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.

The goal of this research was to identify why the federal government should invest in solar research and development, and which areas of solar improvement should be focused on. Motivation for this can be found in the pressing need to prevent and reverse the effects of climate change, the inevitability of fossil fuel resources eventually running out, and the economic and job creation potential which solar energy holds. Additionally, it is important to note that the best course of action will involve a split of funding between current solar rollout and energy grid updating, and the R&D listed in this research. Upon examination, it can be seen that an energy revolution, led by a federal solar jobs program and a Green New Deal, would be both an ethically and economically beneficial solution. A transition from existing fossil fuel infrastructure to renewable, solar-powered infrastructure would not only be possible but highly beneficial in many aspects, including massive job creation, a more affordable, renewable energy solution to replace coal-fired plants, and no fuel spending or negotiation required.<br/>When examining which areas of solar improvement to focus on for R&D funding, four primary areas were identified, with solutions presented for each. These areas for improvement are EM capture, EM conversion efficiency, energy storage capacity, and the prevention of overheating. For each of these areas of improvement, affordable solutions that would greatly improve the efficiency and viability of solar as a primary energy source were identified. The most notable area that should be examined is solar storage, which would allow solar PV panels to overcome their greatest real and perceived obstacle, which is the inconsistent power generation. Solar storage is easily attainable, and with enough storage capacity, excess solar energy which would otherwise be wasted during the day can be stored and used during the night or cloudy weather as necessary. Furthermore, the implementation of highly innovative solutions, such as agrivoltaics, would allow for a solar revolution to occur.