Potential of Regional Ionosphere Prediction Using a Long Short‐Term Memory Deep‐Learning Algorithm Specialized for Geomagnetic Storm Period

• Published in: Space Weather 2021-09, Vol.19 (9), p.n/a
• Main Authors: Kim, Jeong‐Heon, Kwak, Young‐Sil, Kim, YongHa, Moon, Su‐In, Jeong, Se‐Heon, Yun, JongYeon
• Format: Article
• Language: English
• Subjects: Algorithms; Deep learning; foF2; geomagnetic storm period; Geomagnetic storms; Geomagnetism; Interplanetary magnetic field; Ionosondes; Ionosphere; Ionospheric models; LSTM deep‐learning algorithm; Machine learning; Magnetic fields; Magnetic storms; Mathematical models; Moon; Parameters; Performance prediction; prediction model; Storm forecasting; Storm models; Storms
• ISSN: 1542-7390; 1539-4964; 1542-7390
• DOI: 10.1029/2021SW002741

In our previous study (Moon et al., 2020, https://doi.org/10.3938/jkps.77.1265), we developed a long short‐term memory (LSTM) deep‐learning model for geomagnetic quiet days (LSTM‐quiet) to perform effective long‐term predictions for the regional ionosphere. However, their model could not predict geomagnetic storm days effectively at all. This study developed an LSTM model suitable for geomagnetic storms using the new training data set and redesigning input parameters and hyper‐parameters. We collected 131 days of geomagnetic storm cases from January 1, 2009 to December 31, 2019, provided by the Japan Meteorological Agency's Kakioka Magnetic Observatory, and obtained the interplanetary magnetic field Bz, Dst, Kp, and AE indices related to the geomagnetic storm corresponding to each storm date from the OMNI database. These indices and F2 parameters (foF2 and hmF2) of Jeju ionosonde (33.43°N, 126.30°E) were used as input parameters for the LSTM model. To test and verify the predictive performance and the usability of the LSTM model for geomagnetic storms developed in this manner, we created and diagnosed the 0.5, 1, 2, 3, 6, 12, and 24‐h predictive LSTM models. According to the results of this study, the LSTM storm model for 24‐h developed in this study achieved a predictive performance during the three geomagnetic storms about 32% (10%), 34% (17%), and 37% (5%) better in root mean square error of foF2 (hmF2) than the LSTM quiet model (Moon et al., 2020, https://doi.org/10.3938/jkps.77.1265), SAMI2, and IRI‐2016 models. We propose that the short‐term predictions of less than 3 h are sufficiently competitive than other traditional ionospheric models. Thus, this study suggests that our model can be used for short‐term prediction and monitoring of the regional mid‐latitude ionosphere. Key Points We developed a new long short‐term memory (LSTM) specialized for geomagnetic storm periods by training examples of past geomagnetic storm events Our LSTM storm model improves performance for foF2 by about 32%, 34%, and 37% compared to the LSTM quiet, SAMI2, and IRI‐2016 models We propose that the prediction model less than 3 h using the deep‐learning method can effectively forecast the ionosphere state