Neural Networks for Operational SYM‐H Forecasting Using Attention and SWICS Plasma Features

Abstract

In this work, we present an Artificial Neural Network for operational forecasting of the SYM‐H geomagnetic index up to 2 hr ahead using the Interplanetary Magnetic Field, the solar wind plasma features and previous SYM‐H values. Former works that forecast the SYM‐H index use data measured by ACE, in particular from the MAG and SWEPAM instruments. However, the plasma data present a high amount of missing samples. This issue has been addressed in the literature, often using linear interpolation, which leads to a non‐accurate data reconstruction, specially when the features are missing during the most intense periods of a geomagnetic storm. To overcome that issue, we use ACE's Solar Wind Ion Composition Spectrometer (SWICS) data to fill the missing plasma features. To validate this technique, we compare the results of our forecasting model trained using plasma features in two ways: only using SWEPAM and performing linear interpolation and using SWICS to fill the missing values in SWEPAM. Then, both models are evaluated in an operational scenario, when only SWEPAM data are available and interpolation can only be performed if the missing values are surrounded by valid measurements. In both cases, our model outperforms the current literature forecasting the SYM‐H one and 2 hr ahead, yielding the best results when the training has been done using the data completed using SWICS measurements.

Forecasting Geomagnetic Storm Disturbances and Their Uncertainties Using Deep Learning

“…The recent work by Collado‐Villaverde et al. (2023) is going in that direction including Attention to the deep‐learning model and also other features with promising results in their of global metrics.…”

“…This split, as shown in Table 1, was proposed by Siciliano et al. (2021) and followed by later works (Collado‐Villaverde et al., 2021, 2023 (since the latter work has been published very recently, it has not been considered as reference work for comparison); Iong et al., 2022). Following the same data set and split as previous works also allows an easy comparison of different results.…”

“…A correction of this uncertainty is outside the scope of this work, given that a larger data set (more storms for training), more input features and maybe a more appropriate architecture should significantly mitigate this behavior. The recent work by Collado-Villaverde et al (2023) is going in that direction including Attention to the deep-learning model and also other features with promising results in their of global metrics.…”

A Framework for Evaluating Geomagnetic Indices Forecasting Models

“…Camporeale (2019) also gave an overview of different metrics for Space Weather related models. Then, geomagnetic indices forecasting works (Bhaskar & Vichare, 2019; Collado‐Villaverde et al., 2023b; Iong et al., 2022; Siciliano et al., 2020) have mainly used the RMSE, defined in Equation , and the Coefficient of determination ( R 2 ), defined in Equation , being the RMSE the key metric of the assessment. For both metrics, y is the observed value, $$\bar{y}$$ is the average of the observed value and $$\widehat{y}$$ is the prediction for N samples.…”

Operational Forecasting of Global Ionospheric TEC Maps 1-, 2-, and 3-Day in Advance by ConvLSTM Model

“…However, in specific instances such as equipment maintenance, network failures, holiday periods, etc., the timely acquisition of geomagnetic and solar indices might pose limitations. These conditions may limit the use of the model and fail to meet the requirements of operational forecasting [30][31][32][33]. Real-time collection of monitoring data emerges as a crucial factor in the transition from Space Weather Research to Operations (R2O) [34][35][36].…”