Master of Science / Department of Electrical and Computer Engineering / Behrooz Mirafzal / Wide bandgap devices have gained increasing attention in the market of power electronics for their ability to perform even in harsh environments. The high voltage blocking and high temperature withstanding capabilities make them outperform existing Silicon devices. They are expected to find places in future traction systems, electric vehicles, LED lightning and renewable energy engineering systems. In spite of several other advantages later mentioned in this paper, WBG devices also face a few challenges which need to be addressed before they can be applied in large scale in industries. Electromagnetic interference and new requirements in packaging methods are some of the challenges being faced by WBG devices. After the commercialization of these devices, many experiments are being carried out to understand and validate their abilities and drawbacks. This paper summarizes the experimental results of various applications of mainly Silicon Carbide (SiC) and Gallium Nitride (GaN) power devices and also includes a section explaining the current challenges for their employment and improvements being made to overcome them.

The high balance-of-system costs of photovoltaic installations indicate that reductions in absorber cost alone are likely insufficient for photovoltaic electricity to reach grid parity unless energy conversion efficiency is also increased. Technologies which both yield high-efficiency cells (>25%) and maintain low costs are needed. GaAs and related III-V semiconductors are used in the highest-efficiency single- and multi-junction photovoltaics, but the technology is too expensive for non-concentrated terrestrial applications. This is due in part to the limited scalability of traditional syntheses, which rely on expensive reactors and employ toxic and pyrophoric gas-phase precursors such as arsine and trimethyl gallium. This work describes GaAs films made by close-spaced vapor transport, a potentially scalable technique which is carried out at atmospheric pressure and requires only bulk GaAs, water vapor, and a temperature gradient to deposit crystalline films with similar electronic properties to GaAs prepared using traditional syntheses. Although close-spaced vapor transport of GaAs was first developed in 1963, there were few examples of GaAs photovoltaic devices made using this method in the literature at the onset of this project. Furthermore, it was unclear whether close-spaced vapor transport could produce GaAs films appropriate for use in photovoltaics. The goal of this project was to create and study GaAs devices made using close-spaced vapor transport and determine whether the technique could be used for production of grid-connected GaAs photovoltaics. In Chapter I the design of the vapor transport reactor, the chemistry of crystal growth, and optoelectronic characterization techniques are discussed. Chapter II focuses on compositional measurements, doping, and improved electronic quality in CSVT GaAs. Chapter III describes several aspects of the interplay between structure and electronic properties of photoelectrochemical devices. Chapter IV addresses heteroepitaxial growth of GaAs on "virtual" Ge-on-Si substrates. This is a topic of importance for the broader III-V community as well as the photovoltaic community, as Si is the substrate of choice in many areas of industry. This dissertation includes unpublished and previously published co-authored material.

Completely inorganic nanoscale clusters play an essential role in many aspects of inorganic chemistry, materials chemistry, and geochemistry. The underlying dynamic behavior of these species in solution defines how and why they make successful thin film precursors as well as exist naturally in the environment. There have been a limited number of previous solution studies involving inorganic nanoscale clusters due to the lack of spectroscopic handles and availability of analytical techniques. This dissertation outlines the available and appropriate characterization techniques needed for identifying and studying inorganic nanoscale species and then uses proton Nuclear Magnetic Resonance (1H-NMR) and Diffusion Ordered Spectroscopy (DOSY) to fully characterize the Ga13-xInx(µ3-OH)6(µ-OH)18(H2O)24(NO3)15 (0 ≤ x ≤ 6) cluster series in solution. This research lays a foundation for a multitude of future studies on the dynamic behavior of these species that was previously unachievable. This dissertation includes previously published and unpublished co-authored material.

O 67Ga é um importante radiofármaco usado para identificar processos inflamatórios em doenças crônicas, diagnóstico por imagem de tumores em tecidos moles e a possibilidade de avaliar o resultado para intervenção terapêutica. Neste trabalho desenvolveu-se um módulo de processamento de 67Ga, com o objetivo de reduzir as intervenções na célula quente, causadas pela oxidação dos materiais metálicos e desgastes nas mangueiras das bombas peristálticas, que soltavam resíduos e bloqueavam a passagem através das válvulas utilizadas no processo. Utilizaram-se materiais como: acrílico, PVC, PEEK e teflon e vácuo como meio de transferência de fluidos líquidos na maioria dos procedimentos, com estas modificações obteve-se redução no comprimento das mangueiras de transferência, aumentando o rendimento do processo com menos intervenções para manutenção e menos tempo de exposição dos trabalhadores à radiação, garantindo a qualidade e reduzindo-se o tempo do processamento. Utilizando-se um sistema móvel para deslocamento do módulo de processamento, facilitou-se a limpeza e manutenção da célula que opera com material radioativo, atendendo-se a Resolução da Diretoria Colegiada da ANVISA que dispõe sobre as Boas Práticas de Fabricação de Medicamentos (RDC-17). / The 67Ga is an important radiopharmaceutical used to identify inflammatory processes in chronic illnesses, diagnosis by image of tumors in soft tissues and the possibility to evaluate the result for therapeutic intervention. In the present work a module of 67Ga processing was developed with the objective to reduce the interventions in the hot cell, in order to avoid oxidation caused by metallic materials, and consuming in hoses of the peristaltic pumps, that release residues that blocked the valves used in the process. With materials such as: acrylic, PVC, PEEK e teflon and they are used vacuum as method (way) of fluid transferences instead of peristaltic pump in the majority of the procedures, with this improvements the system can make shorter the lengths of transference hoses, increasing the yield in the process with less interventions for maintenance and time exposure of the workers, guaranteeing the quality and reducing the time of the processing. using a mobile system for displacement of the processing module making in the cleanness and maintenance of the cell that works with radioactive material. Reducing the time of exposure dose of the workers in compliance with RDC-17 of ANVISA, which ruling the Good Manufacturing Practice Procedures.

Thesis (Ph.D.)--Chinese University of Hong Kong ,2001. / Includes bibliographical references. / Electronic reproduction. Hong Kong : Chinese University of Hong Kong, [2012] System requirements: Adobe Acrobat Reader. Available via World Wide Web. / Mode of access: World Wide Web. / Abstracts in English and Chinese.

Hui Yat Wai. / Thesis (M.Phil.)--Chinese University of Hong Kong, 1993. / Includes bibliographical references (leaves 106-108). / Acknowledgments / Abstract / Chapter 1. --- Introduction --- p.1 / Chapter 2. --- Theory / Chapter 2.1 --- Optical Waveguide --- p.4 / Chapter 2.1.1 --- Optical Waveguide Classification / Chapter 2.1.2 --- Theoretical Analysis of 2-dimensional Step Index Waveguides / Chapter 2.2 --- Optical Waveguides Measurement --- p.18 / Chapter 2.2.1 --- Refractive Index Measurement / Chapter 2.2.2 --- Loss Measurement / Chapter 2.3 --- Ion Implantation and Annealing --- p.36 / Chapter 2.4 --- Refractive Index Change --- p.40 / Chapter 3. --- Equipments and Their Experimental Setup / Chapter 3.1 --- Light Source-Laser Diode --- p.42 / Chapter 3.2 --- Ellipsometry Measurement System --- p.45 / Chapter 3.2.1 --- Ellipsometry Measurement System and its Existing Problems / Chapter 3.2.2 --- Improvement of the Original System / Chapter 3.2.3 --- System Calibration / Chapter 3.3 --- Reflectance Measurement System --- p.51 / Chapter 3.3.1 --- System Design and Setup / Chapter 3.3.2 --- System Calibration / Chapter 3.4 --- End-Coupling Measurement System --- p.56 / Chapter 3.4.1 --- System Setup / Chapter 3.4.2 --- System Calibration / Chapter 4. --- Experiment / Chapter 4.1 --- Samples Preparation --- p.77 / Chapter 4.2 --- Refractive Index Measurement by Ellipsometer --- p.80 / Chapter 4.3 --- Refractive Index Measurement by Reflectance --- p.84 / Chapter 4.4 --- Waveguide Measurement --- p.88 / Chapter 4.4.1 --- Fiber-Waveguide Coupling / Chapter 4.4.2 --- Lens-Waveguide Coupling / Chapter 5. --- Results and Discussion / Chapter 5.1 --- Refractive Index Change and Waveguide Formation --- p.94 / Chapter 5.2 --- Mechanism of Refractive Index Change --- p.100 / Chapter 6. --- Conclusion --- p.103 / Chapter 7. --- Improvement and Extension --- p.105 / Reference --- p.106 / Appendices / Chapter A. --- Thick.m --- p.VI / Chapter B. --- Distrib.m --- p.IX

by Mok Wing Keung. / Parallel title in Chinese characters. / Thesis (M.Phil.)--Chinese University of Hong Kong, 1992. / Includes bibliographical references (leaves 149-154). / Acknowledgement --- p.i / Abstract --- p.ii / Table Of Contents --- p.iii / List Of Figures --- p.v / List Of Tables --- p.ix / List Of Plates --- p.x / Chapter Chapter One --- Introduction / Chapter 1.1 --- General introduction --- p.1 / Chapter 1.2 --- Gallium arsenide --- p.4 / Chapter 1.2.1 --- Basic facts --- p.4 / Chapter 1.2.2 --- Band structure --- p.6 / Chapter 1.2.3 --- Production of GaAs --- p.9 / Chapter 1.3 --- Ion implantation --- p.11 / Chapter 1.3.1 --- Principle of ion implantation --- p.11 / Chapter 1.3.2 --- Basic facts --- p.17 / Chapter 1.3.3 --- Radiation damage and annealing --- p.21 / Chapter 1.4 --- Optical measurements --- p.27 / Chapter 1.4.1 --- Basic facts --- p.27 / Chapter 1.4.2 --- Optical reflectance --- p.29 / Chapter 1.4.3 --- Oxide overlayer --- p.39 / Chapter Chapter Two --- Experimental / Chapter 2.1 --- Sample preparation --- p.42 / Chapter 2.2 --- Ion implantation --- p.46 / Chapter 2.2.1 --- Implantation parameters --- p.46 / Chapter 2.2.2 --- Computer modeling of implantation profiles --- p.48 / Chapter 2.3 --- Annealing --- p.57 / Chapter 2.3.1 --- Conventional annealing --- p.57 / Chapter 2.3.2 --- Rapid thermal annealing --- p.61 / Chapter 2.4 --- Optical reflectance measurement --- p.69 / Chapter 2.4.1 --- Principle of measurement --- p.69 / Chapter 2.4.1.1 --- Relative reflectance measurement --- p.71 / Chapter 2.4.1.2 --- Absolute reflectance measurement --- p.79 / Chapter 2.4.2 --- Error estimation and data reduction --- p.82 / Chapter 2.4.2.1 --- Error estimation --- p.84 / Chapter 2.4.2.2 --- Data reduction --- p.86 / Chapter 2.5 --- Optical microscopy and photoluminescence --- p.90 / Chapter Chapter Three --- Results And Discussion / Chapter 3.1 --- Surface morphology --- p.93 / Chapter 3.2 --- Optical reflectance measurement --- p.101 / Chapter 3.2.1 --- Reflectance spectrum --- p.101 / Chapter 3.2.1.1 --- Reference mirror --- p.101 / Chapter 3.2.1.2 --- Crystalline GaAs --- p.104 / Chapter 3.2.1.3 --- Implanted GaAs before annealing --- p.108 / Chapter 3.2.1.4 --- Conventional annealed GaAs --- p.115 / Chapter 3.2.1.5 --- Rapid thermal annealed GaAs (proximity) --- p.120 / Chapter 3.2.2 --- Extraction of optical constants --- p.128 / Chapter 3.2.2.1 --- Oxide overlayer --- p.128 / Chapter 3.2.2.2 --- Dielectric function --- p.132 / Chapter 3.3 --- Photoluminescence results --- p.143 / Chapter Chapter Four --- Conclusions And Suggestions For Further Work --- p.147 / References --- p.149

by Choi Kup Sze. / Thesis (M.Phil.)--Chinese University of Hong Kong, 1994. / Includes bibliographical references. / Acknowledgement / Abstract / Chapter 1. --- Introduction --- p.1-1 / Chapter 1.1 --- Introduction --- p.1-1 / Chapter 1.2 --- References --- p.1-6 / Chapter 2. --- Theory of Optical Waveguides --- p.2-1 / Chapter 2.1 --- Theory of Planar Slab Waveguides --- p.2-2 / Chapter 2.2 --- Theory of Channel Dielectric Waveguides --- p.2-13 / Chapter 2.2.1 --- Marcatili's Method --- p.2-13 / Chapter 2.2.2 --- Effective Index Method --- p.2-20 / Chapter 2.3 --- References --- p.2-24 / Chapter 3. --- A Numerical Method for Optical Waveguides --- p.3-1 / Chapter 3.1 --- Introduction --- p.3-1 / Chapter 3.2 --- two-dimensional Fourier Series Expansion Method --- p.3-2 / Chapter 3.3 --- References --- p.3-13 / Chapter 4. --- Theory of Directional Couplers --- p.4-1 / Chapter 4.1 --- Dual-Channel Coupler --- p.4-1 / Chapter 4.2 --- Multi-channel Directional Coupler --- p.4-8 / Chapter 4.3 --- References --- p.4-9 / Chapter 5. --- Waveguide Formation by Ion Implantation --- p.5-1 / Chapter 5.1 --- Introduction --- p.5-1 / Chapter 5.2 --- Physics of Ion Implantation --- p.5-3 / Chapter 5.3 --- Lattice Damage and Annealing --- p.5-5 / Chapter 5.3.1 --- Lattice Damage --- p.5-5 / Chapter 5.3.2 --- Annealing --- p.5-6 / Chapter 5.4 --- Index Change due to Implantation --- p.5-8 / Chapter 5.5 --- Waveguide Processing Techniques --- p.5-10 / Chapter 5.5.1 --- Photolithography --- p.5-10 / Chapter 5.5.2 --- Processing Techniques --- p.5-11 / Chapter 5.6 --- References --- p.5-13 / Chapter 6. --- Optical Loss in Waveguides --- p.6-1 / Chapter 6.1 --- Loss Mechanisms in Optical Waveguides --- p.6-1 / Chapter 6.2 --- Principle of Propagation Loss Measurement --- p.6-4 / Chapter 6.2.1 --- Cut-back Method --- p.6-5 / Chapter 6.2.2 --- Scattering Light Method --- p.6-7 / Chapter 6.2.3 --- Fabry-Perot Interference Technique --- p.6-9 / Chapter 6.3 --- References --- p.6-16 / Chapter 7. --- Fabrication and Measurement of Optical Waveguides --- p.7-1 / Chapter 7.1 --- Fabrication of Optical Waveguides --- p.7-1 / Chapter 7.1.1 --- Fabrication of waveguides in GaAs by MeV oxygen ion implantation --- p.7-1 / Chapter 7.1.2 --- Waveguide End Facet Preparation --- p.7-4 / Chapter 7.2 --- Measurement of Optical Waveguides --- p.7-7 / Chapter 7.2.1 --- Laser Sources --- p.7-7 / Chapter 7.2.2 --- Guided Wave Excitation --- p.7-10 / Chapter 7.2.3 --- Intensity Profile Measurement --- p.7-17 / Chapter 7.2.4 --- Coupling Coefficient Measurement --- p.7-20 / Chapter 7.2.5 --- Propagation Loss Measurement --- p.7-25 / Chapter 7.3 --- References --- p.7-34 / Chapter 8. --- Results and Discussions --- p.8-1 / Chapter 8.1 --- Near Field Pattern Measurement --- p.8-1 / Chapter 8.2 --- Discussion on the Index Change of the Implanted GaAs --- p.8-5 / Chapter 8.3 --- Propagation Loss Measurement --- p.8-8 / Chapter 8.4 --- Observation of Optical Coupling in Directional Coupler --- p.8-14 / Chapter 8.5 --- References --- p.8-19 / Chapter 9. --- Conclusion --- p.9-1 / Chapter 10. --- Improvement and Extension --- p.10-1 / Appendix 1 Evaluation of the product〈n2 φuvφu'v'〉 --- p.A1-1 / Appendix 2 Transmission of Lossy Fabry-Perot Cavity --- p.A2-1 / Appendix 3 Effective Index versus Index Difference --- p.A3-1 / Appendix 4 Effect of Temperature on the Transmission of a Fabry-Perot Cavity --- p.A4-1 / Appendix 5 Evaluation of An from the Near Field Pattern --- p.A5-1

by Clive Hau Ming Shiu. / On t.p., "x" and "1-x" are subscript. / Thesis (M.Phil.)--Chinese University of Hong Kong, 1994. / Includes bibliographical references (leaves [126]-[130]). / ACKNOWLEDGEMENT --- p.i / ABSTRACT --- p.ii / TABLE OF CONTENTS --- p.iii / Chapter Chapter 1 --- INTRODUCTION --- p.1 / Chapter Chapter 2 --- THEORY --- p.3 / Chapter 2.1 --- Fundamentals of GaAs and AlGaAs --- p.3 / Chapter 2.1.1 --- Crystal structure and properties of GaAs --- p.4 / Chapter 2.1.2 --- General properties of GaAs at 300K --- p.5 / Chapter 2.1.3 --- Temperature dependence of bandgap for GaAs --- p.6 / Chapter 2.1.4 --- Dopants of GaAs --- p.7 / Chapter 2.1.5 --- Properties of AlGaAs --- p.8 / Chapter 2.2 --- Phase Equilibrium of GaAs and AlGaAs --- p.10 / Chapter 2.2.1 --- Phase diagram of Ga-As binary system --- p.11 / Chapter 2.2.2 --- Phase diagram of Al-Ga-As ternary system --- p.13 / Chapter 2.3 --- Principle of LPE growth --- p.17 / Chapter 2.3.1 --- General concept of liquid phase epitaxy --- p.17 / Chapter 2.3.2 --- Fundamental methods of LPE growth --- p.19 / Chapter 2.4 --- Dopants in GaAs and AlGaAs system --- p.21 / Chapter 2.4.1 --- Common dopants in GaAs --- p.22 / Chapter 2.4.2 --- Tellurium in GaAs --- p.23 / Chapter 2.4.3 --- Silicon in GaAs --- p.24 / Chapter 2.4.4 --- Tellurium and Tin in AlGaAs --- p.26 / Chapter Chapter 3 --- LPE SYSTEM FOR GaAs AND AlGaAs --- p.28 / Chapter 3.1 --- Basic requirements for horizontal sliding LPE system --- p.30 / Chapter 3.2 --- Cleaning process of the LPE system --- p.37 / Chapter 3.2.1 --- Cleaning procedures of the quartz parts --- p.37 / Chapter 3.2.2 --- Cleaning procedures of the stainless steel tubing --- p.38 / Chapter 3.2.3 --- Cleaning procedures of the graphite boat --- p.39 / Chapter 3.3 --- Final examination for LPE growth --- p.41 / Chapter 3.3.1 --- Examining the sealing of the system --- p.41 / Chapter 3.3.2 --- Examining the palladium hydrogen purifier --- p.41 / Chapter 3.3.2.1 --- Measuring the dew point --- p.41 / Chapter 3.3.2.2 --- Measuring the content of oxygen and nitrogen --- p.42 / Chapter 3.3.3 --- Adjusting and measuring the isothermal zone in the fumace --- p.42 / Chapter 3.3.4 --- Measuring of background impurity --- p.43 / Chapter 3.3.5 --- Inspection of the operating chamber --- p.44 / Chapter Chapter 4 --- EXPERIMENTALS --- p.45 / Chapter 4.1 --- Determination of GaAs and AlGaAs content in the source melt --- p.45 / Chapter 4.2 --- Calculation of GaAs and AlGaAs content in the source melt --- p.45 / Chapter 4.3 --- Experimental determination of source melt composition --- p.48 / Chapter 4.4 --- LPE growth method --- p.49 / Chapter 4.5 --- Thickness control of LPE epilayers --- p.49 / Chapter 4.6 --- Experimental procedures --- p.50 / Chapter Chapter 5 --- RESULTS AND DISCUSSIONS --- p.63 / Chapter 5.1 --- Growth condition studies of GaAs --- p.63 / Chapter 5.1.1 --- Experimental --- p.63 / Chapter 5.1.2 --- Phase equilibrium of GaAs in the range of 780 to 840 °C --- p.63 / Chapter 5.1.3 --- Results of undoped GaAs epilayers --- p.67 / Chapter 5.1.4 --- Results of Si doped GaAs epilayers --- p.72 / Chapter 5.2 --- Growth condition studies of AlxGa1-xAs for x=0.1 to 09 --- p.73 / Chapter 5.2.1 --- Phase equilibrium of AlxGa1-xAs for x=0.1 to 09 --- p.73 / Chapter 5.2.2 --- Relation between saturation of solution and he flatness of interface between epilayer and substrate --- p.79 / Chapter 5.2.3 --- Determination of composition x in AlxGa1-xAs --- p.82 / Chapter 5.2.4 --- Relation between epilayer thickness and x in AlxGa1-xAs --- p.84 / Chapter 5.3 --- High AlxGa1-xAs with x ´ 0.9 ° at 780 °C --- p.87 / Chapter 5.3.1 --- Deposition rate of high AlxGa1-xAs epilayer versus cooling rate --- p.87 / Chapter 5.3.2 --- Thickness profiles of epilayers versus cooling rate --- p.89 / Chapter 5.3.3 --- Spectroscopic refractive index of high AlxGa1-xAs in the visible light spectrum --- p.94 / Chapter 5.3.4 --- Rocking curves of high AlxGa1-xAs --- p.96 / Chapter 5.4 --- Tellurium doped AlxGa1-xAs with x ranging from 0.1 to 09 --- p.98 / Chapter 5.4.1 --- Carrier concentration versus composition x in AlxGa1-xAs --- p.98 / Chapter 5.4.2 --- Carrier concentration of Al0.3Ga0.7As versus Te mole fraction --- p.100 / Chapter 5.4.3 --- Donor activation energy of Te Versus x in AlxGa1-xAs --- p.102 / Chapter 5.4.4 --- Refractive index of Te doped AlxGa1-xAs at 300K --- p.105 / Chapter 5.4.5 --- Dependence of solubility upon Te doping level --- p.106 / Chapter 5.5 --- Heavily tellurium doped Al0.3Ga0.7As --- p.107 / Chapter 5.5.1 --- Diffractometry study of heavily Te doped Al0.3Ga0.7As --- p.108 / Chapter 5.5.2 --- Morphological studies and interface studies of heavily Te doped Al0.3Ga0.7As --- p.112 / Chapter Chapter 6 --- CONCLUSION --- p.119 / APPENDIX Photoluminance Analysis at room temperature / REFERENCE

Gallium Nitride (GaN) power devices have the potential to jump-start the next generation of power converters which are smaller, faster, denser, and cheaper. They are thus expected to meet the increasing 21st Century need for power density and efficiency, while at the same time reducing pollution. With the commercialisation of 600 V GaN power devices, which the industry is keen to adopt, come significant challenges. Since there are a number of such devices which are new to the power community, there is a steep learning curve involved, with dispersed information on how best to employ these devices. This work aims to solve this problem through the development of a universal GaN power device and circuit model and the formulation of design rules and guidelines. Through this contribution, designers will be able to better understand and work with these novel devices with relative ease. This will aid the need for faster adoption of GaN devices by the industry solving the barriers to commercialisation. This research demonstrates the use of machine learning (ML) algorithms for behavioural modelling of GaN power devices. Introducing ML as the key to developing a general behavioural and circuit model for GaN power devices combined with understanding, learning, customizing and successfully demonstrating it is the major contribution of this research work. This research first presents a comprehensive investigation into the parasitic effect on the GaN device switching performance. A simple process based on RF techniques is introduced to approximately extract the impedances of the GaN device to develop a behavioural model. The switching behaviour of the model is validated using simulation and double pulse test experiments at 450 V, 10 A test conditions. The developed behavioural model for Transhporm GaN HEMT is 95.2% accurate as the existing LT-spice manufacturer model, and is very much easier for power designers to handle, without the need for knowledge about the physics or geometry of the device. However, given that separate models would need to be developed for each commercial GaN device, the need for a generalized and accurate GaN behavioural model was identified, and it is this generalised model that the remainder of this thesis focuses on. In the next part of this research, a GaN platform test bench is built through bridging RF and power electronics design methodologies to achieve a gate loop and power loop inductance of around 1.8nH with switching waveforms with rise time and fall time around 2.5ns at 450V, 15A, 500KHz test conditions. The double pulse test circuits are customized using different off the shelf gate drives and analysed for collecting switching data for training the ML model. ML modelling using supervised learning is used to predict the switching voltage and current waveforms thus making it possible to construct a generic GaN black box model. Different architectures with single and multi- layer neural networks are explored for modelling. The ability to demonstrate a GaN device ML model that maps both voltage and current inputs and outputs is another characteristic and novel feature of this work. This research demonstrates different types of GaN ML models. The developed voltage and current prediction models are based on feed forward neural network (FFNN), long short-term memory unit (LSTM) and gated recurrent unit (GRU). Several parameters are quantified and compared for validating the models. They are the network architectures, parameters, training time, validation loss and error loss. The ML models are also compared with the demonstrated model of chapter 3 and existing LT-Spice manufacturer models. The results show that the author has been able to develop a GaN LSTM ML model with an error rate of 0.03, and convergence at 3s with excellent stability. The ML based modelling is then translated from GaN power devices to GaN based circuits. Among the different neural network architectures trained and tested, a multi FFNN with 5 hidden layers and 30 neurons, was found to be the best for prediction and optimization. The switching behaviour comparison results shows the benefits and value of ML modelling in opening up whole new possibilities of employing advanced control algorithms for very efficient, reliable and scalable performance of GaN power electronics systems. Finally, the findings of this work have been generalized to frame machine learning based techniques to address the need for generic modelling of power electronic devices. These solutions are presented as an information manual to researchers, engineers and students interested in benefiting from adopting machine learning for power electronics applications.