English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

We have used time-delay feed-forward neural\udnetworks to compute the geomagnetic-activity index Dst one\udhour ahead from a temporal sequence of solar-wind data. The input data include\udsolar-wind density n, velocity V and the southward component Bz\udof the interplanetary magnetic field. Dst is not included in\udthe input data. The networks implement an explicit functional relationship\udbetween the solar wind and the geomagnetic disturbance, including both direct\udand time-delayed non-linear relations. In this study we especially consider the\udinfluence of varying the temporal size of the input-data sequence. The networks\udare trained on data covering 6600 h, and tested on data covering 2100 h. It is\udfound that the initial and main phases of geomagnetic storms are well predicted,\udalmost independent of the length of the input-data sequence. However, to predict\udthe recovery phase, we have to use up to 20 h of solar-wind input data. The\udrecovery phase is mainly governed by the ring-current loss processes, and is\udvery much dependent on the ring-current history, and thus also the solar-wind\udhistory. With due consideration of the time history when optimizing the\udnetworks, we can reproduce 84% of the Dst variance

Predicting geomagnetic storms from solar-wind data using time-delay neural networks