07-25, 14:00–17:00 (UTC), Green
This minisymposium will feature the use of the differentiable programming paradigm applied to Earth System Models (ESMs). The goal is to exploit derivative information and seamlessly combine PDE-constrained optimization and scientific machine learning (SciML). Speakers will address (1) Why differentiable programming for ESMs; (2) What ESM applications are we targeting?; and (3) How are we realizing differentiable ESMs? Target ESMs include ice sheet, ocean, and solid Earth models.
The differentiable programming paradigm offers large potential to improve Earth system models (ESMs) in at least two ways: (i) in the context of parameter calibration, state estimation, initialization for prediction, and uncertainty quantification derivative information (tangent linear, adjoint and Hessian) are key ingredients; (ii) combining PDE-constrained optimization with SciML approaches may be performed naturally in a composable way and within the same programming framework. This minisymposium is organized in three parts (all speakers listed are tentative):
1/ Why differentiable programming for ESMs? Speakers will discuss the use of derivative information for PDE-constrained optimization in ice sheet (M. Morlighem, N. Petra), ocean (P. Heimbach) and solid Earth (B. Kaus) modeling; the use of SciML in the context of ESMs (J. Le Sommer, A. Ramadhan); The use of adjoints for sensitivity analysis and uncertainty quantification (N. Loose).
2/ What ESM applications are we targeting? The minisymposium will feature three ESM applications for
Global ocean modeling (C. Hill); ice sheet modeling (J. Bolibar, L. Raess).
3/ How are we realizing differentiable ESMs? A key algorithmic framework is the use of general-purpose automatic differentiation. The Julia is developing a number of packages. ESM applications will likely push the envelope of the capability of existing AD tools. The minisymposium will present how these tools are being used in the context of ESMs (S. Williamson, M. Morlighem). Furthermore, specific algorithmic challenges in ongoing AD tool development will be highlighted (S. Narayanan/M. Schanen/...).
The minisymposium seeks to engage both the ESM and the AD tool communities to advance their respective capability. There will be time for discussion. Ideally we are targeting a 3-hour mini symposium.
Chris Hill is a computational scientist at MIT who has developed ocean and planetary models and modeling tools that are used by thousands of researchers yearly. He has been working with members of the Julia community from its earliest days.
I am a computational oceanographer, professor in the Jackson School of Geosciences, and W. A. “Tex” Moncrief, Jr., chair III in Simulation-Based Engineering and Sciences in the Oden Institute at the University of Texas at Austin. At UT, I direct the CRIOS-UT.github.io group.
My research focuses on ocean and ice dynamics and their role in the global climate system. A computational focus is the use of inverse methods and automatic differentiation applied to ocean and sea ice model parameter and state estimation, uncertainty quantification and observing system design. I earned my Ph.D. from the Max-Planck-Institute for Meteorology and the University of Hamburg, Germany. Prior to joining UT, I spent 16 years at MIT. I am the lead-PI of an NSF CSSI project DJ4Earth.github.io (since 08/2021).
Computational geodynamicist at the University of Mainz, Germany
Sri Hari Krishna is a Computer Scientist at Argonne National Laboratory. He conducts research in automatic differentiation, develops AD tools, and applies them to different scientific domains.