Harnessing machine learning for accurate treatment of overlapping opacity species in general circulation models

Open Access

Table 2

Runtime.

Label	Time [h]	Relative to PRE
PRE	3.91	1.00
ADD	7.20	1.84
AEE	7.44	1.90
AEE_we	13.37	3.42
DS	10.88	2.78
RORR	25.12	6.43

Notes. Runtime of the GCM needed for the first 100 days of the simulation. The node used to run the model includes 2x Intel(R) Xeon(R) Gold 6248R CPU at 3.00 GHz, and we utilized all 48 cores.

Current usage metrics show cumulative count of Article Views (full-text article views including HTML views, PDF and ePub downloads, according to the available data) and Abstracts Views on Vision4Press platform.

Data correspond to usage on the plateform after 2015. The current usage metrics is available 48-96 hours after online publication and is updated daily on week days.

Initial download of the metrics may take a while.