VTechWorks

VTechWorks provides global access to Virginia Tech scholarship, including journal articles, books, theses, dissertations, conference papers, slide presentations, technical reports, working papers, administrative documents, videos, images, and more by faculty, students, and staff. Faculty can deposit items to VTechWorks from Elements, including journal articles covered by the University open access policy. Email vtechworks@vt.edu for help.


 
Open Access Policy

Open Access Policy

Virginia Tech's open access policy enables researchers to deposit the accepted version of scholarly articles with no embargo.


Theses and Dissertations

Theses and Dissertations

Virginia Tech was first in the world to require ETDs in 1997, and continues to add scans of older theses and dissertations.


Open Textbooks

Open Textbooks

More than 40 freely available and openly licensed textbooks are among our most downloaded items.


Recent Submissions

The Influence of the North Atlantic Subtropical High on Atmospheric Rivers Over the Eastern United States
Finkhauser, Julia Elizabeth Rose (Virginia Tech, 2024-07-22)
This study addresses the susceptibility of atmospheric rivers (ARs) to the behavior of the North Atlantic Subtropical High (NASH). ARs are a major mechanism for meridional moisture transport often connected to heavy precipitation and mid-latitude troughs. The NASH, a semi-permanent anticyclone over the subtropical North Atlantic Ocean, has been shown to be significantly influential on precipitation variability over the southeastern United States. A self-organizing map (SOM) was trained on a 4 x 3 regular grid over 250 iterations using ERA5 derived 6-hourly 850 hPa Geopotential Heights ≥ 1535 gpm from 1979-2020. The 12 resulting "nodes" were analyzed with respect to ARs defined by objects of ERA5 derived integrated water vapor transport (IVT) > 500 m-1 s-1 with lengths > 2000 km. Composites of thresholded 850 hPa heights, AR-concurrent PRISM precipitation, AR spatial frequency distribution maps, and seasonal AR frequency histograms per node illustrate seasonal interactions between the NASH and ARs that demonstrate a tendency of more frequent ARs and higher mean AR-driven precipitation over the Mississippi embayment and Ohio River Valley in the summer months, believed to be representative of extreme moisture transport events, when the NASH exhibits increased intensity, spatial expansion, and southwestward migration. Conversely, AR frequency and AR-concurrent precipitation composites suggest wintertime events are mainly supported by dynamically-driven nor'easter and bomb type cyclones when the NASH is constricted, at higher latitudes, and further east. Findings suggest that extreme summertime water vapor transport events associated with an AR are enhanced by the warm season NASH due to its increased intensity and proximity to the eastern US that acts as a supplementary lifting mechanism amidst low dynamic influence.
Bridging Machine Learning and Experimental Design for Enhanced Data Analysis and Optimization
Guo, Qing (Virginia Tech, 2024-07-19)
Experimental design is a powerful tool for gathering highly informative observations using a small number of experiments. The demand for smart data collection strategies is increasing due to the need to save time and budget, especially in online experiments and machine learning. However, the traditional experimental design method falls short in systematically assessing changing variables' effects. Specifically within Artificial Intelligence (AI), the challenge lies in assessing the impacts of model structures and training strategies on task performances with a limited number of trials. This shortfall underscores the necessity for the development of novel approaches. On the other side, the optimal design criterion has typically been model-based in classic design literature, which leads to restricting the flexibility of experimental design strategies. However, machine learning's inherent flexibility can empower the estimation of metrics efficiently using nonparametric and optimization techniques, thereby broadening the horizons of experimental design possibilities. In this dissertation, the aim is to develop a set of novel methods to bridge the merits between these two domains: 1) applying ideas from statistical experimental design to enhance data efficiency in machine learning, and 2) leveraging powerful deep neural networks to optimize experimental design strategies. This dissertation consists of 5 chapters. Chapter 1 provides a general introduction to mutual information, fractional factorial design, hyper-parameter tuning, multi-modality, etc. In Chapter 2, I propose a new mutual information estimator FLO by integrating techniques from variational inference (VAE), contrastive learning, and convex optimization. I apply FLO to broad data science applications, such as efficient data collection, transfer learning, fair learning, etc. Chapter 3 introduces a new design strategy called multi-layer sliced design (MLSD) with the application of AI assurance. It focuses on exploring the effects of hyper-parameters under different models and optimization strategies. Chapter 4 investigates classic vision challenges via multimodal large language models by implicitly optimizing mutual information and thoroughly exploring training strategies. Chapter 5 concludes this proposal and discusses several future research topics.
Key Drivers of Coastal Relocation in Spatial Clusters Along the US East Coast
Gyanwali, Sophiya (Virginia Tech, 2024-07-18)
Coastal flooding has been increasing in frequency and severity across the US East Coast, adversely impacting the human population. Preferred adaptation strategies, such as protection and accommodation, may prove insufficient under current climate change scenarios and projected future sea level rise, prompting the coastal population to consider relocation as a more efficient disaster risk reduction strategy. This study focuses on the flood-prone urban areas along the US East Coast where residents are more willing to relocate due to coastal flooding. Using the survey data, it evaluates the flood experiences, considerations toward relocation, and preferences for relocation destinations. The extent of top concerns influencing respondents' willingness to relocate, such as crime rate, buyout programs, access to critical services and amenities, and availability of comparable housing, were further explored as indirect relocation drivers. Four study locations with heightened relocation potential were identified across urban areas on the US East Coast. Relocation drivers such as crime and limited access to services and amenities are not significantly present in these study locations. However, the absence of buyout programs and affordable housing options in similar communities leaves low-income households trapped in high-risk zones, exacerbating socioeconomic disparities, and increasing the disproportionate risk faced by marginalized populations. The findings have important implications for policymakers, urban planners, and stakeholders involved in climate adaptation and disaster risk reduction efforts. They highlight the need for targeted interventions to address socioeconomic vulnerabilities, promote equitable access to housing, and enhance the resilience of communities facing coastal hazards.
A Machine Learning-Based Heuristic to Explain Game-Theoretic Models
Baswapuram, Avinashh Kumar (Virginia Tech, 2024-07-17)
This paper introduces a novel methodology that integrates Machine Learning (ML), Operations Research (OR), and Game Theory (GT) to develop an interpretable heuristic for principal-agent models (PAM). We extract solution patterns from ensemble tree models trained on solved instances of a PAM. Using these patterns, we develop a hierarchical tree-based approach that forms an interpretable ML-based heuristic to solve the PAM. This method ensures the interpretability, feasibility, and generalizability of ML predictions for game-theoretic models. The predicted solutions from this ensemble model-based heuristic are consistently high quality and feasible, significantly reducing computational time compared to traditional optimization methods to solve PAM. Specifically, the computational results demonstrate the generalizability of the ensemble heuristic in varying problem sizes, achieving high prediction accuracy with optimality gaps between 1--2% and significant improvements in solution times. Our ensemble model-based heuristic, on average, requires only 4.5 out of the 9 input features to explain its predictions effectively for a particular application. Therefore, our ensemble heuristic enhances the interpretability of game-theoretic optimization solutions, simplifying explanations and making them accessible to those without expertise in ML or OR. Our methodology adds to the approaches for interpreting ML predictions while also improving numerical tractability of PAMs. Consequently, enhancing policy design and operational decisions, and advancing real-time decision support where understanding and justifying decisions is crucial.
Robust State Estimation, Uncertainty Quantification, and Uncertainty Reduction with Applications to Wind Estimation
Gahan, Kenneth Christopher (Virginia Tech, 2024-07-17)
Indirect wind estimation onboard unmanned aerial systems (UASs) can be accomplished using existing air vehicle sensors along with a dynamic model of the UAS augmented with additional wind-related states. It is often desired to extract a mean component of the wind the from frequency fluctuations (i.e. turbulence). Commonly, a variation of the KALMAN filter is used, with explicit or implicit assumptions about the nature of the random wind velocity. This dissertation presents an H-infinity (H∞) filtering approach to wind estimation which requires no assumptions about the statistics of the process or measurement noise. To specify the wind frequency content of interest a low-pass filter is incorporated. We develop the augmented UAS model in continuous-time, derive the H∞ filter, and introduce a KALMAN-BUCY filter for comparison. The filters are applied to data gathered during UAS flight tests and validated using a vaned air data unit onboard the aircraft. The H∞ filter provides quantitatively better estimates of the wind than the KALMAN-BUCY filter, with approximately 10-40% less root-mean-square (RMS) error in the majority of cases. It is also shown that incorporating DRYDEN turbulence does not improve the KALMAN-BUCY results. Additionally, this dissertation describes the theory and process for using generalized polynomial chaos (gPC) to re-cast the dynamics of a system with non-deterministic parameters as a deterministic system. The concepts are applied to the problem of wind estimation and characterizing the precision of wind estimates over time due to known parametric uncertainties. A novel truncation method, known as Sensitivity-Informed Variable Reduction (SIVR) was developed. In the multivariate case presented here, gPC and the SIVR-derived reduced gPC (gPCr) exhibit a computational advantage over Monte Carlo sampling-based methods for uncertainty quantification (UQ) and sensitivity analysis (SA), with time reductions of 38% and 98%, respectively. Lastly, while many estimation approaches achieve desirable accuracy under the assumption of known system parameters, reducing the effect of parametric uncertainty on wind estimate precision is desirable and has not been thoroughly investigated. This dissertation describes the theory and process for combining gPC and H-infinity (H∞) filtering. In the multivariate case presented, the gPC H∞ filter shows superiority over a nominal H∞ filter in terms of variance in estimates due to model parametric uncertainty. The error due to parametric uncertainty, as characterized by the variance in estimates from the mean, is reduced by as much as 63%.