A review of new science, in plain language

Geophysical Research Letters  ·  22 July 2026  ·  From issue 10

Physics‐Embedded Deep Learning Reveals the Memory Effect of Ionospheric Electron Density in Response to Solar EUV Forcing

A computer model learned how the upper atmosphere remembers past sunlight before reacting fully.

Hongwei Gong, Hanxian Fang et al.

The upper atmosphere does not react to sunlight right away. It holds a kind of memory of past sunlight before its electron levels fully respond. A new computer model learned this memory pattern from real ground station data, instead of guessing a fixed delay. The learned pattern matched known chemistry timing closely, with a correlation of about 0.97, and the model predicted electron levels well during high solar activity.

Integrity screen: passed (3 checks) Checked 24 July 2026. Read the source

The plain-language reading of this paper is in the full issue, for subscribers.

Read the full issue

Five vetted papers in plain language, free, every two days

Five papers free every issue, about 15 emails a month. No spam. Leave in one click.

Also in issue 10 15 papers
More from Geophysical Research Letters