Digital Commons Network^™

Multi-Objective Optimization Of The Fast Neutron Source By Machine Learning, John L. Pevey

Doctoral Dissertations

The design and optimization of nuclear systems can be a difficult task, often with prohibitively large design spaces, as well as both competing and complex objectives and constraints. When faced with such an optimization, the task of designing an algorithm for this optimization falls to engineers who must apply engineering knowledge and experience to reduce the scope of the optimization to a manageable size. When sufficient computational resources are available, unsupervised optimization can be used.

The optimization of the Fast Neutron Source (FNS) at the University of Tennessee is presented as an example for the methodologies developed in this work. …

Exploration Of The Stability Of Multicomponent Metal Halide Perovskites Utilizing Automated, High-Throughput Methods And Machine Learning, Katherine N. Higgins

Doctoral Dissertations

Because of their outstanding optoelectronic properties and low-cost, solution-based fabrication, metal halide perovskites (MHP) are appealing candidates for a variety of applications, such as photovoltaics, light-emitting diodes, photodetectors, and ionizing radiation detectors. However, concerns of this material’s stability in pure or device-integrated form under external stimuli, such as light, humidity, oxygen, and heat, have prohibited the widespread utilizations of MHPs. It is well established that alloying can lessen detrimental effects of these factors. To date, a small portion of alloyed compositions have been investigated compared to the thousands of possible perovskites proposed theoretically. Conventional approaches to materials discovery and optimization, …