Fig. 3 | Scientific Reports

Fig. 3

From: Understanding machine learning weather prediction by designing a cost-efficient model with knowledge-oriented modules

Fig. 3

Spatial distribution of ACC on forecast day 5 for T2M and Z500, and the effects of GeoCyclic Padding and SENet. (a, d) ACC of KARINA for T2M and Z500. (b, e) ACC difference between KARINA and KARINA w/o pad (i.e., Effect of GeoCyclic Padding) for T2M and Z500. (c, f) same as b and e, but for KARINA w/o SENet. In the second and third columns, positive (negative) values indicate a gain (loss) in forecasting performance due to the application of each module. The maps were generated using the Python Matplotlib (version 3.7.2; http://matplotlib.org/).

Back to article page