TY - JOUR
T1 - Data-Driven Forecasting of Low-Latitude Ionospheric Total Electron Content Using the Random Forest and LSTM Machine Learning Methods
AU - Zewdie, Gebreab K.
AU - Valladares, Cesar
AU - Cohen, Morris B.
AU - Lary, David J.
AU - Ramani, Dhanya
AU - Tsidu, Gizaw M.
N1 - Funding Information:
This work was supported by the Defense Advanced Research Projects Agency (DARPA) under Department of the Interior Award D19AC00009 to Georgia Tech. We would like to thank the International GNSS Service (IGS), Geocentric Reference System for the Americas (SIRGAS) for providing GPS data. One of the authors Dr. Valladares was partially supported by Grants AGS-1552161, AGS-1563025, AGS-1933056 and ONR contract N-00014-17-1-2157. The Low Latitude Ionospheric Sensor Network (LISN) is a project led by the University of Texas at Dallas in collaboration with the Geophysical Institute of Peru and other institutions that provide information in benefit of the space weather scientific community. The authors would also like to thank NASA?s Space Physics Data Facility (SPDF) for making freely available different space weather related data sets.
Funding Information:
This work was supported by the Defense Advanced Research Projects Agency (DARPA) under Department of the Interior Award D19AC00009 to Georgia Tech. We would like to thank the International GNSS Service (IGS), Geocentric Reference System for the Americas (SIRGAS) for providing GPS data. One of the authors Dr. Valladares was partially supported by Grants AGS‐1552161, AGS‐1563025, AGS‐1933056 and ONR contract N‐00014‐17‐1‐2157. The Low Latitude Ionospheric Sensor Network (LISN) is a project led by the University of Texas at Dallas in collaboration with the Geophysical Institute of Peru and other institutions that provide information in benefit of the space weather scientific community. The authors would also like to thank NASA’s Space Physics Data Facility (SPDF) for making freely available different space weather related data sets.
Publisher Copyright:
© 2021. The Authors.
PY - 2021/6
Y1 - 2021/6
N2 - In this research, we present data-driven forecasting of ionospheric total electron content (TEC) using the Long-Short Term Memory (LSTM) deep recurrent neural network method. The random forest machine learning method was used to perform a regression analysis and estimate the variable importance of the input parameters. The input data are obtained from satellite and ground based measurements characterizing the solar-terrestrial environment. We estimate the relative importance of 34 different parameters, including the solar flux, solar wind density, and speed the three components of interplanetary magnetic field, Lyman-alpha, the Kp, Dst, and Polar Cap (PC) indices. The TEC measurements are taken with 15-s cadence from an equatorial GPS station located at Bogota, Columbia (4.7110° N, 74.0721° W). The 2008–2017 data set, including the top five parameters estimated using the random forest, is used for training the machine learning models, and the 2018 data set is used for independent testing of the LSTM forecasting. The LSTM method as applied to forecast the TEC up to 5 h ahead, with 30-min cadence. The results indicate that very good forecasts with low root mean square (RMS) error (high correlation) can be made in the near future and the RMS errors increase as we forecast further into the future. The data sources are satellite and ground based measurements characterizing the solar-terrestrial environment.
AB - In this research, we present data-driven forecasting of ionospheric total electron content (TEC) using the Long-Short Term Memory (LSTM) deep recurrent neural network method. The random forest machine learning method was used to perform a regression analysis and estimate the variable importance of the input parameters. The input data are obtained from satellite and ground based measurements characterizing the solar-terrestrial environment. We estimate the relative importance of 34 different parameters, including the solar flux, solar wind density, and speed the three components of interplanetary magnetic field, Lyman-alpha, the Kp, Dst, and Polar Cap (PC) indices. The TEC measurements are taken with 15-s cadence from an equatorial GPS station located at Bogota, Columbia (4.7110° N, 74.0721° W). The 2008–2017 data set, including the top five parameters estimated using the random forest, is used for training the machine learning models, and the 2018 data set is used for independent testing of the LSTM forecasting. The LSTM method as applied to forecast the TEC up to 5 h ahead, with 30-min cadence. The results indicate that very good forecasts with low root mean square (RMS) error (high correlation) can be made in the near future and the RMS errors increase as we forecast further into the future. The data sources are satellite and ground based measurements characterizing the solar-terrestrial environment.
UR - http://www.scopus.com/inward/record.url?scp=85108582139&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85108582139&partnerID=8YFLogxK
U2 - 10.1029/2020SW002639
DO - 10.1029/2020SW002639
M3 - Article
AN - SCOPUS:85108582139
SN - 1542-7390
VL - 19
JO - Space Weather
JF - Space Weather
IS - 6
M1 - e2020SW002639
ER -