Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “supervised training”

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 253 records · Page 14

Automatic Detection of Large-scale Flux Ropes and Their Geoeffectiveness with a Machine-learning Approach

Detecting large-scale flux ropes (FRs) embedded in interplanetary coronal mass ejections (ICMEs) and assessing their geoeffectiveness are essential, since they can drive severe space weather. At 1 au, these FRs have an average duration of 1 day. Their most common magnetic features are large, smoothly rotating magnetic fields. Their manual detection has become a relatively common practice over decades, although visual detection can be time-consuming and subject to observer bias. Our study proposes a pipeline that utilizes two supervised binary classification machine-learning models trained with solar wind magnetic properties to automatically detect large-scale FRs and additionally determine their geoeffectiveness. The first model is used to generate a list of autodetected FRs. Using the properties of the southward magnetic field, the second model determines the geoeffectiveness of FRs. Our method identifies 88.6% and 80% of large-scale ICMEs (duration 1day) observed at 1au by the Wind and the Solar TErrestrial RElations Observatory missions, respectively. While testing with continuous solar wind data obtained from Wind, our pipeline detected 56 of the 64 large-scale ICMEs during the 2008–2014 period (recall = 0.875), but also many false positives (precision = 0.56), as we do not take into account any additional solar wind properties other than the magnetic properties. We find an accuracy of 0.88 when estimating the geoeffectiveness of the autodetected FRs using our method. Thus, in space-weather nowcasting and forecasting at L1 or any planetary missions, our pipeline can be utilized to offer a first-order detection of large-scale FRs and their geoeffectiveness.

Sanchita Pal↗

Deep learning with mixup augmentation for improved pore detection during additive manufacturing

In additive manufacturing (AM), process defects such as keyhole pores are difficult to anticipate, affecting the quality and integrity of the AM-produced materials. Hence, considerable efforts have aimed to predict these process defects by training machine learning (ML) models using passive measurements such as acoustic emissions. This work considered a dataset in which keyhole pores of a laser powder bed fusion (LPBF) experiment were identified using X-ray radiography and then registered both in space and time to acoustic measurements recorded during the LPBF experiment. Due to AM’s intrinsic process controls, where a pore-forming event is relatively rare, the acoustic datasets collected during monitoring include more non-pores than pores. In other words, the dataset for ML model development is imbalanced. Moreover, this imbalanced and sparse data phenomenon remains ubiquitous across many AM monitoring schemes since training data is nontrivial to collect. Hence, we propose a machine learning approach to improve this dataset imbalance and enhance the prediction accuracy of pore-labeled data. Specifically, we investigate how data augmentation helps predict pores and non-pores better. This imbalance is improved using recent advances in data augmentation called Mixup, a weak-supervised learning method. Convolutional neural networks (CNNs) are trained on original and augmented datasets, and an appreciable increase in performance is reported when testing on five different experimental trials. When ML models are trained on original and augmented datasets, they achieve an accuracy of 95% and 99% on test datasets, respectively. We also provide information on how dataset size affects model performance. Lastly, we investigate the optimal Mixup parameters for augmentation in the context of CNN performance.

36 MATERIALS SCIENCE↗

Deep learning with mixup augmentation for improved pore detection during additive manufacturing

In additive manufacturing (AM), process defects such as keyhole pores are difficult to anticipate, affecting the quality and integrity of the AM-produced materials. Hence, considerable efforts have aimed to predict these process defects by training machine learning (ML) models using passive measurements such as acoustic emissions. This work considered a dataset in which keyhole pores of a laser powder bed fusion (LPBF) experiment were identified using X-ray radiography and then registered both in space and time to acoustic measurements recorded during the LPBF experiment. Due to AM’s intrinsic process controls, where a pore-forming event is relatively rare, the acoustic datasets collected during monitoring include more non-pores than pores. In other words, the dataset for ML model development is imbalanced. Moreover, this imbalanced and sparse data phenomenon remains ubiquitous across many AM monitoring schemes since training data is nontrivial to collect. Hence, we propose a machine learning approach to improve this dataset imbalance and enhance the prediction accuracy of pore-labeled data. Specifically, we investigate how data augmentation helps predict pores and non-pores better. This imbalance is improved using recent advances in data augmentation called Mixup, a weak-supervised learning method. Convolutional neural networks (CNNs) are trained on original and augmented datasets, and an appreciable increase in performance is reported when testing on five different experimental trials. When ML models are trained on original and augmented datasets, they achieve an accuracy of 95% and 99% on test datasets, respectively. We also provide information on how dataset size affects model performance. Lastly, we investigate the optimal Mixup parameters for augmentation in the context of CNN performance.

42 ENGINEERING↗

The Italian Summer Students Program at Fermilab and other US Laboratories: 40 years of education in particle physics and technology

Since 1983 the Italian groups collaborating with Fermilab (US) have been running a 2-month summer training program for Master students. While in the first year the program involved only 4 physics students, in the following years it was extended to engineering students. Many students have extended their collaboration with Fermilab with their Master Thesis and PhD. The program has involved almost 600 Italian students from more than 20 Italian universities. Each intern is supervised by a Fermilab Mentor responsible for the training program. Training programs spanned from Tevatron, CMS, Muon (g-2), Mu2e and SBN and DUNE design and data analysis, development of particle detectors, design of electronic and accelerator components, development of infrastructures and software for tera-data handling, quantum computing and research on superconductive elements and accelerating cavities. In 2015 the University of Pisa included the program within its own educational programs. Summer Students are enrolled at the University of Pisa for the duration of the internship and at the end of the internship they write summary reports on their achievements. After positive evaluation by a University of Pisa Examining Board, interns are acknowledged 6 ECTS credits for their Diploma Supplement. In the years 2020 and 2021 the program was canceled due to the sanitary emergency but in 2022 it was restarted and allowed a cohort of 21 students in 2022, and a cohort of 27 students in 2023 to be trained for nine weeks at Fermilab. We are now organizing the 2024 program.

Barzi, Emanuela↗

The Italian Summer Students Program at Fermilab and other US Laboratories: 40 years of education in particle physics and technology

Since 1983 the Italian groups collaborating with Fermilab (US) have been running a 2-month summer training program for Master students. While in the first year the program involved only 4 physics students, in the following years it was extended to engineering students. Many students have extended their collaboration with Fermilab with their Master Thesis and PhD. The program has involved more than 600 Italian students from more than 20 Italian universities. Each intern is supervised by a Fermilab Mentor responsible for the training program. Training programs spanned from Tevatron, CMS, Muon (g-2), Mu2e and SBN (MicroBooNE, Icarus, and SBND) and DUNE design and data analysis, development of particle detectors, design of electronic and accelerator components, development of infrastructures and software for tera-data handling, quantum computing and research on superconductive elements and accelerating cavities. In 2015 the University of Pisa included the program within its own educational programs. Summer Students are enrolled at the University of Pisa for the duration of the internship and at the end of the internship they write summary reports on their achievements. After positive evaluation by a University of Pisa Examining Board, interns are acknowledged 6 ECTS credits for their Diploma Supplement. The program was paused in 2020 and 2021 due to the COVID-19 pandemic, but it resumed in 2022. From 2022 to 2024, a total of 60 students participated in the nine-week training at Fermilab. We are currently organizing the 2025 program. This paper provides an overview of the program, which can serve as a model for other interested laboratories.

Barzi, Emanuela [Ohio State U.]↗

Enforcing constraints for time series prediction in supervised, unsupervised and reinforcement learning

We assume that we are given a time series of data from a dynamical system and our task is to learn the flow map of the dynamical system. We present a collection of results on how to enforce constraints coming from the dynamical system in order to accelerate the training of deep neural networks to represent the flow map of the system as well as increase their predictive ability. In particular, we provide ways to enforce constraints during training for all three major modes of learning, namely supervised, unsupervised and reinforcement learning. In general, the dynamic constraints need to include terms which are analogous to memory terms in model reduction formalisms. Such memory terms act as a restoring force which corrects the errors committed by the learned flow map during prediction. For supervised learning, the constraints are added to the objective function. For the case of unsupervised learning, in particular generative adversarial networks, the constraints are introduced by augmenting the input of the discriminator. Finally, for the case of reinforcement learning and in particular actor-critic methods, the constraints are added to the reward function. In addition, for the reinforcement learning case, we present a novel approach based on homotopy of the action-value function in order to stabilize and accelerate training. We use numerical results for the Lorenz system to illustrate the various constructions.

Stinis, Panagiotis↗

SU-CD-PinS Room/Hall E-00: HAZMAT Training for the Medical Physicist - Part I

Medical Physicists are frequently involved in shipping radioactive materials or supervising those who do. Current U.S. Department of Transportation Hazardous Material Regulations, 49 CFR Parts 171 - 185, require hazmat employees to have documented training specified in 49 CFR 172 Subpart H. A hazmat employee is defined as an individual who: (1) loads, unloads or handles hazardous material; (2) manufactures, tests, reconditions, repairs, modifies, marks or otherwise represents containers, drums or packagings as qualified for use in the transportation of hazardous materials; (3) prepares hazardous materials for transportation; (4) is responsible for safety of transporting hazardous materials; or (5) operates a vehicle used to transport hazardous materials. Recurrent training is required at least once every three years. (The IATA two-year training interval is not applicable and is generally misunderstood.) FAA has escalated inspection and enforcement. Facilities who ship radiopharmaceuticals to other laboratories, return radiopharmaceuticals or radioactive sources to suppliers, or otherwise ship radioactive materials have been cited for failure to provide and document the required training. The interrelationship of transportation regulations, 49 CFR, IATA, ICAO and other transportation regulations, which are frequently misunderstood, will be explained. The course will cover typical shipments by air and highway which are encountered in a medical institution. Items such as fissile materials, highway route controlled quantities, rail shipments, vessel shipments and such will be omitted; although specific questions may be addressed. A major objective of the course is to present the process of shipping radioactive material in a sequential and logical fashion. How radioactive materials for transportation purposes are defined by activity concentrations for exempt materials and activity limits for exempt consignments will be explained. Radioactive material shipments of excepted packages and Type A packages will be emphasized. The program is designed to meet the function specific DOT training requirements for shippers of medical radioactive materials. General awareness training and security awareness training can be obtained from two free DOT training CDs. Safety training and security awareness training is generally satisfied by the training required under the institution’s radioactive material license. For shippers of radioactive Yellow III labeled packages an in-depth written security plan and training are no longer required as of April 8, 2010. In general almost all shippers of medical radioactive material are now not required to have an in-depth security plan. Contents of general awareness training, security awareness training and in-depth security plans will be briefly outlined. It is the hazmat employer’s responsibility to ensure that each hazmat employee is properly trained. No third party can fulfill that requirement. It is the hazmat employer’s responsibility to determine the degree to which this course meets the employer’s requirements, including contents of the course and the examination. Participants will gain sufficient knowledge to prepare hazmat training programs for others in their institutions. A handout will be posted which should be printed out and brought to the course for reference during the presentation. The handout will also satisfy part of the training documentation required by DOT. A feature handout section is a composite table which provides A1, A2, RQ, Exempt Concentration, and Exempt Consignment values in a single table in both Becquerel and Curie units. Course attendance will be certified through the AAPM CEU documentation system. Learning Objectives: Understand the regulatory requirements for shipping radioactive materials. Understand the regulatory requirements for training of hazmat employees. Comprehend how to classify, package, mark, label, document, placard, and transport radioactive materials.

60 APPLIED LIFE SCIENCES↗

Identifying the Learning Curve for Uterine Artery Embolisation in an Interventional Radiological Training Unit

AimA clear understanding of operator experience is important in improving technical success whilst minimising patient risk undergoing endovascular procedures, and there is the need to ensure that trainees have the appropriate skills as primary operators. The aim of the study is to retrospectively analyse uterine artery embolisation (UAE) procedures performed by interventional radiology (IR) trainees at an IR training unit analysing fluoroscopy times and radiation dose as surrogate markers of technical skill.MethodsTen IR fellows were primary operator in 200 UAE procedures over a 5-year period. We compared fluoroscopy times, radiation dose and complications, after having them categorised according to three groups: Group 1, initial five, Group 2, >5 procedures and Group 3, penultimate five UAE procedures. We documented factors that may affect screening time (number of vials employed and use of microcatheters).ResultsMean fluoroscopy time was 18.4 (±8.1), 17.3 (±9.0), 16.3 (±8.4) min in Groups 1, 2 and 3, respectively. There was no statistically significant difference between these groups (p > 0.05) with respect to fluoroscopy time or radiation dose. Analysis after correction for confounding factors showed no statistical significance (p > 0.05). All procedures were technically successful, and total complication rate was 4 %.ConclusionUAE was chosen as a highly standardised procedure followed by IR practitioners. Although there is a non-significant trend for shorter screening times with experience, technical success and safety were not compromised with appropriate Consultant supervision, which illustrates a safe construct for IR training. This is important and reassuring information for patients undergoing a procedure in a training unit.

62 RADIOLOGY AND NUCLEAR MEDICINE↗

Optimizing training trajectories in variational autoencoders via latent Bayesian optimization approach *

Unsupervised and semi-supervised ML methods such as variational autoencoders (VAE) have become widely adopted across multiple areas of physics, chemistry, and materials sciences due to their capability in disentangling representations and ability to find latent manifolds for classification and/or regression of complex experimental data. Like other ML problems, VAEs require hyperparameter tuning, e.g. balancing the Kullback–Leibler and reconstruction terms. However, the training process and resulting manifold topology and connectivity depend not only on hyperparameters, but also their evolution during training. Because of the inefficiency of exhaustive search in a high-dimensional hyperparameter space for the expensive-to-train models, here we have explored a latent Bayesian optimization (zBO) approach for the hyperparameter trajectory optimization for the unsupervised and semi-supervised ML and demonstrated for joint-VAE with rotational invariances. We have demonstrated an application of this method for finding joint discrete and continuous rotationally invariant representations for modified national institute of standards and technology database (MNIST) and experimental data of a plasmonic nanoparticles material system. The performance of the proposed approach has been discussed extensively, where it allows for any high dimensional hyperparameter trajectory optimization of other ML models.

42 ENGINEERING↗

SPECTRAL CLASSIFICATION OF GALAXIES AT 0.5 {<=} z {<=} 1 IN THE CDFS: THE ARTIFICIAL NEURAL NETWORK APPROACH

The aim of this work is to combine spectral energy distribution (SED) fitting with artificial neural network techniques to assign spectral characteristics to a sample of galaxies at 0.5 < z < 1. The sample is selected from the spectroscopic campaign of the ESO/GOODS-South field, with 142 sources having photometric data from the GOODS-MUSIC catalog covering bands between {approx}0.4 and 24 {mu}m in 10-13 filters. We use the CIGALE code to fit photometric data to Maraston's synthesis spectra to derive mass, specific star formation rate, and age, as well as the best SED of the galaxies. We use the spectral models presented by Kinney et al. as targets in the wavelength interval {approx}1200-7500 A. Then a series of neural networks are trained, with average performance {approx}90%, to classify the best SED in a supervised manner. We consider the effects of the prominent features of the best SED on the performance of the trained networks and also test networks on the galaxy spectra of Coleman et al., which have a lower resolution than the target models. In this way, we conclude that the trained networks take into account all the features of the spectra simultaneously. Using the method, 105 out of 142 galaxies of the sample are classified with high significance. The locus of the classified galaxies in the three graphs of the physical parameters of mass, age, and specific star formation rate appears consistent with the morphological characteristics of the galaxies.

79 ASTRONOMY AND ASTROPHYSICS↗

Mining for Strong Gravitational Lenses with Self-supervised Learning

We employ self-supervised representation learning to distill information from 76 million galaxy images from the Dark Energy Spectroscopic Instrument Legacy Imaging Surveys’ Data Release 9. Targeting the identification of new strong gravitational lens candidates, we first create a rapid similarity search tool to discover new strong lenses given only a single labeled example. We then show how training a simple linear classifier on the self-supervised representations, requiring only a few minutes on a CPU, can automatically classify strong lenses with great efficiency. We present 1192 new strong lens candidates that we identified through a brief visual identification campaign and release an interactive web-based similarity search tool and the top network predictions to facilitate crowd-sourcing rapid discovery of additional strong gravitational lenses and other rare objects: github.com/georgestein/ssl-legacysurvey.

79 ASTRONOMY AND ASTROPHYSICS↗

Computer-aided analysis of Landsat-1 MSS data - A comparison of three approaches, including a 'modified clustering' approach

Three approaches for analyzing Landsat-1 data from Ludwig Mountain in the San Juan Mountain range in Colorado are considered. In the 'supervised' approach the analyst selects areas of known spectral cover types and specifies these to the computer as training fields. Statistics are obtained for each cover type category and the data are classified. Such classifications are called 'supervised' because the analyst has defined specific areas of known cover types. The second approach uses a clustering algorithm which divides the entire training area into a number of spectrally distinct classes. Because the analyst need not define particular portions of the data for use but has only to specify the number of spectral classes into which the data is to be divided, this classification is called 'nonsupervised'. A hybrid method which selects training areas of known cover type but then uses the clustering algorithm to refine the data into a number of unimodal spectral classes is called the 'modified-supervised' approach.

Fleming, M. D.↗

SU-G-PinS Room/Hall E-00: HAZMAT Training for the Medical Physicist - Part II

Medical Physicists are frequently involved in shipping radioactive materials or supervising those who do. Current U.S. Department of Transportation Hazardous Material Regulations, 49 CFR Parts 171 - 185, require hazmat employees to have documented training specified in 49 CFR 172 Subpart H. A hazmat employee is defined as an individual who: (1) loads, unloads or handles hazardous material; (2) manufactures, tests, reconditions, repairs, modifies, marks or otherwise represents containers, drums or packagings as qualified for use in the transportation of hazardous materials; (3) prepares hazardous materials for transportation; (4) is responsible for safety of transporting hazardous materials; or (5) operates a vehicle used to transport hazardous materials. Recurrent training is required at least once every three years. (The IATA two year training interval is not applicable and is generally misunderstood.) FAA has escalated inspection and enforcement. Facilities who ship radiopharmaceuticals to other laboratories, return radiopharmaceuticals or radioactive sources to suppliers, or otherwise ship radioactive materials have been cited for failure to provide and document the required training. The interrelationship of transportation regulations, 49 CFR, IATA, ICAO and other transportation regulations, which are frequently misunderstood, will be explained. The course will cover typical shipments by air and highway which are encountered in a medical institution. Items such as fissile materials, highway route controlled quantities, rail shipments, vessel shipments and such will be omitted; although specific questions may be addressed. A major objective of the course is to present the process of shipping radioactive material in a sequential and logical fashion. How radioactive materials for transportation purposes are defined by activity concentrations for exempt materials and activity limits for exempt consignments will be explained. Radioactive material shipments of excepted packages and Type A packages will be emphasized. The program is designed to meet the function specific DOT training requirements for shippers of medical radioactive materials. General awareness training and security awareness training can be obtained from two free DOT training CDs. Safety training and security awareness training is generally satisfied by the training required under the institution’s radioactive material license. For shippers of radioactive Yellow III labeled packages an in-depth written security plan and training are no longer required as of April 8, 2010. In general almost all shippers of medical radioactive material are now not required to have an in-depth security plan. Contents of general awareness training, security awareness training and in-depth security plans will be briefly outlined. It is the hazmat employer’s responsibility to ensure that each hazmat employee is properly trained. No third party can fulfill that requirement. It is the hazmat employer’s responsibility to determine the degree to which this course meets the employer’s requirements, including contents of the course and the examination. Participants will gain sufficient knowledge to prepare hazmat training programs for others in their institutions. A handout will be posted which should be printed out and brought to the course for reference during the presentation. The handout will also satisfy part of the training documentation required by DOT. A feature handout section is a composite table which provides A1, A2, RQ, Exempt Concentration, and Exempt Consignment values in a single table in both Becquerel and Curie units. Course attendance will be certified through the AAPM CEU documentation system. Learning Objectives: Understand the regulatory requirements for shipping radioactive materials. Understand the regulatory requirements for training of hazmat employees. Comprehend how to classify, package, mark, label, document, placard, and transport radioactive materials.

60 APPLIED LIFE SCIENCES↗

Using machine learning to predict the correlation of spectra using SDSS magnitudes as an improvement to the Locus Algorithm

The Locus Algorithm is a new technique to improve the quality of differential photometry by optimising the choices of reference stars. At the heart of this algorithm is a routine to assess how good each potential reference star is by comparing its SDSS magnitude values to those of the target star. In this way, the difference in wavelength-dependent effects of the Earth’s atmospheric scattering between target and reference can be minimised. This paper sets out a new way to estimate the quality of each reference star using machine learning. A random subset of stars from SDSS with spectra was chosen. For each one, a suitable reference star, also with a spectrum, was chosen. The correlation between the two spectra in the SDSS r band (between 550 nm and 700 nm) was taken to be the gold-standard measure of how well they match up for differential photometry. The five SDSS magnitude values for each of these stars were used as predictors. A number of supervised machine learning models were constructed on a training set of the stars and were each evaluated on a testing set. The model using Support Vector Regression had the best performance of these models. It was then tested on a final, hold-out, validation set of stars to get an unbiased measure of its performance. With an R 2 of 0.62, the SVR model presents enhanced performance for the Locus Algorithm technique.

79 ASTRONOMY AND ASTROPHYSICS↗

Neural network based analysis of multimodal bond distributions using extended x-ray absorption fine structure spectra

Knowledge of the local coordination environment around atomic species in functional materials is critical for understanding their mechanisms of operation. Heterogeneous mixtures of metal complexes are ubiquitous in catalysts, ionic liquids, molten salts, biological enzymes, and geochemical systems, among many others. Extracting information from ensemble-average measurements about the structural and compositional descriptors of each type of coordination complex comprising the mixture is not generally possible, especially when they possess multimodal bond-length distributions. Here, we developed a method that enables the mapping of an x-ray absorption spectrum on the radial distribution function describing the average environment of the metal ions. The supervised neural network based method utilizes an objective training set, for which the choice of the local structural motifs is completely agnostic to the theoretically expected structure and dynamics of the modeled system. The method was validated using first-principles modeling of structural dynamics of nickel complexation in molten salts, and it applies to a large class of heterogeneous systems, including those studied under in situ and operando conditions.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

Detecting and Diagnosing Incipient Building Faults Using Uncertainty Information from Deep Neural Networks

Early detection of incipient faults is of significant importance to reducing maintenance costs, saving energy, and enhancing occupant comfort in buildings. Popular supervised learning models such as deep neural networks are considered promising due to their ability to directly learn from labeled fault data; however, it is known that the performance of supervised learning approaches highly relies on the availability and quality of labeled training data. In Fault Detection and Diagnosis (FDD) applications, the lack of labeled incipient fault data has posed a major challenge to applying these supervised learning techniques to commercial buildings. To address this concern, this paper proposes using Monte Carlo dropout (MC-dropout) to enhance the supervised learning pipeline, so that the resulting neural network is able to detect and diagnose unseen incipient fault examples. We also examine the proposed MC-dropout method on the RP-1043 dataset to demonstrate its effectiveness in indicating the most likely incipient fault types.

42 ENGINEERING↗

Sampling Subjective Polygons for Patch-Based Deep Learning Land-Use Classification in Satellite Images

Model generalization remains a key challenge in the analysis of large amounts of heterogeneous satellite image data. One major limiting factor in developing generalizable models, in the context of supervised learning, is the lack of high quality training datasets. A model's capacity to perform well on new data is often inhibited by imbalance and bias in the data that was used for training. This is especially a problem when using convolutional neural networks to classify urban land-use in satellite images. Notable dataset imbalance issues in this application include land-use type imbalance and image scene imbalance. To begin understanding these dataset imbalance problems in more detail, we develop and test a number of sampling methods for generating training image datasets from subjective training polygons for urban land-use classification. We investigate sampling at different point densities as a means to reduce content repetition and therefore content imbalance and bias in the training image dataset.

Arndt, Jacob↗

Development of a Smart Alarm System for the CEBAF Injector

RadiaSoft and Jefferson Laboratory are working together to develop a machine-learning-based smart alarm system for the CEBAF injector. Because of the injector’s large number of parameters and possible fault scenarios, it is highly desirable to have an autonomous alarm system that can quickly identify and diagnose unusual machine states. We present our work on artificial neural networks designed to identify such undesirable machine states. In particular, we test both auto-encoders and inverse models as possible tools for differentiating between normal and abnormal states. These models are being developed using both supervised and unsupervised learning techniques, and are being trained using CEBAF injector data collected during dedicated machine studies as well as during regular operations. Lastly, we discuss tradeoffs between the two types of models.

Abell, D. T.↗