PhD Scholarship in Artificial Intelligence and Machine Learning for Photovoltaics Luminescence Imaging

The University of New South Wales, Sydney, Australia

The Research Environment The Computer Vision and Machine Learning Group is based in the School of Computer Science and Engineering, the University of New South Wales, Sydney, Australia. Its research interests include image analysis and visual analytics based on computer vision and machine learning. style='mso-spacerun:yes'>  Strong collaborative links exist with research groups within UNSW, including Photovoltaics and Renewable Energy, Biology, Optometrics and Vision Science and Medicine, and hospital-based medical research centres, industry and other universities, with a number of ongoing funded research projects and consultancies in the areas of interest. The research is supported by government, industry and strategic university funding schemes. The group currently consists of a number academics, postdocs, PhD students and honours level students. For details about the university, consult this link. For details about the school and its research, consult this link.

 

The School of Photovoltaic and Renewable Energy Engineering (SPREE) is one of the eight schools within the Faculty of Engineering at the University of New South Wales (UNSW), Sydney, Australia. The school is widely considered as the best in the world. Building on its world-leading research, the school attracts leading international researchers in the area of photovoltaic. Our academic staff has been consistently ranked amongst the leaders worldwide in the photovoltaic field through international peer review. Our team has held the world record for silicon solar cell efficiencies for over twenty years and has been responsible for developing the most successfully commercialised photovoltaic technology internationally throughout the same period. The solar cell technology that is predicted to dominate the market in the next decade (the ‘PERC’) was invented and developed in the school. For details about the school and its research, consult this link.

The Project Research opportunities are currently available in a research project on Artificial Intelligence and Machine Learning for Photovoltaics Luminescence Imaging , in collaboration  with Between CSE and SPREE, funded by an ARENA grant, with strong industry backing. The aim of this project is to develop machine learning algorithms for analysing luminescence-based images in order to improve the efficiency of solar cells. Photoluminescence (PL) – the emission of light from a material after the absorption of photons – has been proven to be a very powerful monitoring tool for photovoltaic devices. PL imaging was developed at UNSW more than a decade ago. Since the first proof of concept studies in our laboratories, this technology has seen rapid adoption worldwide by researchers and companies and is now one of the most widely used techniques. For silicon devices, PL imaging is frequently used to monitor essential electrical parameters such as minority carrier lifetime, implied open-circuit voltage, diode saturation currents, series resistance, shunt resistance, and pseudo fill factor. The contactless nature of the measurement and the fact that it can be performed even on non-completed devices makes it an ideal tool to investigate various limiting processes within silicon wafers and silicon solar cells. UNSW has an internationally leading position in the growth of PL as an effective inspection tool for silicon photovoltaics.

This project will benefit from the large knowledge and experience in SPREE on various PL technologies in developing new groundbreaking PL-based applications for silicon and non-silicon solar cells.

The main project aims are to:

* Develop machine learning algorithms to extract various electrical properties for luminescence images of silicon wafers, solar cells, and photovoltaic modules

* Develop machine learning algorithms to improve the reliability of photovoltaics systems

* Develop machine learning algorithms to develop the new generation of solar cells

* Saving the world!

The PhD scholarship Suitable students will be awarded a full scholarship for 3.5 years (PhD duration in Australia is 3-3.5 years). The scholarship fully covers the university fees and provides an additional allowance to cover living costs:

Tuition fees: $45,000 per year

Living allowance: $27,000 per year

Conference allowance: $3,000 per conference (to support attending a scientific international conference; at least two conferences during the PhD). Both local and international students may apply for PhD admission using the university procedure, link at the end.

Requirements: Bachelor’s degree in Computer Science or Computer Engineering with a graduation GPA above 8 out of 10 or equivalent.

Desirable : Priority will be given for those who graduated from a Masters by research program, focusing on machine learning, big data, or similar. Supervision will be done jointly by Associate Professor Ziv Hameiri (SPREE), Prof Arcot Sowmya (CSE), and Prof. Thorsten Trupke (SPREE). For more details please contact Associate Professor Ziv Hameiri (ziv.hameiri@unsw.edu.au) or Professor Arcot Sowmya (a.sowmya@unsw.edu.au).

For admission procedure, consult here.

For further information, contact:

Ziv Hameiri
(email: ziv.hameiri@unsw.edu.au

Prof. Arcot Sowmya
(email: a.sowmya@unsw.edu.au

The application procedure To apply for project support, your application should include:

·  a CV that highlights any publications, awards and prizes you have received,

·  undergraduate/postgraduate transcripts, and

·  the names of two referees.

All of the above should be included in a SINGLE PDF file, and be forwarded electronically by Sept 18, 2020 to:
Ziv Hameiri, email:ziv.hameiri@unsw.edu.au and Arcot Sowmya, email: a.sowmya@unsw.edu.au