Physical Sciences and Mathematics Commons^™

A Data-Driven Multi-Regime Approach For Predicting Real-Time Energy Consumption Of Industrial Machines., Abdulgani Kahraman

Electronic Theses and Dissertations

This thesis focuses on methods for improving energy consumption prediction performance in complex industrial machines. Working with real-world industrial machines brings several challenges, including data access, algorithmic bias, data privacy, and the interpretation of machine learning algorithms. To effectively manage energy consumption in the industrial sector, it is essential to develop a framework that enhances prediction performance, reduces energy costs, and mitigates air pollution in heavy industrial machine operations. This study aims to assist managers in making informed decisions and driving the transition towards green manufacturing. The energy consumption of industrial machinery is substantial, and the recent increase in CO2 …

New Species Of Dryolestoid From The Late Cretaceous Allen Formation And Implications For South American Faunal Diversity., Brigid Erin Connelly

Electronic Theses and Dissertations

Dryolestoids are extinct cladotherians mammals from the Jurassic and Cretaceous periods. I describe a collection of dryolestoid specimens from the Late Cretaceous localities of Cerro Tortuga (Allen Formation), Anfiteatro 1, and Shining (both La Colonia Formation) from Patagonia, Argentina. Using comparative morphology, I identify a new species of meridiolestidan dryolestoid based on eleven specimens across both formations. The new species’ recovery from La Colonia Formation represents the first dryolestoid connection between the two approximately contemporaneous formations. The species’ morphology may represent an ecological shift within Meridiolestida from insectivory to herbivory, showing a transition in characters between the plesiomorphic sharp-toothed meridiolestidans …

Evaluating Chatgpt For Recommendation: How Does The Ability To Converse Impact Recommendation?, Kyle Spurlock

Electronic Theses and Dissertations

Recommendation algorithms have become an absolute necessity in the modern world to avoid information overload. However, the interaction between the human and the system is largely superficial and without any real contact. If you are given poor recommendations, you have no choice but to sift through mountains of content on your own until the model learns to accommodate your tastes more. This is bad for business as well as the consumer. Recently, large language models like ChatGPT have seen a significant rise in popularity due to their ease of use and wide range of knowledge. It has now become nearly …

Penalized Bayesian Exponential Random Graph Models., Vicki Modisette

Electronic Theses and Dissertations

Networks have the critical ability to represent the complex interconnectedness of social relationships, biological processes, and the spread of diseases and information. Exponential random graph models (ERGM) are one of the popular statistical methods for analyzing network data. ERGM, however, struggle with computational challenges and degeneracy issues, further exacerbated by their inability to handle high-dimensional network data. Bayesian techniques provide a promising avenue to overcome these two problems. This paper considers penalized Bayesian exponential random graph models with adaptive lasso and adaptive ridge penalties to perform variable selection and reduce multicollinearity on a variety of networks. The experimental results demonstrate …

The Loneliest Galaxies In The Universe: A Gama And Galaxy Zoo Study On Void Galaxy Morphology, Lori E. Porter, Benne Holwerda, Sandor Kruk, Maritza Lara-López, Kevin A. Pimbblet, Christopher P A Henry, Sarah Casura, Lee S. Kelvin

Faculty Scholarship

The large-scale structure of the Universe is comprised of galaxy filaments, tendrils, and voids. The majority of the Universe’s volume is taken up by these voids, which exist as underdense, but not empty, regions. The galaxies found inside these voids are expected to be some of the most isolated objects in the Universe. This study, using the Galaxy and Mass Assembly (GAMA) and Galaxy Zoo surveys, aims to investigate basic physical properties and morphology of void galaxies versus field (filament and tendril) galaxies. We use void galaxies with stellar masses (⁠M∗" role="presentation" style="box-sizing: border-box; margin: 0px; padding: 0px; border: 0px; …

Gama/Devils: Cosmic Star Formation And Agn Activity Over 12.5 Billion Years, Jordan C J D’Silva, Simon P. Driver, Claudia D P Lagos, Aaron S G Robotham, Sabine Bellstedt, Luke J M Davies, Jessica E. Thorne, Joss Bland-Hawthorn, Matias Bravo, Benne Holwerda, Steven Phillipps, Nick Seymour, Malgorzata Siudek, Rogier A. Windhorst

Faculty Scholarship

We use the Galaxy and Mass Assembly (GAMA) and the Deep Extragalactic Visible Legacy Survey (DEVILS) observational data sets to calculate the cosmic star formation rate (SFR) and active galactic nuclei (AGN) bolometric luminosity history (CSFH/CAGNH) over the last 12.5 billion years. SFRs and AGN bolometric luminosities were derived using the spectral energy distribution fitting code ProSpect, which includes an AGN prescription to self consistently model the contribution from both AGN and stellar emission to the observed rest-frame ultra-violet to far-infrared photometry. We find that both the CSFH and CAGNH evolve similarly, rising in the early Universe up to a …

Galaxy And Mass Assembly (Gama): Comparing Visually And Spectroscopically Identified Galaxy Merger Samples, Alice Desmons, Sarah Brough, Cristina Martínez-Lombilla, Roberto De Propris, Benne Holwerda, Ángel R. López-Sánchez

Faculty Scholarship

We conduct a comparison of the merging galaxy populations detected by a sample of visual identification of tidal features around galaxies as well as spectroscopically detected close pairs of galaxies to determine whether our method of selecting merging galaxies biases our understanding of galaxy interactions. Our volume-limited parent sample consists of 852 galaxies from the Galaxy And Mass Assembly (GAMA) survey in the redshift range 0.04 ≤ z ≤ 0.20 and stellar mass range 9.50 ≤ log 10(M⋆/M⊙)≤ 11.0" role="presentation" style="box-sizing: border-box; margin: 0px; padding: 0px; border: 0px; font-variant: inherit; font-stretch: inherit; line-height: normal; font-family: inherit; font-optical-sizing: inherit; font-kerning: inherit; …

Beyond Covid-19: Designing Inclusive Public Health Surveillance By Including Wastewater Monitoring, Rochelle H. Holm, Na'taki Osborne Jelks, Rebecca Schneider, Ted Smith

Faculty Scholarship

Wastewater-based epidemiology is a promising and expanding public health surveillance method. The current wastewater testing trajectory to monitor primarily at community wastewater treatment plants was necessitated by immediate needs of the pandemic. Going forward, specific consideration should be given to monitoring vulnerable and underserved communities to ensure inclusion and rapid response to public health threats. This is particularly important when clinical testing data are insufficient to characterize community virus levels and spread in specific locations. Now is a timely call to action for equitably protecting health in the United States, which can be guided with intentional and inclusive wastewater monitoring.

Red Riding On Hood: Exploring How Galaxy Colour Depends On Environment, Pankaj C. Bhambhani, Ivan K. Baldry, Sarah Brough, Alexander D. Hill, M A. Lara-Lopez, J Loveday, Benne Holwerda

Faculty Scholarship

Galaxy populations are known to exhibit a strong colour bimodality, corresponding to blue star-forming and red quiescent subpopulations. The relative abundance of the two populations has been found to vary with stellar mass and environment. In this paper, we explore the effect of environment considering different types of measurements. We choose a sample of 49 911 galaxies with 0.05 < z < 0.18 from the Galaxy And Mass Assembly survey. We study the dependence of the fraction of red galaxies on different measures of the local environment as well as the large-scale `geometric’ environment defined by density gradients in the surrounding cosmic web. We find that the red galaxy fraction varies with the environment at fixed stellar mass. The red fraction depends more strongly on local environmental measures than on large-scale geometric environment measures. By comparing the different environmental densities, we show that no density measurement fully explains the observed environmental red fraction variation, suggesting the different measures of environmental density contain different information. We test whether the local environmental measures, when combined together, can explain all the observed environmental red fraction variation. The geometric environment has a small residual effect, and this effect is larger for voids than any other type of geometric environment. This could provide a test of the physics applied to cosmological-scale galaxy evolution simulations as it combines large-scale effects with local environmental impact.

The Study Of Corrosion On Additive-Manufactured Metals., Braydan Daniels

Electronic Theses and Dissertations

The purpose of this study was to investigate and compare the corrosion mechanisms between wrought and additive-manufactured (3D-printed) copper and stainless steel. The experimental procedure consisted of measuring the open circuit potential, electrochemical impedance spectroscopy, linear sweep voltammetry, Tafel analysis, surface topology, and scanning electron microscopy for each metal within salt water, tap water, sulfuric acid, and synthetic body fluid (excluding copper in synthetic body fluid).

Overall, printed stainless steel was more corrosion-resistant than wrought stainless steel in tap water and synthetic body fluid based on OCP, LSV, and surface topology results. Additionally, printed copper was more corrosion-resistant than wrought …

The Loneliest Galaxies In The Universe: A Gama And Galaxy Zoo Study On Void Galaxy Morphology., Lori E. Porter

College of Arts & Sciences Senior Honors Theses

The large-scale structure (LSS) of the Universe is comprised of galaxy filaments, tendrils, and voids. The majority of the Universe’s volume is taken up by these voids, which exist as underdense, but not empty, regions. The galaxies found inside voids are void galaxies and expected to be some of the most isolated objects in the Universe. However, their standard morphology remains poorly studied. This study, using the Galaxy and Mass Assembly (GAMA) data and Galaxy Zoo survey, aims to remedy this. For completeness purposes, we use void galaxies identified by Alpaslan et al. (2014) with stellar masses (M*) of 10 …

Development Of Nonorthogonal Wavefunction Theories And Application To Multistate Reaction Processes., Emily Kempfer

Electronic Theses and Dissertations

Many prominent areas of technological development rely on exploiting the photochemical response of molecules. An application of particular interest is the control of molecular switches through a combination of different external stimuli. However, despite significant advances in theoretical approaches and numerous cases of successful application of theory, simulating photochemical reactions remains a computational challenge. Theoretical methods for describing excited states can be broadly divided into single-reference response methods and multireference methods. Single reference methods provide reliable semiquantitative results for single excitations. However, these methods cannot describe double-excited states, systems with strongly correlated ground states, or regions of degeneracy on the …

Mechanism And Kinetics Of Photocatalytic Partial Oxidation Of Methane On Single Site Mox Reaction Centers., Clint Evrard

Electronic Theses and Dissertations

Single-site transition-metal doped photocatalysts are a class of materials in which small transition-metal oxide clusters are embedded onto the surface of zeolites, graphene, and bulk semiconductors. Experimental findings demonstrate that VO4, CrO4, NbO4, and WO4 clusters embedded on an MCM- 41 mesoporous amorphous SiO2 are effective photocatalysts for oxidative reactions. The selective direct partial oxidation of methane (POM) to form methanol is essential for efficiently utilizing natural gas. Photocatalytic methane oxidation has advantages over traditional thermal catalysis as it can be deployed at small-scale facilities to reduce methane release into the atmosphere due to flaring potentially. Our work has aimed …

Super P-Sulfur Cathodes For Quasi-Solid-State Lithium-Sulfur-Batteries., Milinda Bharatha Kalutara Koralalage

Electronic Theses and Dissertations

Lithium-Sulfur (Li-S) batteries have become a promising candidate to meet the current energy storage demand, with its natural abundance of materials, high theoretical capacity of 1672 mAhg-1, high energy density of 2600 Whkg-1, low cost and lower environmental impact. Sulfide based solid state electrolytes (SSEs) have received greater attention due to their higher ionic conductivity, compatible interface with sulfur-based cathodes, and lower grain boundary resistance. However, the interface between SSEs and cathodes has become a challenge in all solid-state Li-S batteries due to the rigidity of the participating surfaces. A hybrid electrolyte containing SSE coupled with a small amount of …

Mach And Froude Numbers On Mars., Camella-Rosa Nasr

Electronic Theses and Dissertations

Mars atmospheric global circulation models exhibit transonic jet streaks during
northern winter, which motivates this study of the Mach number, Ma (the ratio of
flow speed to the speed of sound), and the Froude number, Fr (the ratio of flow
speed to the speed of buoyancy waves), as a function of season and location. Two
global reanalyses spanning Mars Years (MY) 24 to 33 are used as input, EMARS
and OpenMARS. The study’s vertical coordinate is the isentropic variable potential
temperature, θ, ranging from θ = 125 to 1100 K, which corresponds to altitudes
ranging on average from z ≈ …

Structural, Magnetic, Electrical, Pseudocapacitive, And Electrocatalytic Properties Of Bilayered Ruddlesden-Popper Oxides., Chandana Kananke-Gamage

Electronic Theses and Dissertations

Ruddlesden Popper (RP) oxides are perovskite-derived functional materials with the general formula An-1Aʹ2BnO3n+1, where A/Aʹ is often a lanthanide or alkaline earth metal, and B is usually a transition metal. These materials contain perovskite-like connectivity, where BO6 units share apexes to form layers that are stacked above each other. The number of layers in each stack is represented by n in the above formula. The spaces between stacks are often occupied by lanthanide or alkaline-earth metals (Aʹ-site metals), which also reside in intra-stack spaces (A-site) between the octahedra. Oxide materials derived from perovskites have been studied for a wide range …

Modeling, Simulation And Control Of Microrobots For The Microfactory., Zhong Yang

Electronic Theses and Dissertations

Future assembly technologies will involve higher levels of automation in order to satisfy increased microscale or nanoscale precision requirements. Traditionally, assembly using a top-down robotic approach has been well-studied and applied to the microelectronics and MEMS industries, but less so in nanotechnology. With the boom of nanotechnology since the 1990s, newly designed products with new materials, coatings, and nanoparticles are gradually entering everyone’s lives, while the industry has grown into a billion-dollar volume worldwide. Traditionally, nanotechnology products are assembled using bottom-up methods, such as self-assembly, rather than top-down robotic assembly. This is due to considerations of volume handling of large …

First Principles Study Of 2d Polar Heterostructures., Safia Abdullah R Alharbi

Electronic Theses and Dissertations

Recently, two-dimensional (2D) heterostructures have attracted extensive attention in nanomaterials science. They have been successfully fabricated and applied to nanotechnology in many fields, such as nanoelectronics, solar cells, sensors, energy stores, quantum information, etc. The most common heterostructures are 2D-lateral heterostructure (LH) and 2D-vertical heterostructure (VH) where each of them exhibits unique features depending on the direction of assembly, i.e., along in-plane or out-of-plane direction. Beyond the van der Waals-VH which possess of van der Waals (vdW) interaction, there are other types of heterostructures made of 2D polar materials that possess different types of chemical bonding nature, e.g., chemical bonds …

Online Dashboards For Sars-Cov-2 Wastewater Data Need Standard Best Practices: An Environmental Health Communication Agenda, Colleen C. Naughton, Rochelle H. Holm, Nancy J. Lin, Brooklyn P. James, Ted Smith

Faculty Scholarship

The COVID-19 pandemic has highlighted the benefits of wastewater surveillance to supplement clinical data. Numerous online information dashboards have been rapidly, and typically independently, developed to communicate environmental surveillance data to public health officials and the public. In this study, we review dashboards presenting SARS-CoV-2 wastewater data and propose a path toward harmonization and improved risk communication. A list of 127 dashboards representing 27 countries was compiled. The variability was high and encompassed aspects including the graphics used for data presentation (e.g., line/bar graphs, maps, and tables), log versus linear scale, and 96 separate ways of labeling SARS-CoV-2 wastewater concentrations. …

Galaxy And Mass Assembly (Gama): Low-Redshift Quasars And Inactive Galaxies Have Similar Neighbors, Maria B. Stone, Clare F. Wethers, Roberto De Propris, Jari Kotilainen, Nischal Acharya, Benne W. Holwerda, Jonathan Loveday, Steven Phillipps

Faculty Scholarship

We explore the properties of galaxies in the proximity (within a ∼2 Mpc radius sphere) of Type I quasars at 0.1 <z <0.35, to check whether and how an active galaxy influences the properties of its neighbors. We further compare these with the properties of neighbors around inactive galaxies of the same mass and redshift within the same volume of space, using the Galaxy and Mass Assembly spectroscopic survey. Our observations reveal no significant difference in properties such as the number of neighbors, morphologies, stellar mass, star formation rates, and star formation history between the neighbors of quasars and those of the comparison sample. This implies that quasar activity in a host galaxy does not significantly affect its neighbors (e.g., via interactions with the jets). Our results suggest that quasar host galaxies do not strongly differ from the average galaxy within the specified mass and redshift range. Additionally, the implication of the relatively minor importance of the environmental effect on and from quasars is that nuclear activity is more likely triggered by internal and secular processes.

Jwst’S Pearls: Dust Attenuation And Gravitational Lensing In The Backlit-Galaxy System Vv 191, William C. Keel, Rogier A. Windhorst, Rolf A. Jansen, Seth H. Cohen, Jake Summers, Benne Holwerda, Sarah T. Bradford, Clayton D. Robertson, Giovanni Ferrami, Stuart Wyithe, Haojing Yan, Christopher J. Conselice, Simon P. Driver, Aaron Robotham, Norman A. Grogin, Christopher N. A. Willmer, Anton M. Koekemoer, Brenda L. Frye, Nimish P. Hathi, Russell E. Ryan Jr., Nor Pirzkal, Madeline A. Marshall, Dan Coe, Jose M. Diego, Thomas J. Broadhurst, Michael J. Rutkowski, Lifan Wang, S. P. Willner, Andreea Petric, Cheng Cheng, Adi Zitrin

Faculty Scholarship

We present the first JWST observations of the z = 4.11 luminous radio galaxy TN J1338–1942, obtained as part of the ‘Prime Extragalactic Areas for Reionization and Lensing Science’ (‘PEARLS’) project. Our NIRCam observations, designed to probe the key rest-frame optical continuum and emission line features at this redshift, enable resolved spectral energy distribution modelling that incorporates both a range of stellar population assumptions and radiative shock models. With an estimated stellar mass of log10(M/M⊙) ∼ 10.9, TN J1338–1942 is confirmed to be one of the most massive galaxies known at this epoch. Our observations also reveal extremely high equivalent-width …

Wallaby Pilot Survey: Hydra Cluster Galaxies Uv And H I Morphometrics, Benne W. Holwerda, Frank Bigiel, Albert Bosma, Helene M. Courtois, Nathan Deg, Helga Dénes, Ahmed Elagali, Bi-Qing For, Baerbel Koribalski, Denis A. Leahy, Karen Lee-Waddell, Ángel R. López-Sánchez, Se-Heon Oh, Tristan N. Reynolds, Jonghwan Rhee, Kristine Spekkens, Jing Wang, Tobias Westmeier, O Ivy Wong

Faculty Scholarship

Galaxy morphology in atomic hydrogen (H I) and in the ultraviolet (UV) are closely linked. This has motivated their combined use to quantify morphology over the full H I disc for both H I and UV imaging. We apply galaxy morphometrics: concentration, asymmetry, gini, M₂₀ and multimode-intensity-deviation statistics to the first moment-0 maps of the WALLABY Survey of galaxies in the hydra cluster centre. Taking advantage of this new H I survey, we apply the same morphometrics over the full H I extent on archival GALEX FUV and NUV data to explore how well H I truncated, extended ultraviolet …

Generative Ai As A Tool For Environmental Health Research Translation, Lauren B. Anderson, Dhiraj Kanneganti, Mary Bentley Houk, Rochelle H. Holm, Ted Smith

Faculty Scholarship

One valuable application for generative artificial intelligence (AI) is summarizing research studies for non-academic readers. We submitted five articles to Chat Generative Pre-trained Transformer (ChatGPT) for summarization, and asked the article's author to rate the summaries. Higher ratings were assigned to more insight-oriented activities, such as the production of eighth-grade reading level summaries, and summaries highlighting the most important findings and real-world applications. The general summary request was rated lower. For the field of environmental health science, no-cost AI technology such as ChatGPT holds the promise to improve research translation, but it must continue to be improved (or improve itself) …

Modelling Strong Lenses From Wide-Field Ground-Based Observations In Kids And Gama, Shawn Knabel, Benne Holwerda, J Nightingale, T Treu, M Bilicki, S Brough, S Driver, L Finnerty, L Haberzettl, S Hegde, A M. Hopkins, K Kuijken, J Liske, A K. Pimblett, R C. Steele, A H. Wright

Faculty Scholarship

Despite the success of galaxy-scale strong gravitational lens studies with Hubble-quality imaging, a number of well-studied strong lenses remains small. As a result, robust comparisons of the lens models to theoretical predictions are difficult. This motivates our application of automated Bayesian lens modelling methods to observations from public data releases of overlapping large ground-based imaging and spectroscopic surveys: Kilo-Degree Survey (KiDS) and Galaxy and Mass Assembly (GAMA), respectively. We use the open-source lens modelling software PYAUTOLENS to perform our analysis. We demonstrate the feasibility of strong lens modelling with large-survey data at lower resolution as a complementary avenue to studies …

Clear: Spatially Resolved Emission Lines And Active Galactic Nuclei At 0.6 < Z < 1.3, Bren E. Backhaus, Joanna S. Bridge, Jonathan R. Trump, Nikko J. Cleri, Casey Papovich, Raymond C. Simons, Ivelina Momcheva, Benne Holwerda, Zhiyuan Ji, Intae Jung, Jasleen Matharu

Faculty Scholarship

We investigate spatially resolved emission-line ratios in a sample of 219 galaxies (0.6 < z < 1.3) detected using the G102 grism on the Hubble Space Telescope Wide Field Camera 3 taken as part of the CANDELS Lyα Emission at Reionization survey to measure ionization profiles and search for low-luminosity active galactic nuclei (AGN). We analyze [O III] and Hβ emission-line maps, enabling us to spatially resolve the [O III]/Hβ emission-line ratio across the galaxies in the sample. We compare the [O III]/Hβ ratio in galaxy centers and outer annular regions to measure ionization differences and investigate the potential of sources with nuclear ionization to host AGN. We investigate some of the individual galaxies that are candidates to host strong nuclear ionization and find that they often have low stellar mass and are undetected in X-rays, as expected for low-luminosity AGN in low-mass galaxies. We do not find evidence for a significant population of off-nuclear AGN or other clumps of off-nuclear ionization. We model the observed distribution of [O III]/Hβ spatial profiles and find that most galaxies are consistent with a small or zero difference between their nuclear and off-nuclear line ratios, but 6%–16% of galaxies in the sample are likely to host nuclear [O III]/Hβ that is ∼0.5 dex higher than in their outer regions. This study is limited by large uncertainties in most of the measured [O III]/Hβ spatial profiles; therefore, deeper data, e.g., from deeper HST/ WFC3 programs or from JWST/NIRISS, are needed to more reliably measure the spatially resolved emission-line conditions of individual high-redshift galaxies.

Environmental Health Justice Across The Globe, Arnita Gadson, Rochelle H. Holm

Faculty Scholarship

No abstract provided.

Detection Of Human, Porcine And Canine Picornaviruses In Municipal Sewage Sludge Using Pan-Enterovirus Amplicon-Based Long-Read Illumina Sequencing, Temitope O. C. Faleye, Erin M. Driver, Devin A. Bowes, Rochelle H. Holm, Daymond Talley, Ray Yeager, Aruni Bhatnagar, Ted Smith, Arvind Varsani, Rolf U. Halden, Matthew Scotch

Faculty Scholarship

We describe the successful detection of human, porcine and canine picornaviruses (CanPV) in sewage sludge (at each stage of treatment) from Louisville, Kentucky, USA, using Pan-enterovirus amplicon-based long-read Illumina sequencing. Based on publicly available sequence data in GenBank, this is the first detection of CanPV in the USA and the first detection globally using wastewater-based epidemiology. Our findings also suggest there might be clusters of endemic porcine enterovirus (which have been shown capable of causing systemic infection in porcine) circulation in the USA that have not been sampled for around two decades. Our findings highlight the value of WBE coupled …

Galaxy And Mass Assembly (Gama): The Dependence Of Star Formation On Surface Brightness In Low-Redshift Galaxies, S Phillipps, S Bellstedt, M N. Bremer, R De Propris, P A. James, S Casura, J Liske, B W. Holwerda

Faculty Scholarship

The star-formation rate in galaxies is well known to correlate with stellar mass (the ‘star-forming main sequence’). Here, we extend this further to explore any additional dependence on galaxy surface brightness, a proxy for stellar mass surface density. We use a large sample of low-redshift (z ≤ 0.08) galaxies from the Galaxy And Mass Assembly survey which have both spectral energy distribution (SED) derived star-formation rates and photometric bulge-disc decompositions, the latter providing measures of disc surface brightness and disc masses. Using two samples, one of galaxies fitted by a single component with Sérsic index below 2 and one …

The Role Of Generative Adversarial Networks In Bioimage Analysis And Computational Diagnostics., Ahmed Naglah

Electronic Theses and Dissertations

Computational technologies can contribute to the modeling and simulation of the biological environments and activities towards achieving better interpretations, analysis, and understanding. With the emergence of digital pathology, we can observe an increasing demand for more innovative, effective, and efficient computational models. Under the umbrella of artificial intelligence, deep learning mimics the brain’s way in learn complex relationships through data and experiences. In the field of bioimage analysis, models usually comprise discriminative approaches such as classification and segmentation tasks. In this thesis, we study how we can use generative AI models to improve bioimage analysis tasks using Generative Adversarial Networks …

Estimating Sewage Flow Rate In Jefferson County, Kentucky, Using Machine Learning For Wastewater-Based Epidemiology Applications, Dhiraj Kanneganti, Lauren E. Reinersman, Rochelle H. Holm, Ted Smith

Faculty Scholarship

Direct measurement of the flow rate in sanitary sewer lines is not always feasible and is an important parameter for the normalization of data used in wastewater-based epidemiology applications. Machine learning to estimate past wastewater influent flow rates supporting public health applications has not been studied. The aim of this study was to assess wastewater treatment plant influent flow rates when compared with weather data and to retrospectively estimate flow rates in Louisville, Kentucky (USA), based on other data types using machine learning. A random forest model was trained using a range of variables, such as feces-related indicators, weather data …