Arpit Kapoor

Arpit Kapoor is a Postdoctoral Research Associate in the Faculty of Engineering at The University of Sydney, specializing in the integration of physics into modern Machine Learning and Deep Learning approaches for water resource modelling and related applications. He submitted his PhD thesis titled "Process-aware hybrid deep learning for environmental systems and extremes" at the School of Mathematics and Statistics, University of New South Wales (UNSW), in February 2026. During his PhD, he was part of the ARC Training Centre in Data Analytics for Resources and Environment (DARE Centre) HDR training program, where he received rigorous training in statistical data science tools for environmental modelling. His PhD was supervised by Dr. Rohitash Chandra, Dr. Sahani Pathiraja, and Professor Lucy Marshall, focusing on the synergy of process-based hydrological models with machine learning to advance environmental process modelling. As part of his PhD research, he developed hybrid and Bayesian deep learning approaches for rainfall–runoff modelling, flood forecasting, cyclone prediction, and groundwater flow emulation. Arpit also holds industry experience working with the Bureau of Meteorology for the implementation of multivariate bias correction methods for climate datasets produced for the Australian Climate Service. He has worked in multiple industries solving business-critical data intelligence and computer vision problems through machine learning and data science.

Arpit Kapoor is a researcher at the University of Sydney with expertise in Machine Learning, Environmental Data Science, and Hydrology. His work focuses on developing advanced machine learning techniques for environmental systems, particularly in hydrological modeling and climate data analysis. Kapoor has published extensively on deep learning hybridization for rainfall-runoff modeling, Bayesian neural networks, and uncertainty quantification in climate predictions. His research also includes climate model bias correction and flood prediction using ensemble deep learning frameworks. Kapoor's contributions emphasize the integration of data science with environmental challenges to improve predictive accuracy and inform policy decisions.