{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,12]],"date-time":"2026-06-12T19:22:50Z","timestamp":1781292170072,"version":"3.54.1"},"reference-count":48,"publisher":"MDPI AG","issue":"19","license":[{"start":{"date-parts":[[2021,9,26]],"date-time":"2021-09-26T00:00:00Z","timestamp":1632614400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["No.41574146, 41774162, 42074187"],"award-info":[{"award-number":["No.41574146, 41774162, 42074187"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"National Key R&amp;D Program of China","award":["No. 2018YFC1503506"],"award-info":[{"award-number":["No. 2018YFC1503506"]}]},{"name":"Excellent Youth Foundation of Hubei Provincial Natural Science Foundation","award":["No. 2019CFA054"],"award-info":[{"award-number":["No. 2019CFA054"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Remote Sensing"],"abstract":"<jats:p>In this paper, a deep learning long-short-term memory (LSTM) method is applied to the forecasting of the critical frequency of the ionosphere F2 layer (foF2). Hourly values of foF2 from 10 ionospheric stations in China and Australia (based on availability) from 2006 to 2019 are used for training and verifying. While 2015 and 2019 are exclusive for verifying the forecasting accuracy. The inputs of the LSTM model are sequential data for the previous values, which include local time (LT), day number, solar zenith angle, the sunspot number (SSN), the daily F10.7 solar flux, geomagnetic the Ap and Kp indices, geographic coordinates, neutral winds, and the observed value of foF2 at the previous moment. To evaluate the forecasting ability of the deep learning LSTM model, two different neural network forecasting models: a back-propagation neural network (BPNN) and a genetic algorithm optimized backpropagation neural network (GABP) were established for comparative analysis. The foF2 parameters were forecasted under geomagnetic quiet and geomagnetic disturbed conditions during solar activity maximum (2015) and minimum (2019), respectively. The forecasting results of these models are compared with those of the international reference ionosphere model (IRI2016) and the measurements. The diurnal and seasonal variations of foF2 for the 4 models were compared and analyzed from 8 selected verification stations. The forecasting results reveal that the deep learning LSTM model presents the optimal performance of all models in forecasting the time series of foF2, while the IRI2016 model has the poorest forecasting performance, and the BPNN model and GABP model are between two of them.<\/jats:p>","DOI":"10.3390\/rs13193849","type":"journal-article","created":{"date-parts":[[2021,9,27]],"date-time":"2021-09-27T22:16:38Z","timestamp":1632780998000},"page":"3849","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":37,"title":["Forecasting Ionospheric foF2 Based on Deep Learning Method"],"prefix":"10.3390","volume":"13","author":[{"given":"Xiaojun","family":"Li","sequence":"first","affiliation":[{"name":"Department of Space Physics, School of Electronic Information, Wuhan University, Wuhan 430072, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2692-9451","authenticated-orcid":false,"given":"Chen","family":"Zhou","sequence":"additional","affiliation":[{"name":"Department of Space Physics, School of Electronic Information, Wuhan University, Wuhan 430072, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qiong","family":"Tang","sequence":"additional","affiliation":[{"name":"Institute of Space Science and Applied Technology, Harbin Institute of Technology, Shenzhen 518000, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jun","family":"Zhao","sequence":"additional","affiliation":[{"name":"Research Institute of Radiowave Propagation, Qingdao 266107, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8192-8924","authenticated-orcid":false,"given":"Fubin","family":"Zhang","sequence":"additional","affiliation":[{"name":"Department of Space Physics, School of Electronic Information, Wuhan University, Wuhan 430072, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guozhen","family":"Xia","sequence":"additional","affiliation":[{"name":"Department of Space Physics, School of Electronic Information, Wuhan University, Wuhan 430072, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yi","family":"Liu","sequence":"additional","affiliation":[{"name":"Department of Space Physics, School of Electronic Information, Wuhan University, Wuhan 430072, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2021,9,26]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Blaunstein, N., and Plohotniuc, E. (2008). Ionosphere and Applied Aspects of Radio Communication and Radar, CRC Press, Taylor & Francis Group.","DOI":"10.1201\/9781420055177"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"2241","DOI":"10.1016\/j.asr.2003.05.063","article-title":"Operational communication systems and relationships to the ionosphere and space weather","volume":"36","author":"Goodman","year":"2005","journal-title":"Adv. Space Res."},{"key":"ref_3","first-page":"23","article-title":"HF communication during ionospheric storms","volume":"67","author":"Hill","year":"1963","journal-title":"J. Res. NBS"},{"key":"ref_4","first-page":"1325","article-title":"TEC and foF2 variations: Preliminary results","volume":"47","author":"Kouris","year":"2004","journal-title":"Ann. Geophys."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"5264","DOI":"10.1109\/TAP.2013.2275153","article-title":"Estimation of hmF2 and foF2 Communication Parameters of Ionosphere F2-Layer Using GPS Data and IRI-Plas Model","volume":"61","author":"Sezen","year":"2013","journal-title":"IEEE Trans. Antennas Propag."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"1966","DOI":"10.1016\/j.asr.2004.06.010","article-title":"Towards the development of a new global foF2 empirical model using neural networks","volume":"34","author":"Oyeyemi","year":"2004","journal-title":"Adv. Space Res."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"418","DOI":"10.1002\/2016SW001593","article-title":"International Reference Ionosphere 2016: From ionospheric climate to real-time weather predictions","volume":"15","author":"Bilitza","year":"2017","journal-title":"Space Weather."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"1854","DOI":"10.1016\/j.jastp.2006.02.009","article-title":"Long-term trends in foF2: A comparison of various methods","volume":"68","author":"Mikhailov","year":"2006","journal-title":"J. Atmos. Sol.-Terr. Phys."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"459","DOI":"10.1029\/1998RS900020","article-title":"Autocorrelation method for temporal interpolation and short-term prediction of ionospheric data","volume":"34","author":"Muhtarov","year":"2016","journal-title":"Radio Sci."},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Sojka, J.J., Thompson, S.R., and Schunk, R.W. (2001). Assimilation ionospheric model: Development and testing with combined ionospheric campaign Caribbean measurements. J. Radio Sci., 247\u2013259.","DOI":"10.1029\/1999RS002411"},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Scherliess, L., Thompson, D.C., and Schunk, R.W. (2009). Ionospheric dynamics and drivers obtained from a physics-based data assimilation model. Radio Sci., 44.","DOI":"10.1029\/2008RS004068"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"1573","DOI":"10.1049\/el:19981113","article-title":"Ionospheric forecasting technique by artificial neural network","volume":"34","author":"Cander","year":"1998","journal-title":"Electron. Lett."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1029\/2004RS003223","article-title":"On the global model for foF2 using neural networks","volume":"40","author":"Oyeyemi","year":"2005","journal-title":"Radio Sci."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1029\/2004RS003239","article-title":"On the global short-term forecasting of the ionospheric critical frequency foF2 up to 5 h in advance using neural networks","volume":"40","author":"Oyeyemi","year":"2005","journal-title":"Radio Sci."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"1807","DOI":"10.1016\/j.jastp.2006.07.002","article-title":"Near-real time foF2 predictions using neural networks","volume":"68","author":"Oyeyemi","year":"2006","journal-title":"J. Atmos. Terr. Phys."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"225","DOI":"10.1029\/1999RS900105","article-title":"On the predictability of foF2 using neural networks","volume":"35","author":"Poole","year":"2016","journal-title":"Radio Sci."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"7","DOI":"10.1016\/j.jastp.2012.09.010","article-title":"Predicting foF2 in the China Region Using the Neural Networks Improved by the Genetic Algorithm","volume":"92","author":"Wang","year":"2013","journal-title":"J. Atmos. Sol. Terr. Phys."},{"key":"ref_18","first-page":"708","article-title":"The ionospheric foF2 prediction based on neural network optimization algorithm","volume":"33","author":"Hu","year":"2018","journal-title":"Chin. J. Radio Sci."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"153","DOI":"10.1007\/s10462-011-9208-z","article-title":"An optimizing BP neural network algorithm based on genetic algorithm","volume":"36","author":"Ding","year":"2011","journal-title":"Artif. Intell. Rev."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"4003","DOI":"10.1016\/j.asr.2019.02.038","article-title":"Ionospheric foF2 disturbance forecast using neural network improved by a genetic algorithm","volume":"63","author":"Zhao","year":"2019","journal-title":"Adv. Space Res."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"2536","DOI":"10.1002\/jgra.50262","article-title":"Preliminary investigation of real-time mapping of foF2 in northern China based on oblique ionosonde data","volume":"118","author":"Zhou","year":"2013","journal-title":"J. Geophys. Res. Space Phys."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"387","DOI":"10.1016\/j.asr.2013.12.001","article-title":"A prediction model of short-term ionospheric foF2 based on AdaBoost","volume":"53","author":"Zhao","year":"2013","journal-title":"Adv. Space Res."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"2111","DOI":"10.5194\/angeo-27-2111-2009","article-title":"A recurrent neural network approach to quantitatively studying solar wind effects on TEC derived from GPS; preliminary results","volume":"27","author":"Habarulema","year":"2009","journal-title":"Ann. Geophys."},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Lv, Z., Yu, C., and Liu, A. (2019, January 27\u201329,). Forecasting the Ionospheric f0F2 Parameter One Hour in Advance Using Recurrent Neural Network. Proceedings of the 2019 International Conference on Computer, Network, Communication and Information Systems (CNCI 2019), Qingdao, China.","DOI":"10.2991\/cnci-19.2019.37"},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Sun, W., Xu, L., Huang, X., Zhang, W., Yuan, T., Chen, Z., and Yan, Y. (2017, January 9\u201312). Forecasting of ionospheric vertical total electron content (TEC) using LSTM networks. Proceedings of the 2017 International Conference on Machine Learning and Cybernetics (ICMLC), Ningbo, China.","DOI":"10.1109\/ICMLC.2017.8108945"},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"1004","DOI":"10.1109\/LGRS.2020.2992633","article-title":"Implementation of hybrid deep learning model (LSTM-CNN) for ionospheric TEC forecasting using GPS data","volume":"18","author":"Ruwali","year":"2020","journal-title":"IEEE Geosci. Remote Sens. Lett."},{"key":"ref_27","unstructured":"Cherrier, N., Castaings, T., and Boulch, A. (2017). Forecasting ionospheric Total Electron Content maps with deep neural networks. Proceedings of the Big Data Space (BIDS), ESA Workshop."},{"key":"ref_28","first-page":"28","article-title":"Computer network traffic prediction: A comparison between traditional and deep learning neural networks","volume":"3","author":"Oliveira","year":"2016","journal-title":"Int. J. Big Data Intell."},{"key":"ref_29","unstructured":"Fausett, L.V. (1994). Fundamentals of Neural Networks: Architectures, Algorithms, and Applications, Prentice-Hall."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"425","DOI":"10.1162\/neco.1989.1.4.425","article-title":"Learning in artificial neural networks: A statistical perspective","volume":"1","author":"White","year":"1989","journal-title":"Neural Comput."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"865","DOI":"10.1109\/72.329683","article-title":"Network information criterion-determining the number of hidden units for an artificial neural network model","volume":"5","author":"Murata","year":"1994","journal-title":"IEEE Trans. Neural Netw."},{"key":"ref_32","first-page":"1245","article-title":"Modelling of foF2 using neural networks at an equatorial anomaly station","volume":"89","author":"Sarma","year":"2005","journal-title":"Curr. Sci."},{"key":"ref_33","first-page":"35","article-title":"Analysis of Local Minimization for BP Algorithm and Its Avoidance Methods","volume":"28","author":"Wang","year":"2002","journal-title":"Comput. Eng."},{"key":"ref_34","first-page":"267","article-title":"Ionospheric foF2 storm forecasting using neural networks","volume":"25","author":"Wintoft","year":"2000","journal-title":"Phys. Chem. Earth Part C Sol. Terr. Planet. Sci."},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"3659","DOI":"10.1029\/96GL03472","article-title":"Neural networks, foF2, sunspot number and magnetic activity","volume":"23","author":"Williscroft","year":"1996","journal-title":"Geophys. Res. Lett."},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"1497","DOI":"10.1029\/1999RS900070","article-title":"Temporal and spatial forecasting of ionospheric critical frequency using neural networks","volume":"34","author":"Kumluca","year":"1999","journal-title":"Radio Sci."},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"410","DOI":"10.2478\/s11600-007-0011-9","article-title":"Spatial correlation of foF2 and vTEC under quiet and disturbed ionospheric conditions: A case study","volume":"55","author":"Cander","year":"2007","journal-title":"Acta Geophys."},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"10125","DOI":"10.1029\/JA092iA09p10125","article-title":"Time-Weighted Accumulations ap(\u03c4) and Kp(\u03c4)","volume":"92","author":"Wrenn","year":"1987","journal-title":"J. Geophys. Res."},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"1717","DOI":"10.1029\/97RS01350","article-title":"Statistical studies of an effective sunspot number","volume":"32","author":"Secan","year":"1997","journal-title":"Radio Sci."},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"1171","DOI":"10.5194\/angeo-22-1171-2004","article-title":"The 22-year cycle in the geomagnetic 27-day recurrences reflecting on the F2-layer ionization","volume":"22","author":"Apostolov","year":"2004","journal-title":"Ann. Geophys."},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1029\/2008GL034433","article-title":"Short-period solar cycle signals in the ionosphere observed by FORMOSAT-3\/COSMIC","volume":"35","author":"Liang","year":"2008","journal-title":"Geophys. Res. Lett."},{"key":"ref_42","first-page":"1425","article-title":"Effects of declination and thermospheric wind on TEC longitude variations in the mid-latitude ionosphere","volume":"56","author":"Xu","year":"2013","journal-title":"Chin. J. Geophys."},{"key":"ref_43","doi-asserted-by":"crossref","unstructured":"Kaselimi, M., Voulodimos, A., Doulamis, N., Doulamis, A., and Delikaraoglou, D.A. (2020). Causal Long Short-Term Memory Sequence to Sequence Model for TEC Prediction Using GNSS Observations. Remote Sens., 12.","DOI":"10.3390\/rs12091354"},{"key":"ref_44","doi-asserted-by":"crossref","first-page":"1180","DOI":"10.1109\/LGRS.2019.2895112","article-title":"A deep learning-based approach to forecast ionospheric delays for GPS signals","volume":"16","author":"Srivani","year":"2019","journal-title":"IEEE Geosci. Remote Sens. Lett."},{"key":"ref_45","doi-asserted-by":"crossref","first-page":"1265","DOI":"10.3938\/jkps.77.1265","article-title":"Forecasting the ionospheric F2 Parameters over Jeju Station (33.43\u00b0 N, 126.30\u00b0 E) by Using Long Short-Term Memory","volume":"77","author":"Moon","year":"2020","journal-title":"J. Korean Phys. Soc."},{"key":"ref_46","doi-asserted-by":"crossref","first-page":"22","DOI":"10.1002\/cjg2.1006","article-title":"A technology study of foF2 forecasting during the ionospheric disturbance","volume":"50","author":"Chen","year":"2007","journal-title":"Chin. J. Geophys."},{"key":"ref_47","doi-asserted-by":"crossref","first-page":"599","DOI":"10.1016\/j.asr.2007.07.048","article-title":"International reference ionosphere 2007: Improvements and new parameters","volume":"42","author":"Bilitza","year":"2008","journal-title":"Adv. Space Res."},{"key":"ref_48","doi-asserted-by":"crossref","first-page":"61","DOI":"10.11648\/j.ajaa.20140206.11","article-title":"Geomagnetic disturbances and its impact on ionospheric critical frequency (foF2) at high, mid and low latitude region","volume":"2","author":"Atulkar","year":"2014","journal-title":"Am. J. Astron. Astrophys."}],"container-title":["Remote Sensing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2072-4292\/13\/19\/3849\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T07:05:15Z","timestamp":1760166315000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2072-4292\/13\/19\/3849"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,9,26]]},"references-count":48,"journal-issue":{"issue":"19","published-online":{"date-parts":[[2021,10]]}},"alternative-id":["rs13193849"],"URL":"https:\/\/doi.org\/10.3390\/rs13193849","relation":{},"ISSN":["2072-4292"],"issn-type":[{"value":"2072-4292","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,9,26]]}}}