Data Science Commons^™

Toward Mapping Multiphase Multicomponent Mixtures With Neural Networks, Kristen L. Hallas, Melissa De Jesus, Christine J. Wu, Jianzhi Li, Jason Bernstein, Philip C. Myint

School of Mathematical & Statistical Sciences Faculty Publications

Equation of state (EOS) tables are commonly used in hydrodynamic simulations of high-pressure, high-temperature phenomena in fields like planetary science, astrophysics, and high-energy-density science. However, generating and storing EOS tables for multiphase, multicomponent mixtures over a wide range of pressures and temperatures is computationally infeasible due to their memory-intensive nature. To address this issue, we have developed a neural network-based machine learning model to predict new EOS tables for binary mixtures. In particular, a deep feedforward neural network trained on a set of ten EOS tables at particular mixture compositions is able to predict nine new (hold-out) EOS tables at …

Harnessing Digital Twin (Dt) Technology For Food Security And Climate Resilience In Sub-Saharan Africa (Ssa), Henri E.Z. Tonnang, Francis Chianu, Siyabusa Mkuhlani, Francis Muthoni, John Michael Humphries Choptiany, Franck B.N. Tonle, Bonoukpoe M. Sokame, Mercy Lung’Aho

All Peer-Reviewed Publications

Sub-Saharan Africa (SSA) faces chronic food insecurity despite possessing approximately 60% of the world’s uncultivated arable land. Field trials generate evidence but are costly and insufficiently scaled to address accelerating climate and demographic pressures. Digital twin (DT) technology, defined as the continuous, bidirectional virtual replication of physical systems using real-time data, supports monitoring, modelling, and optimisation of agrifood systems. To our knowledge, however, no published synthesis has examined DT agriculture research through the lens of SSA food systems or smallholder farming realities. A PRISMA-compliant systematic review was conducted across bibliographic databases using a pre-defined Boolean search and adapted PICOS eligibility …

Predictive Tropical Cyclogenesis Using Deep Learning: A Novel Approach To Early Warning Systems, Nikolay Todorov

Computational and Data Sciences (PhD) Dissertations

Tropical cyclogenesis (TCG) is among the least predictable stages of the tropical cyclone life cycle, yet the timing and location of genesis are exactly what early warning systems (EWS) depend on. We present a spatio-temporal deep learning framework that forecasts genesis as a normalized probability field and delivers that skill through a real-time warning pipeline. The model couples a two-layer ConvLSTM encoder with learned temporal-attention pooling over nine 6-hourly steps (0–48 h lead) and a convolutional refinement head that outputs per-cell genesis probability. It is trained on 1980–2025 ERA5 fields and Emanuel potential intensity at 0.25° and evaluated by leave-one-year-out …

Machine Learning-Based Regression For Magnetic Field Prediction From Odmr Spectral Data, Jesse B. Hernandez

Electronic Theses, Projects, and Dissertations

Optically Detected Magnetic Resonance (ODMR) using nitrogen-vacancy (NV) centers in diamond enables sensitive, room-temperature magnetic field sensing, but real ODMR spectra are often noisy and difficult to analyze with traditional peak-fitting methods. This thesis investigates whether machine learning can reliably predict magnetic field strength directly from ODMR spectra, and compares four model families under a single regression task: a random forest, an artificial neural network (ANN), a one-dimensional convolutional neural network (1D-CNN), and a Transformer.

Training data were generated from an NV-ensemble simulation calibrated to real measurements provided by the Ulsan National Institute of Science and Technology (UNIST), spanning 0 …

Engineered Acoustic Features And Neural Networks For Music Emotion Recognition: An Empirical Comparison On The Deam Dataset, Xiaoyu Lyu

Electronic Theses, Projects, and Dissertations

This study compares engineered acoustic features with spectrogram based convolutional neural networks for static Valence and Arousal prediction on the 1,802-song DEAM dataset. Random Forest and XGBoost use 520 dimensional openSMILE features, while the CNN learns from 30-second log-mel spectrograms. The evaluation uses five saved song-level train, validation, and test partitions. The original XGBoost baseline achieves mean RMSE of 0.780 for Valence and 0.793 for Arousal, below every tested CNN configuration on both targets in all five runs. Increasing the CNN to 101,506 parameters lowers its mean RMSE to 0.837 and 0.855, respectively; a further increase to 403,714 parameters gives …

Enhancing Agricultural Sustainability Under Climate Change: A Multi-Scale Framework Integrating Climate Extremes, Resource Efficiency, And Data-Driven Modeling, Shahryar Fazli

Computational and Data Sciences (PhD) Dissertations

Agricultural systems are increasingly challenged by climate variability, where shifting temperature regimes, hydrological variability, and the rising frequency of compound and cascading extremes threaten global food security and resource sustainability. Addressing these challenges requires integrated frameworks that bridge biophysical monitoring, predictive modeling, and adaptive decision-making. This dissertation develops a data-driven, multi-scale framework to quantify and enhance agricultural resilience by integrating remote sensing, climate analytics, and machine learning across the United States, with a focus on California and the Western U.S.

First, hyperspectral and thermal remote sensing data from EMIT and OpenET are integrated to characterize crop nitrogen–water interactions and assess …

Finding The Missing Link: Host Galaxies Of Intermediate-Mass Black Holes In Illustris, Michael J. Pinto Ii

Science University Research Symposium (SURS)

Black holes are significant cosmological objects that challenge the fundamentals of physics and our understanding of black hole evolution. Moreover, formation pathways and lifetimes for intermediate-mass black holes (IMBHs) remain poorly constrained. This raises the question of whether these bodies persist as stable remnants or represent transient stages in supermassive black hole (SMBH) evolution. This study utilizes the Illustris Project’s Illustris-3, a cosmological hydrodynamical simulation, to build and characterize different galactic environments that host IMBHs across four distinct environmental samples: dwarf galaxies, Milky Way-mass galaxies, massive galaxies, and cluster-mass halos at redshifts z ≈ 4.9, 0.6, and 0. We then …

Several Complex Variables, Pseudoconvexity, And Plurisubharmonic Defining Functions, Luka Mernik

Math Department Colloquium Series

This talk introduces some basic concepts in several complex variables and explains the role of pseudo convexity through two fundamental topics: Hartog’s' extension phenomenon and the Levi problem. A stronger property than pseudo convexity is the existence of a plurisubharmonic defining function. Such defining functions play an important role in the study of analytic objects associated with a domain, including the regularity of the d-bar Neumann operator and the Bergman projection. The main question of this talk is whether a pseudo convex domain admits a plurisubharmonic defining function. We approach this question in two steps. First, we establish a necessary …

Repeated Games In The Presence Of Incomplete Information, Reza Habibi

The Journal of Economics and Politics

There are many strategic situations at which a game theoretical framework should be used to analyze the equilibrium decisions at which the incomplete information annoy the process of deriving the certain rules for making decisions. In these cases, players use signals of each other's to get proper decisions. For example, in economic environment, some macro-economic latent variables induce incomplete information. Morris and Shin (2000) referred this type of game as global game and studied one-shot type of it. However, in practical situations, it is a type of repeated game. In the current paper, following notations of Morris and Shin (2000), …

Stewards Of Data: A Practical Handbook For Undergraduate Researchers In Engineering And Applied Sciences, Şenay Purzer, Wei Zakharov, Carla B. Zoltowski

Purdue University Press Books

Filled with actionable guides and real-world examples, Stewards of Data: A Practical Handbook for Undergraduate Researchers in Engineering and Applied Sciences allows readers to utilize the provided templates and guides almost immediately. In today’s world, data is ubiquitous and AI is growing exponentially. Practicing ethical data management is, therefore, crucial. Ensuring that data is findable, accessible, interoperable, and reusable is essential. This book is an interdisciplinary effort aimed at embedding ethical data life-cycle management education into undergraduate research. The authors present a Data Steward Framework, which serves as a guide for undergraduate researchers, the graduate students who mentor them, postdocs, …

Bridging Theory And Practice: A Data-Driven Community Partnership To Optimize Maintenance Effectiveness, Daniel Wu

Academic Affairs

This project established an immersive, industry-engaged learning experience that embedded Data Science students in a professional business environment through a partnership with Thiele Kaolin. Students applied advanced data mining, machine learning, and big data analytics techniques to large proprietary datasets to address authentic business challenges and generate actionable, data-driven insights. By working with complex real-world data, students bridged the gap between classroom theory and industry practice while gaining hands-on experience with the full data science workflow, including data preparation, exploratory analysis, predictive modeling, and results interpretation. The project also fostered critical thinking, teamwork, and professional competencies. Students collaborated in multidisciplinary …

Models For Second Courses In Data Science: Insights From Five Different Institutions, Ben Baumer, Gillian D. Beltz-Mohrmann, Brianna C. Heggeseth, Nicholas J. Horton, Leslie Myint, Michael A. Posner, Paul Roback

Statistical and Data Sciences: Faculty Publications

As data science continues to mature as an academic discipline, curricular standardization remains elusive. While a number of groups have defined program-level learning outcomes for data science, there is no consensus surrounding course-level learning outcomes. We present five different models for a second course in data science, each of which comes with its own learning goals, coverage of topics, points of emphasis, prerequisites, and role in our respective (statistics and) data science curricula. We use the data science topic, subtopic, and competency/concept framework created by the MASDER project to analyze the content of our courses, and present areas of similarity …

Domain Knowledge-Informed Machine Learning Model To Study Weather-Induced Flight Delays, Gurvir Bawa

Doctoral Dissertations and Master's Theses

Weather-induced Traffic Management Initiatives (TMIs) occur rarely relative to normal air traffic operations. This scarcity produces severe class imbalance that limits predictive models of flight delay. To address it, this dissertation leverages a physics- and domain- knowledge informed Variational Autoencoder (VAE), conditioned on airport identity, that generates physically plausible synthetic weather events for underrepresented TMI categories. The fidelity of the model is assessed with a calibrated discrepancy measure disclosed along- side the results rather than described in free-form terms. A multitask Graph Neural Network (GNN) is then trained on the augmented dataset to jointly classify airport-level TMI status and predict …

Understanding The Role Of Data Science Applications In Soil And Water Health, Payton Davis, Debabrata Sahoo, Dara Park, Brook Russell

Forestry and Natural Resources

Data science is an emerging field that can be incorporated into many disciplines, including environmental science. Data science can provide valuable information from data, enhancing the understanding of systems and environments. This publication is intended to give an overview of the different aspects of data science and how data science can be leveraged into and applied to soil and water health.

Readme Template For Geospatial Data, Alyssa Renteria

Library Faculty Research

A readme file provides descriptive information about a dataset, file(s), or software. The goal is to ensure that the files and data can be correctly interpreted by your future self or others when sharing or publishing data, code, or software.

Individualized Bayesian Inference Identifies Novel Genetic Variants For Parkinson's Disease, Jin Ren, Yasaman J. Soofi, Md Asad Rahman, Qing Lu, Jinling Liu

Engineering Management and Systems Engineering Faculty Research & Creative Works

Parkinson's disease (PD) is a complex neurodegenerative disorder with a significant genetic component. While genome-wide association studies (GWAS) have been instrumental in identifying genetic variants associated with PD, the reliance on large sample sizes and population-level analyses may overlook variants with lower minor allele frequencies or individual-specific relevance. Individualized Bayesian Inference (IBI) offers a promising method to complement GWAS by identifying and prioritizing candidate genetic markers at both the individual and patients-like-me subgroup levels. This study evaluates the application of IBI to PD genetics, using GWAS as a baseline for comparison. We analyzed genetic data from the Fox Insight online …

Machine Learning-Enabled Chemical Ecology For Integrated Pest Management: From Volatiles To Field Applications, Steve B.S. Baleba, Victor O. Omondi, Pascal Aigbedion-Atalor, Emmanuel Peter, Souleymane Diallo, Komi Mensah Agboka

All Peer-Reviewed Publications

Machine learning is transforming chemical ecology by accelerating the discovery and deployment of semiochemical-based tools for precision pest management. These advances are particularly important in the face of climate change, pesticide resistance, and the growing need for sustainable agricultural intensification. This review synthesizes how machine learning can be applied across the semiochemical discovery and implementation pipeline, from chemical signal detection to field deployment and decision support for integrated pest management. We review major machine learning approaches and demonstrate how they extract biologically relevant information from high-dimensional chemical, electrophysiological, behavioral, sensor, and field datasets. These methods accelerate semiochemical discovery, prioritize candidate …

Bridging Data Gaps In Retinal Imaging: From Structural Domain Adaptation To Topology-Aware Synthesis, Gözde Merve Demirci

Dissertations, Theses, and Capstone Projects

Comprehensive visualization of the retina is essential for diagnosing and monitoring blinding diseases such as Diabetic Retinopathy and Retinopathy of Prematurity (ROP), where pathological changes often extend beyond a single field of view. Despite significant advances in automated retinal image analysis, clinical deployment remains limited by two fundamental data gaps: a structural learning gap, arising from scarce expert annotations and poor generalization across imaging domains, and a spatial coverage gap, caused by the difficulty of acquiring multi-view retinal images in fragile populations. Although these challenges are often addressed independently, this dissertation argues that they are tightly coupled: accurate, …

Mapping The Water Quality Of Jamaica Bay, New York (1996-2024): Principal Component Analysis And K-Means Clustering, Sneha Srivastava

Dissertations, Theses, and Capstone Projects

Jamaica Bay, located along the southeastern coast of New York City, acts as a biodiverse estuary of wetlands, meadows, and salt marsh islands. The purpose of this study is to analyze the water quality conditions of the region over time, comparing locations around the bay to identify hyperlocal features that influence larger trends in the hydrological system. Ten variables were used as water quality indicators, including total Kjeldahl nitrogen, salinity, pH, Secchi disk depth, and total phosphorus, among others, across five stations in the bay, between 1994 and 2024. After data cleaning and standardization methods were applied, principal component analysis …

Ecu-Malnett V2, Matthew G. Gaber, Mohiuddin Ahmed, Michael N. Johnstone

Research Datasets

ECU-MALNETT (ECU MALware NETwork Traffic) is a real world, reproducible dataset of labeled benign and malicious network flows built from the Peekaboo execution corpus. Peekaboo runs evasive malware with dynamic binary instrumentation and records raw host-level PCAPs while granting full Internet access, yielding noisy, real-world captures with background OS activity and concurrent processes. To derive trustworthy labels from these traces, we apply Construct, a baseline aware, zero-trust labeling framework. Construct first ingests a baseline capture to establish reference sets (DNS qnames, HTTP hosts, TLS SNIs, and socket endpoints) and grows a conservative benign IP pool only via whitelisted DNS resolutions. …