Hewlett Packard Enterprise (HPE), through a strategic partnership with the US Department of Energy’s Oak Ridge National Laboratory (ORNL), has built a new supercomputer for the United States Air Force (USAF) to support weather modeling and forecasting projects.
The new system, powered by HPE Cray EX supercomputers, is now operational at ORNL in Oak Ridge, Tennessee, where it is managed by ORNL’s high-performance computing (HPC) systems team. Air Force Weather, the Air Force’s meteorology division, will leverage the new system to support research and development needs in addition to its operational role. The HPE Cray EX supercomputers feature second-gen AMD EPYC processors to enable significant compute performance to process large and complex volumes of computations necessary to simulate weather data.
The new system comprises two supercomputers that the US Air Force has named Fawbush and Miller after meteorologists Major Ernest Fawbush and Captain Robert Miller, who predicted the first tornado forecast at the Tinker Air Force Base in Oklahoma in 1948. The combined capability of the computers makes the system 6.5 times faster than Air Force Weather’s existing system, allowing larger computations at a higher resolution. They should also allow for an increase in accuracy of global weather simulations from 17km between model grid points to 10km.
“We are thrilled to have built the US Air Force a new supercomputer that is one of the first operational systems powered by the latest HPE Cray EX supercomputer and managed by Oak Ridge National Laboratory (ORNL). The end-to-end HPC technologies made possible by the HPE Cray EX supercomputer will enable greater speed and dedicated performance to advance simulations in weather forecasting that were never made possible before,” said Bill Mannel, vice president and general manager, HPC at HPE. “We look forward to our continued collaboration with Oak Ridge National Laboratory in supporting a range of complex science and engineering research, which includes powering ORNL’s Frontier, one of the nation’s upcoming exascale systems.”
The system’s new levels of performance and combined advancements will, says the US Air Force, allow it (in collaboration with ORNL’s Computational Earth Sciences Division), to introduce completely new forecasting capabilities over the next several years and it hopes to make breakthroughs in the following areas:
- Forecasting of stream flow, flooding, or inundation to predict how much of a given land will be submerged in water and the level of its depth. Researchers hope to achieve this by creating a global hydrology model that involves simulating hundreds of watershed and drainage basins to eventually increase accuracy in predicting future events.
- Remote sensing of a cloud-covered area to address how to navigate impacted missions through forecasting the formation, growth and precipitation of atmospheric clouds. Researchers plan to achieve this by using comprehensive cloud physics that are not made possible with existing statistical regression models.