Skip to content

Research Seminar - The Potential of Deep Learning Techniques and Satellite-Based Data in Predicting air Pollution for Smart Cities

Presented by Dr Ekta Sharma, Vice-Chancellor's Postdoctoral Research Fellow for Women In STEMM School of Mathematics, Physics and Computing, UniSQ
28 MAR 2023
12.00 PM - 1.00 PM
Toowoomba - D207, or via Zoom

Public health risks arising from airborne pollutants can significantly elevate ongoing and future healthcare costs. A significant challenge in designing practical air quality systems is the chaotic behaviour of air pollutants that poses major difficulties in tracking three-dimensional movements over diverse temporal domains. The talk will discuss the importance of building deep-learning hybrid models to forecast air contaminants. The efficacy of these models will also be elucidated in the model testing phase at several study regions where air pollution is a considerable threat to public health. Finally, the practical utility of these models will be discussed for air-polluting forecasting systems in health risk mitigation.

Dr. Ekta Sharma is a researcher with research interests in applied artificial intelligence. She is currently working with the Australian Government’s National Intelligence Community on space satellite communication challenges. She is also working as the UniSQ's Vice Chancellors' Postdoctoral Fellow for Women in the STEMM discipline. This work supports UniSQ’s commitment to improving career pathways for women as part of the Science in Australia Gender Equity Athena Swan Action Plan. Her Ph.D. research with an excellence award designed novel methods in early warning systems to predict critical atmospheric pollutants. The work got featured in multiple newspapers and media outlets. Dr. Sharma has over a decade of strong technical and teaching experience in Australia, Switzerland, and India. Her other background in Operations Research and double Master's (Mathematical Sciences) assist her to accomplish key processes in a feasible, sustainable, and optimum manner. This has awarded her competitive grants reserved for top Australian females working on big data. She has co-authored 8 books and serves as a reviewer for many key academic journals, such as JMLR, IEEE-TPAMI, IEEE-ACCESS, STOTEN among many others. She is based in Springfield at the School of Mathematics, Sciences, and Computing.

For further details, please contact Di Wu.