An automated satellite cloud classification scheme using self‐organizing maps: Alternative ISCCP weather states

Journal of Geophysical Research: Atmospheres (2016)

This study explores the application of the self‐organizing map (SOM) methodology to cloud classification.

We demonstrate that this scheme produces clusters which have geographical and seasonal patterns similar to those produced in previous studies using the k‐means clustering technique, but potentially provides complementary information.

We also show that clustering joint histogram data from the ISCCP D1 data set using SOM is a promising methodology for use in cloud classification, and that the SOM scheme automatically creates an organization of the various nodes.