5:00-6:00 PM Networking
6:00-7:00 PM Dinner
7:00-8:00 PM Presentation
Using Machine Learning Approaches To Address Carbon Cycling-Related Questions
Quantification of carbon fluxes from the weathering of various rocks in addition to other sources in the land water system is critical to understand the global carbon cycle and to tackle the inevitable climate change. Traditional modeling approaches are limited with respect to reproducing empirical estimates. Characterization of coupled water and carbon cycling is utterly complicated due to their heterogeneous and anisotropic properties, especially when anthropogenic activities are also involved. In the big data era, the improved computational capability along with the new assemblage of varying types of geochemical, geophysical, and biological datasets provide us with new tools to probe carbon cycling-related questions, particularly those pertaining to the assessment of anthropogenic impacts. In this presentation, we will demonstrate a few examples of our recent research efforts in which we apply various data-driven approaches to resolve a few critical carbon cycling-related science questions on multiple spatiotemporal scales. In addition, we will also share our thoughts on what we can benefit from and contribute to the emerging big data evolution across the Earth science fields, particularly as geochemists.
Bio:
Dr. Tao Wen is an Assistant Professor in the Department of Earth and Environmental Sciences at Syracuse University. Dr. Wen received his Ph.D. in Geology from the University of Michigan and worked as a postdoc at the Pennsylvania State University. His research interests are broadly at the interface between humankind and water/carbon cycles. His research group blends field-based, laboratory-based, and data-driven approaches to assess the patterns and drivers of water/carbon cycles in the coupled human and natural systems.