Unravelling Earth’s geological history with geoscientific models

PUBLIC SEMINAR
School of Computing, Information and Mathematical Sciences
Faculty of Science, Technology and Environment
The University of the South Pacific
THURSDAY, SEPTEMBER 5 2019,11 am, N111
FSTE Smart Room, FSTE building, Laucala Campus, USP.
"Unravelling Earth’s geological history with geoscientific models powered by artificial intelligence"
The geological past of Earth's history is enigmatic due to limited data. Unravelling Earth evolution requires a fusion of available data and expert knowledge with models that capture environmental and geological processes. Over the past decade, there has been an increase in using artificial intelligence methodologies for optimisation and uncertainty quantification of unknown parameters in geoscientific forward models. The seminar highlights some of my recent work in this area that features contribution in the area of landscape evolution, reef evolution, and paleoclimate reconstruction over millions of years. These include the evolution of the Australian continent over 150 million years that feature timelines when a large portion of the interior of the continent was covered by the ocean. Reef evolution simulation focuses on the past ten thousand years using drilled reef-core data featuring the growth of the coralgae assemblages in the Great Barrier Reef given different environmental conditions. Furthermore, Bayesian machine learning is employed for paleoclimate reconstruction using coal deposit datasets to reconstruct forest covers, and precipitation estimation in deep time, of up to 250 million years.
----
Dr. Rohitash Chandra is a USyd Research Fellow (2016-2019) and Co-Lead of Natural Resources theme at the Centre for Translational Data Science, and School of Geosciences, University of Sydney. Dr. Chandra has a built a program of research encircling methodologies and applications of artificial intelligence; particularly in areas of deep learning, neuro-evolution, Bayesian methods, climate extremes, solid Earth Evolution, reef modelling and mineral exploration. Together with leading international interdisciplinary teams, he has attracted over 11 million dollars from various funding agencies, including the Deep Carbon Observatory (2018-2019) and the recently announced Australian Research Council (ARC) Training Centre for Data Analytics in Minerals and Resources (2020-2025), Australia’s first effort in training data scientists for the natural resources sector. Further details of his research projects and outputs can be found here: sydney.edu.au/...
researchgate.n...
Seminar pdf: github.com/roh...