Environmental researchers to use AI supercomputer for earth observation

Environmental researchers are set to benefit from a powerful supercomputer that will slash their data workload processing times.

Plymouth Marine Laboratory is offering out its first HPC (high performance computing) service for applying artificial intelligence to earth observation data.

The technology allows environmental scientists to complete research in ten days that would have taken 16 months on the previous machine used, said the Laboratory.

The facility is part of the Natural Environment Research Council (NERC) Earth Observation Data Acquisition and Analysis Service (NEODAAS).

The new Massive GPU Cluster for Earth Observation (MAGEO) will be used for a diverse range of applications including wildfires, oil spill and plastics detection, mangrove mapping and satellite and airborne data fusion.

It has previously contributed to the COVID-19 sequencing effort by donating computing power to Folding@Home.

Despite having only recently been installed, MAGEO has been used to develop a new method for the estimation of chlorophyll concentrations in the upper ocean. The method would have taken 16 months to train on a single GPU machine, but using MAGEO it took only ten days.

Daniel Clewley, NEODAAS manager and research software engineer at Plymouth Marine Laboratory, said: “AI is a tremendous step forward within the earth observation field. A staggering amount of data is produced by satellite every day and by using AI researchers can tease out changes, trends and anomalies not possible with standard analysis.”

The cluster is built around five special edition NVIDIA DGX-1 MaxQ nodes, providing energy efficient processing using 50 per cent of the power of a standard DGX-1 unit, whilst still delivering 80 per cent of the capacity.

Each DGX-1 at Plymouth has 40,960 CUDA cores and 40 Intel Xeon 2.2 GHz cores.

    Share Story:

Recent Stories