![]( "undefined")
第一时间获取气象科研资讯
『气象学家』公众号交流群
加入
『气象学家』公众号交流群
今年的戈登贝尔气候建模奖颁发给了项目“Boosting Earth System Model Outputs and Saving PetaBytes in Their Storage Using Exascale Climate Emulators”，由12人团队（来自沙特阿拉伯阿卜杜拉国王科技大学、NCAR、NVIDIA、美国圣路易斯大学和美国圣母大学）完成这项工作。
原文：
KAUST has been awarded the “Nobel" prize of high-performance computing—the ACM Gordon Bell Prize for Climate Modelling—in partnership with the NSF National Center for Atmospheric Research, U.S. and other partner institutions.
KAUST was a double finalist this year with two projects and won the ACM Gordon Bell Prize for Climate Modelling for the paper: “Boosting earth system model outputs and saving petabytes in their storage using exascale climate emulators.” This was a collaborative effort from KAUST lead research scientist Sameh Abdulah, lead Principal Investigator Al-Khawarizmi Distinguished Professor Marc G. Genton, Professor David E. Keyes, principal research scientist Hatem Ltaief, Professor Georgiy L. Stenchikov, Associate Professor Ying Sun, and postdoc Yan Song. The partner institutions were the NSF National Center for Atmospheric Research, the University of Notre Dame, Saint Louis University, NVIDIA and Lahore University of Management Sciences.
The Gordon Bell Prize is a prestigious award named after the pioneering computer architect who founded the U.S. National Science Foundation’s Directorate for Computing and Information Sciences. The prize, in its 37th year, is awarded annually to recognize outstanding achievements in the field of high-performance computing (HPC) applied to real-world systems.
This is the first time an institution in the Middle East has won an ACM Gordon Bell Prize, a significant milestone for Saudi Arabia and the region.
Abdulah commented, “Thank you to the entire team for their dedication and hard work. Winning the HPC Gordon Bell Prize is a significant milestone, not just for us but also for KAUST, reaffirming our position as the leading university in the region.”
“Words cannot describe how excited I am about this once-in-a-lifetime prize, but this is exactly why I decided to join KAUST over a decade ago—to make it happen,” commented Genton.
Professor Keyes commented, “This is the third consecutive year of being a finalist, and it is exciting to finally bring home a Gordon Bell prize for the young researchers on the team and for Saudi Arabia.”
While climate modeling has been a scientific practice since the 1950s, recently introduced exascale supercomputers (which can process a quintillion calculations each second) offer the opportunity to understand climate change at a far more advanced level than ever before. Using exascale computers, computer scientists and climate scientists have developed extremely high-resolution earth system models.
These models offer great promise in understanding the Earth’s climate, but they require a great deal of computational time and energy and a tremendous amount of storage for the massive quantity of data they generate.
In the winning paper, KAUST scientists, in collaboration with partners, developed an exascale climate emulator to meet the rising computational and storage demands of high-resolution earth system models.
A statistical emulation of a system, like the global climate, can reproduce statistics of interest concerning the system without requiring an ensemble of detailed simulations of the system. It employs a small number of detailed simulations or direct observations of a system to develop a more compact model that can be probed at will for the expected behavior of the system at arbitrary points in space or time. For example, the system could be used to identify the number of days in a crop-bearing season when rain is expected or expected winds at a particular hour for which windfarm capacity is being sized at a given location, or the snow expected in a ski week at a particular resort. Without an emulator, such results would come from averaging simulations or observations over vast volumes of data that would need to be stored.
As demonstrated on multiple supercomputers, including KAUST's Shaheen III, the emulator could save several petabytes of computing storage space. By comparison, one petabyte is equal to the storage capacity of approximately 170 top-end servers.
Ltaief and Keyes have co-authored all four of KAUST’s Gordon Bell finalist papers over the past three years, along with different applications experts in statistics, climate, genomics and seismic imaging.
The ACM Gordon Bell Prize for Climate Modelling was presented during the International Conference for High Performance Computing, Networking, Storage and Analysis (SC24) and was held November 17 – 22 in Atlanta, Georgia.
KAUST is a key player in COP16 this December in Riyadh, where the University will be sharing updates regarding its applied climate solutions with the policymakers and leaders in attendance.
The following is the full list of authors: Sameh Abdulah from KAUST; Allison H. Baker from Informational Science Lab, NSF National Center for Atmosphere Research U.S.; George Bosilica from NVIDIA; Qinglei Cao from Department of Computer Science, Saint Louis University U.S.; Stefano Castruccio from Department of Applied and Computational Mathematics and Statistics, University of Notre Dame USA; Marc G. Genton and David E. Keyes from KAUST; Zubair Khalid from LUMS; Hatem Ltaief, Yan Song, Georgiy L. Stenchikov and Ying Sun from KAUST.
来源：WetWan、KAUST官网
