383-bus system were performed for these coarse operators over different disturbances, evaluating the number of Parareal iterations, computational time, and stability of convergence. All the coarse operators tested with different scenarios have converged to the same corresponding true solution (if they are convergent) and the SAS methods provide comparable computational speed, while having more stable convergence to the true solution in many cases.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2019

TTHRESH: Tensor Compression for Multidimensional Visual Data

Memory and network bandwidth are decisive bottlenecks when handling high-resolution multidimensional data sets in visualization applications, and they increasingly demand suitable data compression strategies. In this paper, we introduce a novel lossy compression algorithm for multidimensional data over regular grids. It leverages the higher-order singular value decomposition (HOSVD), a generalization of the SVD to three dimensions and higher, together with bit-plane, run-length and arithmetic coding to compress the HOSVD transform coefficients. Our scheme degrades the data particularly smoothly and achieves lower mean squared error than other state-of-the-art algorithms at low-to-medium bit rates, as it is required in data archiving and management for visualization purposes. Further advantages of the proposed algorithm include very fine bit rate selection granularity and the ability to manipulate data at very small cost in the compression domain, for example to reconstruct filtered and/or subsampled versions of all (or selected parts) of the data set.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2022

Comprehensive compartmental model and calibration algorithm for the study of clinical implications of the population-level spread of COVID-19: a study protocol

The complex dynamics of the coronavirus disease 2019 (COVID-19) pandemic has made obtaining reliable long-term forecasts of the disease progression difficult. Simple mechanistic models with deterministic parameters are useful for short-term predictions but have ultimately been unsuccessful in extrapolating the trajectory of the pandemic because of unmodelled dynamics and the unrealistic level of certainty that is assumed in the predictions. We propose a 22-compartment epidemiological model that includes compartments not previously considered concurrently, to account for the effects of vaccination, asymptomatic individuals, inadequate access to hospital care, post-acute COVID-19 and recovery with long-term health complications. Additionally, new connections between compartments introduce new dynamics to the system and provide a framework to study the sensitivity of model outputs to several concurrent effects, including temporary immunity, vaccination rate and vaccine effectiveness. Subject to data availability for a given region, we discuss a means by which population demographics (age, comorbidity, socioeconomic status, sex and geographical location) and clinically relevant information (different variants, different vaccines) can be incorporated within the 22-compartment framework. Considering a probabilistic interpretation of the parameters allows the model's predictions to reflect the current state of uncertainty about the model parameters and model states. We propose the use of a sparse Bayesian learning algorithm for parameter calibration and model selection. This methodology considers a combination of prescribed parameter prior distributions for parameters that are known to be essential to the modelled dynamics and automatic relevance determination priors for parameters whose relevance is questionable. This is useful as it helps prevent overfitting the available epidemiological data when calibrating the parameters of the proposed model. Population-level administrative health data will serve as partial observations of the model states.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2019

R and DE Robotic Sensor Intern Team: Remote 3D Mapping Overview

The Department of Energy (DOE) nuclear complex includes many hazardous and challenging environments that must be inspected remotely and routinely for structural integrity evaluation and long-term planning purposes. The H-Canyon Air Exhaust (HCAEX) Tunnel biannual inspection is an example of such an environment. Presently inspections are performed by teleoperated robotic crawlers provide low resolution video feedback to the structural engineers. Advanced sensors such as Lidar and panospheric hi-res cameras have the potential to provide additional valuable data in future inspections. UT-Austin Lidar work in support of an H-Canyon deployment began with the DOE EM sponsored H-Canyon Integrated Research Project. The R and DE Robotic Sensor intern team includes two of the UT-Austin Masters students working on Lidar development to facilitate the pulling of university developed solutions to the field. The goal of this project is to develop a suite of sensors that could be used to gather advanced data in future HCAEX tunnel inspections. Of particular interest is the ability to map the tunnel walls at an accuracy that will allow for the comparison of two scans performed at different time periods to estimate the concrete erosion rate. Additionally, the development of the 3D point cloud in the GPS denied environment is the first step in being able to collect and overlay other 3D data such as radiation mapping. Project specific goals include: - Design and develop 3D mapping sensor suite. Merge Lidar point cloud with high res camera images Incorporate Inertial Measurement Unit (IMU) to assist with positioning. - Develop sensor software and user GUI Sensor data collection and integration software User GUI for reach back system. - Test solution on crawler in tunnel test bed Use crawler base similar to H-Canyon planned crawler Design and build test bed simulating tunnel conditions. To facilitate rapid sensor integration, software coding and user GUI development, the Robot Operating System (ROS) was employed as the development platform. ROS is a set of open source software libraries and tools that assist with the building of robot applications. ROS includes drivers for many sensors, state-of-the-art algorithms, and powerful developer tools. Sensors selected for the summer intern solution included assessment as to whether they possessed ROS drivers and associated sample code. Additionally, the ROS 3D Robot Visualizer (rviz) tool has been employed.

12 MANAGEMENT OF RADIOACTIVE AND NON-RADIOACTIVE W↗
DOE OSTI2023

Encoding nonlinear and unsteady aerodynamics of limit cycle oscillations using nonlinear sparse Bayesian learning

This article investigates the applicability of a recently proposed, nonlinear sparse Bayesian learning (NSBL) algorithm to identify and estimate the complex aerodynamics of limit cycle oscillations. NSBL provides a semi-analytical framework for determining the data-optimal sparse model nested within a (potentially) over-parameterized model. This is particularly relevant to nonlinear dynamical systems where modelling approaches involve the use of physics-based and data-driven components. In such cases, the data-driven components, where analytical descriptions of the physical processes are not readily available, are often prone to overfitting, meaning that the empirical aspects of these models will often involve the calibration of an unnecessarily large number of parameters. While an overparameterized model may fit the observed data well, such models may be inadequate for making predictions in regimes that are different from those wherein the data were recorded. In view of this, it is desirable to not only calibrate the model parameters, but also identify the optimal compromise between data fit and model complexity. In this article, we exhibit the optimal model discovery for an aeroelastic system wherein the structural dynamics are well-known and described by a differential equation model, coupled with a semi-empirical aerodynamic model for laminar separation flutter, resulting in low-amplitude limit cycle oscillations (LCO). To illustrate the performance of the algorithm, in this article, we use synthetic data and demonstrate the ability of the algorithm to correctly rediscover the optimal model and model parameters, given a known data-generating model. The synthetic data are generated from a forward simulation of a known differential equation model with parameters selected so as to mimic the dynamics observed in wind-tunnel experiments. Subsequently, we demonstrate the performance of the algorithm for model selection using noisy LCO data from wind tunnel experiments. As there is no ground truth available for the experimental data case, we provide a comparison between NSBL and Bayesian model selection to validate the results, and demonstrate the use of NSBL as an efficient alternative to traditional methods.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2020

Clustering Analysis of Commercial Vehicles Using Automatically Extracted Features from Time Series Data

Standard of practice approaches to time series cluster analysis involve careful feature engineering, often utilizing expert input to tune and select features by hand. In many cases, expert input may not be readily available, or there may not yet exist a community consensus on the ideal features for a given application. This paper compares the results of several cluster analysis methods, using both hand selected features and those extracted automatically, when applied to large geospatial time series telematics data from commercial trucking fleets. The impacts of feature selection, dimensionality reduction, and choice of clustering algorithm on the quality of clustering results are explored. Results from this analysis confirm prior results that domain agnostic features are competitive with the hand engineered features with respect to clustering quality metrics. These results also provide new insight into the most successful strategies for identifying structure in large unstructured vehicle telematics data, and suggest that time series clustering using automatic feature extraction can be an effective approach to extract structure from large scale geospatial time series data in cases when hand selected features are not available.

33 ADVANCED PROPULSION SYSTEMS↗
DOE OSTI2025

Model-based Hierarchical Reinforcement Learning for Improved Physical Security Design: A Prototype

Prior work in FY24 developed an adversarial AI agent aid in path analysis of physical protection systems. This agent, trained using a model-based reinforcement learning algorithm, was able to successfully learn the most vulnerable path in facilities. It was able to extend the current state of practice for physical protection design by exhibiting dynamic behavior based on current environmental conditions. Whereas PathTrace largely performs a static, graph-based analysis, the AI agent was able to make decisions based on relative position in the facility, current conditions (was the adversarial agnet discovered?), and proximity to secondary targets. The agent demonstrated some novel capabilities, but had limitations that need to be resolved before it can be used for production purposes. For example, the adversarial agent generalizes poorly and takes a relatively long time to train. Nonetheless, there is still considerable promise for developing the adversarial agent further in order to explore even richer, more dynamic behaviors (e.g., adversary motivations, environmental debris, and more). This work considers a complementary idea; development of a planning agent. The planning agent is envisioned as an auto-complete-like tool that can help accelerate security system design by human experts. The agent would respect existing barriers and sensors placed by a human expert while offering cost-effective suggestions (i.e., implicitly balancing effectiveness with cost) to improve the design. The goal is for this agent to be part of an expert’s toolbox, not to totally upend the current state-of-practice, or to displace human experts. The ultimate goal would be concurrent training of both the adversarial and planning agent together, to learn entirely through self-play. This would represent an entirely new way of performing system deign. We selected a hierarchical, model-based reinforcement learning algorithm to serve as the planning agent. This is an extension of concepts used in the prior FY24 adversarial agent work. There, we had a single agent acting an environment. Here, we have two different sub-agents (policies), working together, to form a complete agent. There is a manager policy, which can select abstract goals on slower time scales, and a worker, which performs primitive actions to reach goals selected by the manager. It is worth noting that this class of algorithm is challenging to work with. From our understanding, our work is one of the first successful uses of model-based reinforcement learning (MBRL) in nuclear energy1 , and likely the first hierarchical model-based reinforcement learning application in nuclear energy. Further, this work is one of the first known attempts to apply AI to perform a design tasks in nuclear energy. Consequently, there were significant implementation challenges and the bulk of the work was focused on successful implementation and algorithm design. The results presented here are very low technology readiness level as a consequence of the lack of related literature, but still represent a significant step forward in the pursuit of applied AI for design.

42 ENGINEERING↗
DOE OSTI2022

Optical selection bias and projection effects in stacked galaxy cluster weak lensing

ABSTRACT Cosmological constraints from current and upcoming galaxy cluster surveys are limited by the accuracy of cluster mass calibration. In particular, optically identified galaxy clusters are prone to selection effects that can bias the weak lensing mass calibration. We investigate the selection bias of the stacked cluster lensing signal associated with optically selected clusters, using clusters identified by the redMaPPer algorithm in the Buzzard simulations as a case study. We find that at a given cluster halo mass, the residuals of redMaPPer richness and weak lensing signal are positively correlated. As a result, for a given richness selection, the stacked lensing signal is biased high compared with what we would expect from the underlying halo mass probability distribution. The cluster lensing selection bias can thus lead to overestimated mean cluster mass and biased cosmology results. We show that the lensing selection bias exhibits a strong scale dependence and is approximately 20–60 per cent for ΔΣ at large scales. This selection bias largely originates from spurious member galaxies within ±20–60 $h^{-1}\, \rm Mpc$ along the line of sight, highlighting the importance of quantifying projection effects associated with the broad redshift distribution of member galaxies in photometric cluster surveys. While our results qualitatively agree with those in the literature, accurate quantitative modelling of the selection bias is needed to achieve the goals of cluster lensing cosmology and will require synthetic catalogues covering a wide range of galaxy–halo connection models.

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2021

Scalable Approaches to Selecting Key Entities in Large Networked Infrastructure Systems

This work aims at bringing advances in discrete optimization algorithms to solving practical engineering problems at scale. Often times, in many engineering design problems, there is a need to select a small set of influential or representative elements from a large ground set of entities in an optimal fashion. Submodular optimization provides for a formal way to solve such problems. Common examples with infrastructure systems involve sensor placement and identification of key entities with certain objectives. However, scaling these approaches to large infrastructure systems can be challenging because of the high computational complexity of the overall framework that include the optimization algorithms as well as high-complexity compute-oracles that provide the necessary objective function values. In this work, we explore a well-studied and widely-applicable paradigm, namely leader-selection in a multi-agent networked setting in the context of scalable methodologies. We demonstrate novel frameworks that utilize variations of accelerated submodular optimization algorithms along with linear-algebraic methods that can help accelerate the oracle computations. We further explore this combination in conjunction with graph partitioning paradigms to take advantage of the accelerated algorithms in a distributed setting. Finally we demonstrate the key findings on a practical problem in an operational setting. For this, we leverage an example road network with approximately 18k nodes and 27k edges in a traffic control application, where we seek a limited number of k=200 key intersections. This problem can be solved in a serial setting in just under 5 hours providing more than 2 orders of magnitude speed-up over methods that do not consider acceleration techniques.

Visweswara Sathanur, Arun↗
DOE OSTI2022

Quantum model learning agent: characterisation of quantum systems through machine learning

Accurate models of real quantum systems are important for investigating their behaviour, yet are difficult to distil empirically. Here, we report an algorithm—the quantum model learning agent (QMLA)—to reverse engineer Hamiltonian descriptions of a target system. We test the performance of QMLA on a number of simulated experiments, demonstrating several mechanisms for the design of candidate Hamiltonian models and simultaneously entertaining numerous hypotheses about the nature of the physical interactions governing the system under study. QMLA is shown to identify the true model in the majority of instances, when provided with limited a priori information, and control of the experimental setup. Our protocol can explore Ising, Heisenberg and Hubbard families of models in parallel, reliably identifying the family which best describes the system dynamics. We demonstrate QMLA operating on large model spaces by incorporating a genetic algorithm to formulate new hypothetical models. The selection of models whose features propagate to the next generation is based upon an objective function inspired by the Elo rating scheme, typically used to rate competitors in games such as chess and football. In all instances, our protocol finds models that exhibit F 1 score ≥ 0.88 when compared with the true model, and it precisely identifies the true model in 72% of cases, whilst exploring a space of over 250 000 potential models. By testing which interactions actually occur in the target system, QMLA is a viable tool for both the exploration of fundamental physics and the characterisation and calibration of quantum devices.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2018

Shared autonomy for low–cost underwater vehicles

This field report presents an overview of the development and testing of a semi-autonomous underwater vehicle (sAUV). The work presented here is aimed at bridging the gap between current remotely operated vehicles and autonomous research platforms by developing shared autonomy capabilities for low-cost underwater vehicles. We use commercially available components and open-source software interfaces to provide a wider range of capabilities for underwater autonomy research at a lower cost than previously available systems. We describe the overall structure of the system, discuss its capabilities, and provide results demonstrating system performance. We place particular emphasis on shared autonomy, where a human operator is assisted in controlling an underwater tethered vehicle. We present three capabilities developed for the sAUV: (a) an assisted control mode that provides a variable level of assistance using an on-line estimate of user skill level, (b) a planner to generate paths that avoid tether entanglement, and (c) a sonar processing algorithm that identifies informative sonar images for selecting features for 3D scene reconstruction. Here, the vehicle has been deployed on five off-shore and near-shore marine field deployments since 2015, and this report includes selected results from four of those trials to demonstrate the capabilities and limitations of the sAUV system.

16 TIDAL AND WAVE POWER↗
DOE OSTI2022

Comparison of Machine Learning and Deep Learning for View Identification from Cardiac Magnetic Resonance Images

Background: Artificial intelligence is increasingly utilized to aid in the interpretation of cardiac magnetic resonance (CMR) studies. One of the first steps is the identification of the imaging plane depicted, which can be achieved by both deep learning (DL) and classical machine learning (ML) techniques without user input. We aimed to compare the accuracy of ML and DL for CMR view classification and to identify potential pitfalls during training and testing of the algorithms. Methods: To train our DL and ML algorithms, we first established datasets by retrospectively selecting 200 CMR cases. The models were trained using two different cohorts (passively and actively curated) and applied data augmentation to enhance training. Once trained, the models were validated on an external dataset, consisting of 20 cases acquired at another center. We then compared accuracy metrics and applied class activation mapping (CAM) to visualize DL model performance. Results: The DL and ML models trained with the passively-curated CMR cohort were 99.1% and 99.3% accurate on the validation set, respectively. However, when tested on the CMR cases with complex anatomy, both models performed poorly. After training and testing our models again on all 200 cases (active cohort), validation on the external dataset resulted in 95% and 90% accuracy, respectively. The CAM analysis depicted heat maps that demonstrated the importance of carefully curating the datasets to be used for training. Conclusions: Both DL and ML models can accurately classify CMR images, but DL outperformed ML when classifying images with complex heart anatomy.

artificial intelligence↗
DOE OSTI2025

Benchmarking optimization methods for materials research: Gradient descent and Bayesian optimization for lithium-ion battery aging diagnostics

Accurate and efficient parameter estimation is essential for battery diagnostics and aging analysis. Here, in this study, we compare two optimization-based approaches—gradient descent and Bayesian optimization—for extracting parameters from differential voltage analysis in lithium-ion batteries. While these techniques are widely used, their relative strengths and limitations for this application are not well understood. The study evaluates the trade-offs between these methods in terms of result quality, computational cost, and reliability within this specific application. The diagnostic results from our battery data suggest adopting gradient descent as an initial method for rapid and efficient analysis, while employing more stable optimization techniques, such as Bayesian optimization, as a verification step to mitigate potential instability. Comparing the two methods provides information on algorithmic choice, while inspiring further discussions on selecting appropriate techniques for specific research tasks.

Zhao, Ziqing [Boston Univ., MA (United States)] (O↗
DOE OSTI2018

Machine-Learning Identification of the Sensing Descriptors Relevant in Molecular Interactions with Metal Nanoparticle-Decorated Nanotube Field-Effect Transistors

We report that carbon nanotube-based field-effect transistors (NTFETs) are ideal sensor devices as they provide rich information regarding carbon nanotube interactions with target analytes and have potential for miniaturization in diverse applications in medical, safety, environmental, and energy sectors. Herein, we investigate chemical detection with cross-sensitive NTFETs sensor arrays comprised of metal nanoparticle-decorated single-walled carbon nanotubes (SWCNTs). By combining analysis of NTFET device characteristics with supervised machine-learning algorithms, we have successfully discriminated among five selected purine compounds, adenine, guanine, xanthine, uric acid, and caffeine. Interactions of purine compounds with metal nanoparticle-decorated SWCNTs were corroborated by density functional theory calculations. Furthermore, by testing a variety of prepared as well as commercial solutions with and without caffeine, our approach accurately discerns the presence of caffeine in 95% of the samples with 48 features using a linear discriminant analysis and in 93.4% of the samples with only 11 features when using a support vector machine analysis. Lastly, we also performed recursive feature elimination and identified three NTFET parameters, transconductance, threshold voltage, and minimum conductance, as the most crucial features to analyte prediction accuracy.

36 MATERIALS SCIENCE↗
DOE OSTI2022

DefectTrack: a deep learning-based multi-object tracking algorithm for quantitative defect analysis of in-situ TEM videos in real-time

Abstract In-situ irradiation transmission electron microscopy (TEM) offers unique insights into the millisecond-timescale post-cascade process, such as the lifetime and thermal stability of defect clusters, vital to the mechanistic understanding of irradiation damage in nuclear materials. Converting in-situ irradiation TEM video data into meaningful information on defect cluster dynamic properties (e.g., lifetime) has become the major technical bottleneck. Here, we present a solution called the DefectTrack , the first dedicated deep learning-based one-shot multi-object tracking (MOT) model capable of tracking cascade-induced defect clusters in in-situ TEM videos in real-time. DefectTrack has achieved a Multi-Object Tracking Accuracy (MOTA) of 66.43% and a Mostly Tracked (MT) of 67.81% on the test set, which are comparable to state-of-the-art MOT algorithms. We discuss the MOT framework, model selection, training, and evaluation strategies for in-situ TEM applications. Further, we compare the DefectTrack with four human experts in quantifying defect cluster lifetime distributions using statistical tests and discuss the relationship between the material science domain metrics and MOT metrics. Our statistical evaluations on the defect lifetime distribution suggest that the DefectTrack outperforms human experts in accuracy and speed.

42 ENGINEERING↗