Forecasting SYM‐H Index: A Comparison Between Long Short‐Term Memory and Convolutional Neural Networks. Issue 2 (10th February 2021)

• Record Type: Journal Article
• Authors: Siciliano, F.; Consolini, G.; Tozzi, R.; Gentili, M.; Giannattasio, F.; De Michelis, P.
• Is Part Of: Space weather. Volume 19:Issue 2(2021)
• Page Start: n/a
• Page End: n/a
• Publication Date: 2021-02-10
• Subjects: forecasting -- neural networks -- geomagnetic storms -- SYM‐H index; Space environment -- Periodicals; 551.509992
• DOI: 10.1029/2020SW002589
• Languages: English
• ISSNs: 1542-7390

Abstract

Abstract: Forecasting geomagnetic indices represents a key point to develop warning systems for the mitigation of possible effects of severe geomagnetic storms on critical ground infrastructures. Here we focus on SYM‐H index, a proxy of the axially symmetric magnetic field disturbance at low and middle latitudes on the Earth's surface. To forecast SYM‐H, we built two artificial neural network (ANN) models and trained both of them on two different sets of input parameters including interplanetary magnetic field components and magnitude and differing for the presence or not of previous SYM‐H values. These ANN models differ in architecture being based on two conceptually different neural networks: the long short‐term memory (LSTM) and the convolutional neural network (CNN). Both networks are trained, validated, and tested on a total of 42 geomagnetic storms among the most intense that occurred between 1998 and 2018. Performance comparison of the two ANN models shows that (1) both are able to well forecast SYM‐H index 1 h in advance, with an accuracy of more than 95% in terms of the coefficient of determination R 2 ; (2) the model based on LSTM is slightly more accurate than that based on CNN when including SYM‐H index at previous steps among the inputs; and (3) the model based on CNN has interesting potentialities being more accurate than that based on LSTM when not including SYM‐H index among the inputs. Predictions made including SYM‐H index among the inputs provide a root mean squared error on average 42% lower than that of predictions made without SYM‐H . Plain Language Summary: Geomagnetic indices are proxies of geomagnetic disturbances observed on the ground during geomagnetic storms and substorms. This work deals with the forecasting of one of such indices, that is, SYM‐H index, using two different artificial neural network architectures. Between the two, one has never been used for this purpose, being generally applied for image processing. Both the architectures provide good predictions. The capability to forecast high‐resolution geomagnetic indices, such as SYM‐H index, is crucial in issuing alerts for fast geomagnetic disturbances which can be responsible for the activation of geomagnetically induced currents (GICs), one of the most harmful ground effects of space weather events. Key Points: Two artificial neural network (ANN) models are built to forecast SYM‐H index 1 h ahead using interplanetary magnetic field measurements The developed models are based on two conceptually different neural networks: long short‐term memory and convolutional neural network (CNN) CNN, used here for the first time for geomagnetic indices forecasting, has proved potentialities worth being further explored