Physical Sciences and Mathematics Commons^™

Accelerating Markov Chain Monte Carlo Sampling With Diffusion Models, N. T. Hunt-Smith, W. Melnitchouk, F. Ringer, N. Sato, A. W. Thomas, M. J. White

Physics Faculty Publications

Global fits of physics models require efficient methods for exploring high-dimensional and/or multimodal posterior functions. We introduce a novel method for accelerating Markov Chain Monte Carlo (MCMC) sampling by pairing a Metropolis-Hastings algorithm with a diffusion model that can draw global samples with the aim of approximating the posterior. We briefly review diffusion models in the context of image synthesis before providing a streamlined diffusion model tailored towards low-dimensional data arrays. We then present our adapted Metropolis-Hastings algorithm which combines local proposals with global proposals taken from a diffusion model that is regularly trained on the samples produced during the …

A Data-Driven Machine Learning Approach For Electron-Molecule Ionization Cross Sections, Allison Harris, Josh Nepomuceno

Faculty publications – Physics

Despite their importance in a wide variety of applications, the estimation of ionization cross sections for large molecules continues to present challenges for both experiment and theory. Machine learning (ML) algorithms have been shown to be an effective mechanism for estimating cross section data for atomic targets and a select number of molecular targets. We present an efficient ML model for predicting ionization cross sections for a broad array of molecular targets. Our model is a 3-layer neural network that is trained using published experimental datasets. There is minimal input to the network, making it widely applicable. We show that …

Faster, Cheaper, And Better Cfd: A Case For Machine Learning To Augment Reynolds-Averaged Navier-Stokes, John Peter Romano Ii

Mechanical & Aerospace Engineering Theses & Dissertations

In recent years, the field of machine learning (ML) has made significant advances, particularly through applying deep learning (DL) algorithms and artificial intelligence (AI). The literature shows several ways that ML may enhance the power of computational fluid dynamics (CFD) to improve its solution accuracy, reduce the needed computational resources and reduce overall simulation cost. ML techniques have also expanded the understanding of underlying flow physics and improved data capture from experimental fluid dynamics.

This dissertation presents an in-depth literature review and discusses ways the field of fluid dynamics has leveraged ML modeling to date. The author selects and describes …

Compatibility Of Clique Clustering Algorithm With Dimensionality Reduction, Ug ̆Ur Madran, Duygu Soyog ̆Lu

Applied Mathematics & Information Sciences

In our previous work, we introduced a clustering algorithm based on clique formation. Cliques, the obtained clusters, are constructed by choosing the most dense complete subgraphs by using similarity values between instances. The clique algorithm successfully reduces the number of instances in a data set without substantially changing the accuracy rate. In this current work, we focused on reducing the number of features. For this purpose, the effect of the clique clustering algorithm on dimensionality reduction has been analyzed. We propose a novel algorithm for support vector machine classification by combining these two techniques and applying different strategies by differentiating …

The Influence Of Allostery Governing The Changes In Protein Dynamics Upon Substitution, Joseph Hess

All Dissertations

The focus of this research is to investigate the effects of allostery on the function/activity of an enzyme, human immunodeficiency virus type 1 (HIV-1) protease, using well-defined statistical analyses of the dynamic changes of the protein and variants with unique single point substitutions ¹. The experimental data¹ evaluated here only characterized HIV-1 protease with one of its potential target substrates. Probing the dynamic interactions of the residues of an enzyme and its variants can offer insight of the developmental importance for allosteric signaling and their connection to a protein’s function. The realignment of the secondary structure elements can …

Using Deep Neural Networks To Classify Astronomical Images, Andrew D. Macpherson

Honors Projects

As the quantity of astronomical data available continues to exceed the resources available for analysis, recent advances in artificial intelligence encourage the development of automated classification tools. This paper lays out a framework for constructing a deep neural network capable of classifying individual astronomical images by describing techniques to extract and label these objects from large images.

A Quantum Approach To Language Modeling, Constantijn Van Der Poel

Dissertations, Theses, and Capstone Projects

This dissertation consists of six chapters. . . Chapter 1: We introduce language modeling, outline the software used for this thesis, and discuss related work. Chapter 2: We will unpack the transition from classical to quantum probabilities, as well as motivate their use in building a model to understand language-like datasets. Chapter 3: We motivate the Motzkin dataset, the models we will be investigating, as well as the necessary algorithms to do calculations with them. Chapter 4: We investigate our models’ sensitivity to various hyperparameters. Chapter 5: We compare the performance and robustness of the models. Chapter 6: We conclude …

Quantum Computing And Its Applications In Healthcare, Vu Giang

OUR Journal: ODU Undergraduate Research Journal

This paper serves as a review of the state of quantum computing and its application in healthcare. The various avenues for how quantum computing can be applied to healthcare is discussed here along with the conversation about the limitations of the technology. With more and more efforts put into the development of these computers, its future is promising with the endeavors of furthering healthcare and various other industries.

Patch-Wise Training With Convolutional Neural Networks To Synthetically Upscale Cfd Simulations, John P. Romano, Alec C. Brodeur, Oktay Baysal

Mechanical & Aerospace Engineering Faculty Publications

This paper expands the authors’ prior work[1], which focuses on developing a convolutional neural network (CNN) model capable of mapping time-averaged, unsteady Reynold’s-averaged Navier-Stokes (URANS) simulations to higher resolution results informed by time-averaged detached eddy simulations (DES). The authors present improvements over the prior CNN autoencoder model that result from hyperparameter optimization, increased data set augmentation through the adoption of a patch-wise training approach, and the predictions of primitive variables rather than vorticity magnitude. The training of the CNN model developed in this study uses the same URANS and DES simulations of a transonic flow around several NACA 4-digit airfoils …

Using Machine Learning To Search For Vector Boson Scattering At The Cms Detector During Run 2, Mark Mekosh

Graduate Research Theses & Dissertations

This work reports on the use of different machine learning (ML) techniques in the search for vector boson scattering (VBS) events in the semileptonic $WV$ channel. VBS is an important process for studying electroweak symmetry breaking (EWSB), the Higgs mechanism, as well as for probing beyond the standard model physics. Boosted decision trees as well as deep neural networks were trained on Monte Carlo simulation samples and applied to 137 fb$^{-1}$ of proton-proton collision data taken from 2016 to 2018 by the Compact Muon Solenoid (CMS) experiment at the Large Hadron Collider (LHC) with a center of mass energy $\sqrt{s} …

Machine Learning-Based Jet And Event Classification At The Electron-Ion Collider With Applications To Hadron Structure And Spin Physics, Kyle Lee, James Mulligan, Mateusz Płoskoń, Felix Ringer, Feng Yuan

Physics Faculty Publications

We explore machine learning-based jet and event identification at the future Electron-Ion Collider (EIC). We study the effectiveness of machine learning-based classifiers at relatively low EIC energies, focusing on (i) identifying the flavor of the jet and (ii) identifying the underlying hard process of the event. We propose applications of our machine learning-based jet identification in the key research areas at the future EIC and current Relativistic Heavy Ion Collider program, including enhancing constraints on (transverse momentum dependent) parton distribution functions, improving experimental access to transverse spin asymmetries, studying photon structure, and quantifying the modification of hadrons and jets in …

Machine Learning Strategies For Potential Development In High-Entropy Driven Nickel-Based Superalloys, Marium Mostafiz Mou

MSU Graduate Theses

In this study, I developed Deep Learning interatomic potentials to model a multi-phase and multi-component system of Ni-based Superalloys. The system has up to three major phase constituents, namely Gamma, Gamma Prime, and Transition-metal rich Carbide. I utilized invariant scalar-based and/or equivariant, tensor-based neural network (NN) approach as implemented in DEEPMD, NEQUIP/ALLEGRO codes, respectively, and Moment Tensor Potential (MTP). For the training and validation sets, I employed the ab-initio molecular dynamics (AIMD) trajectory results and ground state DFT calculations, including the energy, force, and virial database from highly diverse compositions, temperatures, and pressures following a “High Entropy Strategy.” The Deep …

Detection And Diagnosis Of Bacterial Pathogens In Blood And Urine Using Laser-Induced Breakdown Spectroscopy, Emma J.M. Blanchette

Electronic Theses and Dissertations

The aim of this thesis is to expand on and improve the existing techniques used for detecting and identifying bacterial pathogens in clinical specimens with laser-induced breakdown spectroscopy (LIBS). Specifically, the existing experimental procedures, including bacterial sample preparation and data acquisition, as well as the data analysis with chemometric algorithms were investigated. Substantial reductions in LIBS background signal were achieved by implementing rigorous cleaning steps and the introduction of the use of ultrapure water. Following this, a database of LIBS spectra was acquired from specimens of E. coli, S. aureus, E. cloacae, M. smegmatis, and P. …

Using Machine Learning To Predict Student Outcomes, Saba Fatima

Graduate Research Theses & Dissertations

Predicting students’ performance to identify which students are at risk of receiving aD/Fail/Withdraw (DFW) grade and ensuring their timely graduation is not just desirable but also necessary in most educational entities. In the US, not only is the Science, Technology, Engineering, and Mathematics (STEM) major becoming less popular among students, the graduation rate of STEM students is steadily declining. The lack of STEM graduates in the US is a serious problem that will place this country at a disadvantage as a competitor in international technological advancement. In order to secure its status as a technological leader internationally, the US institutions …

Photonic Monitoring Of Atmospheric Fauna, Adrien P. Genoud

Dissertations

Insects play a quintessential role in the Earth’s ecosystems and their recent decline in abundance and diversity is alarming. Monitoring their population is paramount to understand the causes of their decline, as well as to guide and evaluate the efficiency of conservation policies. Monitoring populations of flying insects is generally done using physical traps, but this method requires long and expensive laboratory analysis where each insect must be identified by qualified personnel. Lack of reliable data on insect populations is now considered a significant issue in the field of entomology, often referred to as a “data crisis” in the field. …

Pyseg: A Python Package For 2d Material Flake Localization, Segmentation, And Thickness Prediction, Diana B. Horangic

Student Research Projects

Thin materials are of interest for their extraordinary physical, mechanical, thermal, electrical, and optical properties. Monolayers and bilayers of 2D materials can be manufactured through a variety of exfoliation methods. To determine layer thickness, Raman spectroscopy or other methods like Rayleigh scattering are used. These methods are, however, slow, and they require equipment beyond an optical microscope. A Python package that automates flake identification processes was built, with access solely to RGB data from an optical microscope assumed. My package, pyseg, localizes flakes on a substrate and then makes a rough estimate of their thickness from first principles. It can …

Generation Of Phase Transitions Boundaries Via Convolutional Neural Networks, Christopher Alexis Ibarra

Open Access Theses & Dissertations

Accurate mapping of phase transitions boundaries is crucial in accurately modeling the equation of state of materials. The phase transitions can be structural (solid-solid) driven by temperature or pressure or a phase change like melting which defines the solid-liquid melt line. There exist many computational methods for evaluating the phase diagram at a particular point in temperature (T) and pressure (P). Most of these methods involve evaluation of a single (P,T) point at a time. The present work partially automates the search for phase boundaries lines utilizing a machine learning method based on convolutional neural networks and an efficient search …

Imaging Normal Fluid Flow In He Ii With Neutrons And Lasers — A New Application Of Neutron Beams For Studies Of Turbulence, Xin Wen

Doctoral Dissertations

Turbulence is ubiquitous in life —from biology to astrophysics. The best direct numeric simulations (DNS) have only been benchmarked against low resolution, time-averaged experimental configurations—partly because of limitations in computing power. With time, computing power has greatly increased, so there is need for higher quality data of turbulent flow. In this dissertation, we explore a solution that enables quantitative visualization measurement of the velocity field in liquid helium, which has the potential of breaking new ground for high Reynolds number turbulence research and model testing.

Our technique involves creation of clouds of molecular tracers using 3He-neutron absorption reaction in liquid …

Search For Triple-Proton Decay Using Machine Learning With Cuore, Douglas Adams

Theses and Dissertations

A framework to search for a triple-proton decay of ¹³⁰Te in the CUORE detector against a background of muons is presented. We use machine learning to classify different kinds of energy depositing events. We use the classification information to improve our detection or non-detection limits of a triple-proton decay process. We derive and use a methodology of combining Poisson counting statistics with supervised classification machine learning tools. Additionally, a sensitivity calculation is provided which uses the classification counting likelihood. Using our analysis technique, we achieve an lower 2σ half-life bound of 7.43×10²⁴yrs for triple-proton decay of …

Enabling Rapid Chemical Analysis Of Plutonium Alloys Via Machine Learning-Enhanced Atomic Spectroscopy Techniques, Ashwin P. Rao

Theses and Dissertations

Analytical atomic spectroscopy methods have the potential to provide solutions for rapid, high fidelity chemical analysis of plutonium alloys. Implementing these methods with advanced analytical techniques can help reduce the chemical analysis time needed for plutonium pit production, directly enabling the 80 pit-per-year by 2030 manufacturing goal outlined in the 2018 Nuclear Posture Review. Two commercial, handheld elemental analyzers were validated for potential in situ analysis of Pu. A handheld XRF device was able to detect gallium in a Pu surrogate matrix with a detection limit of 0.002 wt% and a mean error of 8%. A handheld LIBS device was …

The Interaction Of Different Primary Producers And Physical And Chemical Dynamics Of An Urban Shallow Lake, Majid Sahin

Dissertations, Theses, and Capstone Projects

An artificial urban shallow lake, Prospect Park Lake (PPL), is situated on a terminal moraine in Brooklyn New York, and supplied with municipal water treated with ortho-phosphates. The constant input of the phosphate nutrient is the primary source of eutrophication in the lake. The numerous pools along the water course houses various aquatic phototrophs, which influence the water quality and the state of the system, driving conditions into favoring the survival of their species. In the first half of the dissertation, the focus of the project is on analyzing how the different primary producers in different regions of PPL affect …

Applications Of Machine Learning Algorithms In Materials Science And Bioinformatics, Mohammed Quazi

Mathematics & Statistics ETDs

The piezoelectric response has been a measure of interest in density functional theory (DFT) for micro-electromechanical systems (MEMS) since the inception of MEMS technology. Piezoelectric-based MEMS devices find wide applications in automobiles, mobile phones, healthcare devices, and silicon chips for computers, to name a few. Piezoelectric properties of doped aluminum nitride (AlN) have been under investigation in materials science for piezoelectric thin films because of its wide range of device applicability. In this research using rigorous DFT calculations, high throughput ab-initio simulations for 23 AlN alloys are generated.

This research is the first to report strong enhancements of piezoelectric properties …

An Interdisciplinary Approach To Understanding Volcanoes And Their Processes, Katherine Cosburn

Physics & Astronomy ETDs

To better understand volcanoes and their processes is important from both a fundamental science perspective and for hazard monitoring purposes. The complexity and limitations we face in pursuing such a science are numerous and this dissertation explores how an interdisciplinary approach combining physics, computer science, and volcanology can address this complexity in a straightforward and meaningful way. This is achieved through various modelling techniques across three studies: (1) a first-order analytic modelling of stratovolcano topographic shape, (2) the use of a Bayesian joint inversion on gravity and novel cosmic-ray muon measurements for imaging flat-lying subsurface density anomalies, and (3) the …

Advanced Communication And Sensing Protocols Using Twisted Light And Engineered Quantum Statistics, Michelle L. Lollie

LSU Doctoral Dissertations

Advanced performance of modern technology at a fundamental physical level is driving new innovations in communication, sensing capability, and information processing. Key to this improvement is the ability to harness the power of physical phenomena at the quantum mechanical level, where light and light-matter interactions produce technological advancement not realizable by classical means. Theoretical investigation into quantum computing, sensing capability beyond classical limits, and quantum information has prompted experimental work to bring state-of-the-art quantum systems to the forefront for commercial use. This dissertation contributes to the latter portion of the work. A set of preliminaries is included highlighting pertinent physical …

A Machine Learning Approach To Denoising Particle Detector Observations In Nuclear Physics, Polykarpos Thomadakis, Angelos Angelopoulos, Gagik Gavalian, Nikos Chrisochoides

College of Sciences Posters

With the evolution in detector technologies and electronic components used in the Nuclear Physics field, experimental setups become larger and more complex. Faster electronics enable particle accelerator experiments to run with higher beam intensity, providing more interactions per time and more particles per interaction. However, the increased beam intensities present a challenge to particle detectors because of the higher amount of noise and uncorrelated signals. Higher noise levels lead to a more challenging particle reconstruction process by increasing the number of combinatorics to analyze and background signals to eliminate. On the other hand, increasing the beam intensity can provide physics …

Development Of Advanced Machine Learning Models For Analysis Of Plutonium Surrogate Optical Emission Spectra, Ashwin P. Rao, Phillip R. Jenkins, John D. Auxier Ii, Michael B. Shattan, Anil Patnaik

Faculty Publications

This work investigates and applies machine learning paradigms seldom seen in analytical spectroscopy for quantification of gallium in cerium matrices via processing of laser-plasma spectra. Ensemble regressions, support vector machine regressions, Gaussian kernel regressions, and artificial neural network techniques are trained and tested on cerium-gallium pellet spectra. A thorough hyperparameter optimization experiment is conducted initially to determine the best design features for each model. The optimized models are evaluated for sensitivity and precision using the limit of detection (LoD) and root mean-squared error of prediction (RMSEP) metrics, respectively. Gaussian kernel regression yields the superlative predictive model with an RMSEP of …

Multi-Modality Automatic Lung Tumor Segmentation Method Using Deep Learning And Radiomics, Siqiu Wang

Theses and Dissertations

Delineation of the tumor volume is the initial and fundamental step in the radiotherapy planning process. The current clinical practice of manual delineation is time-consuming and suffers from observer variability. This work seeks to develop an effective automatic framework to produce clinically usable lung tumor segmentations. First, to facilitate the development and validation of our methodology, an expansive database of planning CTs, diagnostic PETs, and manual tumor segmentations was curated, and an image registration and preprocessing pipeline was established. Then a deep learning neural network was constructed and optimized to utilize dual-modality PET and CT images for lung tumor segmentation. …

Data-Driven Methods For Low-Energy Nuclear Theory, Jordan M.R. Fox

CGU Theses & Dissertations

The term data-driven describes computational methods for numerical problem solvingwhich have been developed by the field of data science; these are at the intersection of computer science,mathematics, and statistics. When applied to a domain science like nuclear physics, especially with the goalof deepening scientific insight, data-driven methods form a core pillar of the computational science endeavor.In this dissertation I explore two problems related to theoretical nuclear physics: one in the framework of numerical statistics, and the other in the framework of machine learning. I) Historically our understanding of the structure of the atomic nucleus, the quantum many-body problem, has been …

Machine Learning-Driven Surrogate Models For Electrolytes, Tong Gao

Dissertations, Master's Theses and Master's Reports

We have developed a lattice Monte Carlo (MC) simulation based on the diffusion-limited aggregation model that accounts for the effect of the physical properties of ionic liquids (ILs) on lithium dendrite growth. Our simulations show that the size asymmetry between the cation and anion, the dielectric constant, and the volume fraction of ILs are critical factors to significantly suppress the dendrite growth, primarily due to substantial changes in electric-field screening. Specifically, the volume fraction of ILs has the optimal value for dendrite suppression. The present simulation method indicates potential challenges for the model extension to macroscopic systems. Therefore, we also …

A Surrogate Model Of Molecular Dynamics Simulations For Polar Fluids: Supervised Learning Methods For Molecular Polarization And Unsupervised Methods For Phase Classification, Zackerie W. Hjorth

Dissertations, Master's Theses and Master's Reports

Molecular Dynamic (MD) simulation is a standard computational tool in soft matter physics. While very powerful, it is computationally expensive, leading to some simulations taking days or even weeks to complete depending on the size of your computer cluster. Finding computationally cheap surrogate models which can learn the output features of MD simulation is therefore highly motivated. In this report I explore the use of deep neural network ensembles as well as support vector machine regressors as surrogate models for MD simulation. From the output of the surrogate models, we can then employ unsupervised learning methods to get insight into …