Matching Items (7)
Filtering by
- All Subjects: Machine Learning
- All Subjects: 2D materials
Description
High-entropy alloys possessing mechanical, chemical, and electrical properties that far exceed those of conventional alloys have the potential to make a significant impact on many areas of engineering. Identifying element combinations and configurations to form these alloys, however, is a difficult, time-consuming, computationally intensive task. Machine learning has revolutionized many different fields due to its ability to generalize well to different problems and produce computationally efficient, accurate predictions regarding the system of interest. In this thesis, we demonstrate the effectiveness of machine learning models applied to toy cases representative of simplified physics that are relevant to high-entropy alloy simulation. We show these models are effective at learning nonlinear dynamics for single and multi-particle cases and that more work is needed to accurately represent complex cases in which the system dynamics are chaotic. This thesis serves as a demonstration of the potential benefits of machine learning applied to high-entropy alloy simulations to generate fast, accurate predictions of nonlinear dynamics.
ContributorsDaly, John H (Author) / Ren, Yi (Thesis director) / Zhuang, Houlong (Committee member) / Mechanical and Aerospace Engineering Program (Contributor) / Barrett, The Honors College (Contributor)
Created2021-05
Description
In the last two decades, fantasy sports have grown massively in popularity. Fantasy football in particular is the most popular fantasy sport in the United States. People spend hours upon hours every year building, researching, and perfecting their teams to compete with others for money or bragging rights. One problem, however, is that National Football League (NFL) players are human and will not perform the same as they did last week or last season. Because of this, there is a need to create a machine learning model to help predict when players will have a tough game or when they can perform above average. This report discusses the history and science of fantasy football, gathering large amounts of player data, manipulating the information to create more insightful data points, creating a machine learning model, and how to use this tool in a real-world situation. The initial model created significantly accurate predictions for quarterbacks and running backs but not receivers and tight ends. Improvements significantly increased the accuracy by reducing the mean average error to below one for all positions, resulting in a successful model for all four positions.
ContributorsCase, Spencer (Author) / Johnson, Jarod (Co-author) / Kostelich, Eric (Thesis director) / Zhuang, Houlong (Committee member) / Barrett, The Honors College (Contributor) / Department of Psychology (Contributor) / Mechanical and Aerospace Engineering Program (Contributor)
Created2023-05
Description
A Compact Linear Fresnel Reflector (CLFR) is a simple, cost-effective, and scalable option for generating solar power by concentrating the sun rays. To make a most feasible application, design parameters of the CLFR, such as solar concentrator design parameters, receiver design parameters, heat transfer, power block parameters, etc., should be optimized to achieve optimum efficiency. Many researchers have carried out modeling and optimization of CLFR with various numerical or analytical methods. However, often computational time and cost are significant in these existing approaches. This research attempts to address this issue by proposing a novel computational approach with the help of increased computational efficiency and machine learning. The approach consists of two parts: the algorithm and the machine learning model. The algorithm has been created to fulfill the requirement of the Monte Carlo Ray tracing method for CLFR collector simulation, which is a simplified version of the conventional ray-tracing method. For various configurations of the CLFR system, optical losses and optical efficiency are calculated by employing these design parameters, such as the number of mirrors, mirror length, mirror width, space between adjacent mirrors, and orientation angle of the CLFR system. Further, to reduce the computational time, a machine learning method is used to predict the optical efficiency for the various configurations of the CLFR system. This entire method is validated using an existing approach (SolTrace) for the optical losses and optical efficiency of a CLFR system. It is observed that the program requires 6.63 CPU-hours of computational time are required by the program to calculate efficiency. In contrast, the novel machine learning approach took only seconds to predict the optical efficiency with great accuracy. Therefore, this method can be used to optimize a CLFR system based on the location and land configuration with reduced computational time. This will be beneficial for CLFR to be a potential candidate for concentrating solar power option.
ContributorsLunagariya, Shyam (Author) / Phelan, Patrick (Thesis advisor) / Kwon, Beomjin (Committee member) / Zhuang, Houlong (Committee member) / Arizona State University (Publisher)
Created2021
Description
Janus Transition Metal Dichalcogenides (TMDs) are emerging 2D quantum materials with an asymmetric chalcogen configuration that induces an out-of-plane dipole moment. Their synthesis has been a limiting factor in exploring these systems' many-body physics and interactions. This dissertation examines the challenges associated with synthesis and charts the excitonic landscape of Janus crystals by proposing the development of the Selective Epitaxy and Atomic Replacement (SEAR) technique. SEAR utilizes ionized radical precursors to modify TMD monolayers into their Janus counterparts selectively. The synthesis is coupled with optical spectroscopy and monitored in real-time, enabling precise control of reaction kinetics and the structural evolution of Janus TMDs. The results demonstrate the synthesis of Janus TMDs at ambient temperatures, reducing defects and preserving the structural integrity with the hitherto best-reported exciton linewidth emission value, indicating ultra-high optical quality. Cryogenic optical spectroscopy (4K) coupled with a magnetic field on Janus monolayers has allowed the isolation of excitonic transitions and the identification of charged exciton complexes. Further study into macroscopic and microscopic defects reveals that structural asymmetry results in the spontaneous formation of 2D Janus Nanoscrolls from an in-plane strain. The chalcogen arrangement in these structures dictates two types of scrolling dynamics that form Archimedean or inverted C-scrolls. High-resolution scanning transmission electron microscopy of these superlattices shows a preferential orientation of scrolling and formation of Moiré patterns. These materials' thermodynamically favorable defect states are identified and shown to be optically active. The encapsulation of Janus TMDs with hexagonal Boron Nitride (h-BN) has allowed isolation defect transitions. DFT coupled with power-dependent PL spectroscopy at 4K shows the broad defect band to be a convolution of individual defect states with extremely narrow linewidth (2 meV) indicative of a two-state quantum system. The research presents a comprehensive synthesis approach with insights into the structural and morphological stability of 2D Janus layers, establishing a complete structure-property correlation of optical transitions and defect states, broadening the scope for practical applications in quantum information technologies.
ContributorsSayyad, Mohammed Yasir (Author) / Tongay, Sefaattin (Thesis advisor) / Esqueda, Ivan S (Committee member) / Zhuang, Houlong (Committee member) / Arizona State University (Publisher)
Created2024
Description
Phase-field (PF) models are one of the most powerful tools to simulate microstructural evolution in metallic materials, polymers, and ceramics. However, existing PF approaches rely on rigorous mathematical model development, sophisticated numerical schemes, and high-performance computing for accuracy. Although recently developed surrogate microstructure models employ deep-learning techniques and reconstruction of microstructures from lower-dimensional data, their accuracy is fairly limited as spatio-temporal information is lost in the pursuit of dimensional reduction. Given these limitations, a novel data-driven emulator (DDE) for extrapolation prediction of microstructural evolution is presented, which combines an image-based convolutional and recurrent neural network (CRNN) with tensor decomposition, while leveraging previously obtained PF datasets for training. To assess the robustness of DDE, the emulation sequence and the scaling behavior with phase-field simulations for several noisy initial states are compared. In conclusion, the effectiveness of the microstructure emulation technique is explored in the context of accelerating runtime, along with an emphasis on its trade-off with accuracy.Meanwhile, an interpolation DDE has also been tested, which is based on obtaining
a low-dimensional representation of the microstructures via tensor decomposition and subsequently predicting the microstructure evolution in the low-dimensional space using Gaussian process regression (GPR). Once the microstructure predictions are obtained in the low-dimensional space, a hybrid input-output phase retrieval algorithm will be employed to reconstruct the microstructures. As proof of concept, the results on microstructure prediction for spinodal decomposition are presented, although the method itself is agnostic of the material parameters. Results show that GPR-based DDE model are able to predict microstructure evolution sequences that closely resemble the true microstructures (average normalized mean square of 6.78 × 10−7) at time scales half of that employed in obtaining training data. This data-driven
microstructure emulator opens new avenues to predict the microstructural evolution by leveraging phase-field simulations and physical experimentation where the time resolution is often quite large due to limited resources and physical constraints, such as the phase coarsening experiments previously performed in microgravity.
Future work will also be discussed and demonstrate the intended utilization of these two approaches for 3D microstructure prediction through their combined application.
ContributorsWu, Peichen (Author) / Ankit, Kumar (Thesis advisor) / Iquebal, Ashif (Committee member) / Jiao, Yang (Committee member) / Zhuang, Houlong (Committee member) / Arizona State University (Publisher)
Created2024
Description
Layer structured two dimensional (2D) semiconductors have gained much interest due to their intriguing optical and electronic properties induced by the unique van der Waals bonding between layers. The extraordinary success for graphene and transition metal dichalcogenides (TMDCs) has triggered a constant search for novel 2D semiconductors beyond them. Gallium chalcogenides, belonging to the group III-VI compounds, are a new class of 2D semiconductors that carry a variety of interesting properties including wide spectrum coverage of their bandgaps and thus are promising candidates for next generation electronic and optoelectronic devices. Pushing these materials toward applications requires more controllable synthesis methods and facile routes for engineering their properties on demand.
In this dissertation, vapor phase transport is used to synthesize layer structured gallium chalcogenide nanomaterials with highly controlled structure, morphology and properties, with particular emphasis on GaSe, GaTe and GaSeTe alloys. Multiple routes are used to manipulate the physical properties of these materials including strain engineering, defect engineering and phase engineering. First, 2D GaSe with controlled morphologies is synthesized on Si(111) substrates and the bandgap is significantly reduced from 2 eV to 1.7 eV due to lateral tensile strain. By applying vertical compressive strain using a diamond anvil cell, the band gap can be further reduced to 1.4 eV. Next, pseudo-1D GaTe nanomaterials with a monoclinic structure are synthesized on various substrates. The product exhibits highly anisotropic atomic structure and properties characterized by high-resolution transmission electron microscopy and angle resolved Raman and photoluminescence (PL) spectroscopy. Multiple sharp PL emissions below the bandgap are found due to defects localized at the edges and grain boundaries. Finally, layer structured GaSe1-xTex alloys across the full composition range are synthesized on GaAs(111) substrates. Results show that GaAs(111) substrate plays an essential role in stabilizing the metastable single-phase alloys within the miscibility gaps. A hexagonal to monoclinic phase crossover is observed as the Te content increases. The phase crossover features coexistence of both phases and isotropic to anisotropic structural transition.
Overall, this work provides insights into the controlled synthesis of gallium chalcogenides and opens up new opportunities towards optoelectronic applications that require tunable material properties.
In this dissertation, vapor phase transport is used to synthesize layer structured gallium chalcogenide nanomaterials with highly controlled structure, morphology and properties, with particular emphasis on GaSe, GaTe and GaSeTe alloys. Multiple routes are used to manipulate the physical properties of these materials including strain engineering, defect engineering and phase engineering. First, 2D GaSe with controlled morphologies is synthesized on Si(111) substrates and the bandgap is significantly reduced from 2 eV to 1.7 eV due to lateral tensile strain. By applying vertical compressive strain using a diamond anvil cell, the band gap can be further reduced to 1.4 eV. Next, pseudo-1D GaTe nanomaterials with a monoclinic structure are synthesized on various substrates. The product exhibits highly anisotropic atomic structure and properties characterized by high-resolution transmission electron microscopy and angle resolved Raman and photoluminescence (PL) spectroscopy. Multiple sharp PL emissions below the bandgap are found due to defects localized at the edges and grain boundaries. Finally, layer structured GaSe1-xTex alloys across the full composition range are synthesized on GaAs(111) substrates. Results show that GaAs(111) substrate plays an essential role in stabilizing the metastable single-phase alloys within the miscibility gaps. A hexagonal to monoclinic phase crossover is observed as the Te content increases. The phase crossover features coexistence of both phases and isotropic to anisotropic structural transition.
Overall, this work provides insights into the controlled synthesis of gallium chalcogenides and opens up new opportunities towards optoelectronic applications that require tunable material properties.
ContributorsCai, Hui, Ph.D (Author) / Tongay, Sefaattin (Thesis advisor) / Dwyer, Christian (Committee member) / Zhuang, Houlong (Committee member) / Arizona State University (Publisher)
Created2018
Description
2D materials with reduced symmetry have gained great interest in the past decade due to the arising quantum properties introduced by the structural asymmetry. A particular example is called 2D Janus materials. Named after Roman god Janus with two faces, Janus materials have different chemical compositions on the two sides of materials, leading to a structure with broken mirror symmetry. Electronegativity difference of the facial elements induces a built-in polarization field pointing out of the plane, which has driven a lot of theory predictions on Rashba splitting, high- temperature ferromagnetism, Skyrmion formation, and so on. Previously reported experimental synthesis of Janus 2D materials relies on high-temperature processing, which limits the crystallinity of as produced 2D layers. In this dissertation, I present a room temperature selective epitaxial atomic re- placement (SEAR) method to convert CVD-grown transition metal dichalcogenides (TMDs) into a Janus structure. Chemically reactive H2 plasma is used to selectively etch off the top layer of chalcogen atoms and the introduction of replacement chalco- gen source in-situ allows for the achievement of Janus structures in one step at room temperature. It is confirmed that the produced Janus monolayers possess high crys- tallinity and good excitonic properties. Moving forward, I show the fabrication of lateral and vertical heterostructures of Janus materials, which are predicted to show exotic properties because of the intrinsic polarization field. To efficiently screen other kinds of interesting Janus structures, a new plasma chamber is designed to allow in-situ optical measurement on the target monolayer during the SEAR process. Successful conversion is seen on mechanically exfoliated MoSe2 and WSe2, and insights into reaction kinetics are gain from Raman spectra evolution. Using the monitoring ability, Janus SNbSe is synthesized for the first time. It’s also demonstrated that the overall crystallinity of as produced Janus monolayer
SWSe and SMoSe are correlated with the source of monolayer TMDs.
Overall, the synthesis of the Janus monolayers using the described method paves the way to the production of highly crystalline Janus materials, and with the in-situ monitoring ability, a deeper understanding of the mechanism is reached. This will accelerate future exploration of other Janus materials synthesis, and confirmation and discovery of their exciting quantum properties.
ContributorsQin, Ying (Author) / Tongay, Sefaattin (Thesis advisor) / Zhuang, Houlong (Committee member) / Jiao, Yang (Committee member) / Arizona State University (Publisher)
Created2021