Theses and Dissertations from UMD
Permanent URI for this communityhttp://hdl.handle.net/1903/2
New submissions to the thesis/dissertation collections are added automatically as they are received from the Graduate School. Currently, the Graduate School deposits all theses and dissertations from a given semester after the official graduation date. This means that there may be up to a 4 month delay in the appearance of a give thesis/dissertation in DRUM
More information is available at Theses and Dissertations at University of Maryland Libraries.
Browse
3 results
Search Results
Item MODELING GROUNDWATER FLUCTUATIONS IN THE COASTAL PLAIN OF MARYLAND: AN ANN POWERED STRATEGY(2024) Steeple, Jennifer Lynne; Negahban-Azar, Masoud; Shirmohammadi, Adel; Environmental Science and Technology; Digital Repository at the University of Maryland; University of Maryland (College Park, Md.)Groundwater management in the face of climate change presents a critical challenge with far-reaching implications for water resource sustainability. This study evaluates the effectiveness of Artificial Neural Networks (ANNs) as predictive tools for estimating current groundwater levels and forecasting future groundwater levels in the Aquia aquifer in the Coastal Plain ofMaryland. The groundwater levels of the Aquia aquifer have declined under the pressures of land use change, increases in agricultural irrigation, and population growth. We tested, trained, and employed eight county-level artificial neural network (ANNs) models to predict and project Aquia aquifer groundwater levels for the near (2030-2050) and far (2050-2100) future under two socio-economic pathways (SSP245 and SSP585). The models exhibited significant predictive performance during testing (R²= 0.82-0.99). Minimum temperature and population were the most influential variables across all county-based models. When used to forecast groundwater level under two climate scenarios, the models predicted declining groundwater levels over time in Calvert, Caroline, Queen Anne’s, and Kent counties, aligning with regional trends in the Aquia aquifer. Conversely, Anne Arundel, Charles, St. Mary’s, and Talbot counties exhibited projected increases in groundwater levels, likely influenced by correlations with the variable irrigated farm acreage, underscoring the importance of considering nonlinear relationships and interactions among variables in groundwater modeling. The study highlights the ability of ANNs to accurately predict county-scale groundwater levels, even with limited data, indicating their potential utility for informing decision-making processes regarding water resource management and climate change adaptation strategies. This study also assessed the usability of multiple methods to fill in the missing data and concluded that using the repeated groundwater level data still resulted in powerful ANN models capable of both predicting and forecasting ground water levels in the Coastal Plain of Maryland.Item APPLICATIONS OF ARTIFICIAL NEURAL NETWORKS IN LEARNING QUANTUM SYSTEMS(2023) Pan, Ruizhi; Clark, Charles; Physics; Digital Repository at the University of Maryland; University of Maryland (College Park, Md.)Quantum machine learning is an emerging field that combines techniques in the disciplines of machine learning (ML) and quantum physics. Research in this field takes three broad forms: applications of classical ML techniques to quantum physical systems, quantum computing and algorithms for classical ML problems, and new ideas inspired by the intersection of the two disciplines. We mainly focus on the power of artificial neural networks (NNs) in quantum-state representation and phase classification in this work. In the first part of the dissertation, we study NN quantum states which are used as wave-function ans{\" a}tze in the context of quantum many-body physics. While these states have achieved success in simulating low-lying eigenstates and short-time unitary dynamics of quantum systems and efficiently representing particular states such as those with a stabilizer nature, more rigorous quantitative analysis about their expressibility and complexity is warranted. Here, our analysis of the restricted Boltzmann machine (RBM) state representation of one-dimensional (1D) quantum spin systems provides new insight into their computational complexity. We define a class of long-range-fast-decay (LRFD) RBM states with quantifiable upper bounds on truncation errors and provide numerical evidence for a large class of 1D quantum systems that may be approximated by LRFD RBMs of at most polynomial complexities. These results lead us to conjecture that the ground states of a wide range of quantum systems may be exactly represented by LRFD RBMs or a variant of them, even in cases where other state representations become less efficient. At last, we provide the relations between multiple typical state manifolds. Our work proposes a paradigm for doing complexity analysis for generic long-range RBMs which naturally yields a further classification of this manifold. This paradigm and our characterization of their nonlocal structures may pave the way for understanding the natural measure of complexity for quantum many-body states described by RBMs and are generalizable for higher-dimensional systems and deep neural-network quantum states. In the second part, we use RBMs to investigate, in dimensions $D=1$ and $2$, the many-body excitations of long-range power-law interacting quantum spin models. We develop an energy-shift method to calculate the excited states of such spin models and obtain a high-precision momentum-resolved low-energy spectrum. This enables us to identify the critical exponent where the maximal quasiparticle group velocity transits from finite to divergent in the thermodynamic limit numerically. In $D=1$, the results agree with an analysis using the field theory and semiclassical spin-wave theory. Furthermore, we generalize the RBM method for learning excited states in nonzero-momentum sectors from 1D to 2D systems. At last, we analyze and provide all possible values ($3/2$, $2$ and $3$) of the critical exponent for 1D generic quadratic bosonic and fermionic Hamiltonians with long-range hoppings and pairings which serves for understanding the speed of information propagation in quantum systems. In the third part, we study deep NNs as phase classifiers. We analyze the phase diagram of a 2D topologically nontrivial fermionic model Hamiltonian with pairing terms at first and then demonstrate that deep NNs can learn the band-gap closing conditions only based on wave-function samples of several typical energy eigenstates, thus being able to identify the phase transition point without knowledge of Hamiltonians.Item PREDICTING WIND PRESSURE ON LOWRISE BUILDINGS WITH PROTECTIVE PARAPETS USING ARTIFICIAL NEURAL NETWORKS(2020) Wang, Yanan; Phillips, Brian M; Civil Engineering; Digital Repository at the University of Maryland; University of Maryland (College Park, Md.)Wind hazards cause tremendous destruction and threaten people’s safety and economical losses. To improve current provision toward wind load and strengthen buildings against wind forces, it’s vital to properly characterize wind loading on buildings in wind hazard. The turbulence created by the bluff body makes analytical modeling difficult. Therefore, engineers typically turn to wind tunnel tests. This thesis investigates the application of Artificial Neural Networks (ANN) to predict the wind pressure on low-rise buildings with protective parapets. With existing experimental datasets conducted in BLWT, ANN models were trained to model non-linear relationship between inputs, such as tap coordinates and parapet height, and outputs, such as pressure coefficients. The developed model was used to predict pressure coefficients with unseen parapet height to cut down experimental cost.