{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,21]],"date-time":"2026-02-21T15:56:56Z","timestamp":1771689416801,"version":"3.50.1"},"reference-count":29,"publisher":"MDPI AG","issue":"18","license":[{"start":{"date-parts":[[2022,9,9]],"date-time":"2022-09-09T00:00:00Z","timestamp":1662681600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100002855","name":"Ministry of Science and Technology of Taiwan","doi-asserted-by":"publisher","award":["MOST 109-2923-M-008-001-MY2"],"award-info":[{"award-number":["MOST 109-2923-M-008-001-MY2"]}],"id":[{"id":"10.13039\/501100002855","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002855","name":"Ministry of Science and Technology of Taiwan","doi-asserted-by":"publisher","award":["MOST 110-2111-M-008-012"],"award-info":[{"award-number":["MOST 110-2111-M-008-012"]}],"id":[{"id":"10.13039\/501100002855","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002855","name":"Ministry of Science and Technology of Taiwan","doi-asserted-by":"publisher","award":["MOST 110-2111-M-008-013"],"award-info":[{"award-number":["MOST 110-2111-M-008-013"]}],"id":[{"id":"10.13039\/501100002855","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002855","name":"Ministry of Science and Technology of Taiwan","doi-asserted-by":"publisher","award":["MOST 111-2111-M-008-013"],"award-info":[{"award-number":["MOST 111-2111-M-008-013"]}],"id":[{"id":"10.13039\/501100002855","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Remote Sensing"],"abstract":"<jats:p>Modern space missions provide a great number of height profiles of ionospheric electron density, measured by the remote sensing technique of radio occultation (RO). The deducing of the profiles from the RO measurements suffers from bias, resulting in negative values of the electron density. We developed a machine learning technique that allows automatic identification of ionospheric layers and avoids the bias problem. An algorithm of convolutional neural networks was applied for the classification of the height profiles. Six classes of the profiles were distinguished on the base of prominent ionospheric layers F2, Es, E, F1 and F3, as well as distorted profiles (Sc). For the models, we selected the ground truth of more than 712 height profiles measured by the COSMIC\/Formosat-3 mission above Taiwan from 2011 to 2013. Two different models, a 1D convolutional neural network (CNN) and fully convolutional network (FCN), were applied for classification. It was found that both models demonstrate the best classification performance, with the average accuracy around 0.8 for prediction of the F2 layer-related class and the E layer-related class. The F1 layer is classified by the models with good performance (&gt;0.7). The CNN model can effectively classify the Es layer with an accuracy of 0.75. The FCN model has good classification performance (0.72) for the Sc-related profiles. The lowest performance (&lt;0.4) was found for the F3 layer-related class. It was shown that the more complex FCN model has better classification performance for both large-scale and small-scale variations in the height profiles of the ionospheric electron density.<\/jats:p>","DOI":"10.3390\/rs14184521","type":"journal-article","created":{"date-parts":[[2022,9,13]],"date-time":"2022-09-13T04:05:41Z","timestamp":1663041941000},"page":"4521","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":7,"title":["Deep Learning Application for Classification of Ionospheric Height Profiles Measured by Radio Occultation Technique"],"prefix":"10.3390","volume":"14","author":[{"given":"Mon-Chai","family":"Hsieh","sequence":"first","affiliation":[{"name":"Department of Space Science and Engineering, National Central University, Taoyuan City 320317, Taiwan"}]},{"given":"Guan-Han","family":"Huang","sequence":"additional","affiliation":[{"name":"Department of Space Science and Engineering, National Central University, Taoyuan City 320317, Taiwan"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8038-251X","authenticated-orcid":false,"given":"Alexei V.","family":"Dmitriev","sequence":"additional","affiliation":[{"name":"Department of Space Science and Engineering, National Central University, Taoyuan City 320317, Taiwan"},{"name":"Skobeltsyn Institute of Nuclear Physics, Lomonosov Moscow State University, 119899 Moscow, Russia"}]},{"given":"Chia-Hsien","family":"Lin","sequence":"additional","affiliation":[{"name":"Department of Space Science and Engineering, National Central University, Taoyuan City 320317, Taiwan"}]}],"member":"1968","published-online":{"date-parts":[[2022,9,9]]},"reference":[{"key":"ref_1","unstructured":"Kelley, M.C. (2009). The Earth\u2019s Ionosphere: Plasma Physics and Electrodynamics, International Geophysics Series, Elsevier Inc."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"35","DOI":"10.3319\/TAO.2007.12.26.01(F3C)","article-title":"GPS radio occultation: Results from CHAMP, GRACE and FORMOSAT-3\/COSMIC","volume":"20","author":"Wickert","year":"2009","journal-title":"Terr. Atmos. Ocean. Sci."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"1541","DOI":"10.5194\/amt-4-1541-2011","article-title":"Validation of refractivity profiles derived from GRAS raw-sampling data","volume":"4","author":"Zus","year":"2011","journal-title":"Atmos. Meas. Tech."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"272","DOI":"10.1016\/j.asr.2013.11.013","article-title":"Atmosphere sounding by GPS radio occultation: First results from TanDEM-X and comparison with TerraSAR-X","volume":"53","author":"Zus","year":"2014","journal-title":"Adv. Space Res."},{"key":"ref_5","first-page":"1049","article-title":"Radio occultation techniques for probing the ionosphere","volume":"47","author":"Jakowski","year":"2004","journal-title":"Ann. Geophys."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"174","DOI":"10.1002\/ima.1850050214","article-title":"Imaging the ionosphere with Global Positioning System","volume":"5","author":"Hajj","year":"1994","journal-title":"Int. J. Imaging Syst. Technol."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"2473","DOI":"10.1029\/2000GL000032","article-title":"Improving the Abel inversion by adding ground GPS data to LEO radio occultation in ionospheric sounding","volume":"27","author":"Juan","year":"2000","journal-title":"Geophys. Res. Lett."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"56","DOI":"10.1051\/swsc\/2021040","article-title":"Sensing the ionosphere with the Spire radio occultation constellation","volume":"11","author":"Angling","year":"2021","journal-title":"J. Space Weather Space Clim."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"RS1013","DOI":"10.1029\/2010RS004514","article-title":"Evaluation of the orbit altitude electron density estimation and its effect on the Abel inversion from radio occultation measurements","volume":"46","author":"Yue","year":"2011","journal-title":"Radio Sci."},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Li, J., and Jin, S. (2016, January 10\u201315). Second-order ionospheric effects on ionospheric electron density estimation from GPS Radio Occultation. Proceedings of the 2016 IEEE International Geoscience and Remote Sensing Symposium (IGARSS), Beijing, China.","DOI":"10.1109\/IGARSS.2016.7730027"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"3813","DOI":"10.1109\/TGRS.2007.903365","article-title":"FORMOSAT-3\/COSMIC GPS Radio Occultation Mission: Preliminary Results","volume":"45","author":"Liou","year":"2007","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"452","DOI":"10.1016\/j.asr.2016.12.026","article-title":"Comparative study of COSMIC\/FORMOSAT-3, Irkutsk incoherent scatter radar, Irkutsk Digisonde and IRI model electron density vertical profiles","volume":"60","author":"Ratovsky","year":"2017","journal-title":"Adv. Space Res."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1029\/2021RS007267","article-title":"Processing and validation of FORMOSAT-7\/COSMIC-2 GPS total electron content observations","volume":"56","author":"Pedatella","year":"2021","journal-title":"Radio Sci."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"942","DOI":"10.1016\/j.asr.2020.05.009","article-title":"Deep-learning for ionogram automatic scaling","volume":"66","author":"Xiao","year":"2020","journal-title":"Adv. Space Res."},{"key":"ref_15","first-page":"1","article-title":"The new ARTIST 5 for all digisondes","volume":"69","author":"Galkin","year":"2008","journal-title":"Ionosonde Netw. Advis. Group Bull."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"107398","DOI":"10.1016\/j.ymssp.2020.107398","article-title":"1D convolutional neural networks and applications: A survey","volume":"151","author":"Kiranyaz","year":"2021","journal-title":"Mech. Syst. Signal Process."},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Long, J., Shelhamer, E., and Darrell, T. (2014). Fully convolutional networks for semantic segmentation. arXiv.","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"L04808","DOI":"10.1029\/2006GL027557","article-title":"Estimates of the precision of GPS radio occultation from the COSMIC\/FORMOSAT-3 mission","volume":"34","author":"Schreiner","year":"2007","journal-title":"Geophys. Res. Lett."},{"key":"ref_19","unstructured":"Abadi, M., Agarwal, A., Barham, P., Brevdo, E., Chen, Z., Citro, C., Corrado, G., Davis, A., Dean, J., and Devin, M. (2022, September 05). TensorFlow: Large-Scale MACHINE learning on Heterogeneous Systems. Available online: https:\/\/www.tensorflow.org\/."},{"key":"ref_20","unstructured":"Ioffe, S., and Szegedy, C. (2015). Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift. arXiv."},{"key":"ref_21","first-page":"1929","article-title":"Dropout: A Simple Way to Prevent Neural Networks from Overfitting","volume":"15","author":"Srivastava","year":"2014","journal-title":"J. Mach. Learn. Res."},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Frazier, P.I. (2018). A Tutorial on Bayesian Optimization. arXiv.","DOI":"10.1287\/educ.2018.0188"},{"key":"ref_23","unstructured":"Kingma, D.P., and Ba, J. (2014). Adam: A method for stochastic optimization. arXiv."},{"key":"ref_24","first-page":"135","article-title":"Solar flare prediction using SDO\/HMI vector magnetic field data with a machine-learning algorithm","volume":"798","author":"Bobra","year":"2015","journal-title":"Am. Astron. Soc."},{"key":"ref_25","unstructured":"Sabour, S., Frosst, N., and Hinton, G.E. (2017). Dynamic routing between capsules. Adv. Neural Inf. Process. Syst., 30."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"59","DOI":"10.1051\/swsc\/2021043","article-title":"Solar energetic particle event occurrence prediction using solar flare soft X-ray measurements and machine learning","volume":"11","author":"Raptis","year":"2021","journal-title":"J. Space Weather Space Clim."},{"key":"ref_27","first-page":"1089","article-title":"No unbiased estimator of the variance of K-fold cross-validation","volume":"5","author":"Bengio","year":"2004","journal-title":"J. Mach. Learn. Res."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"24","DOI":"10.3389\/fspas.2020.00024","article-title":"Classification of magnetosheath jets using neural networks and high resolution OMNI (HRO) data","volume":"7","author":"Raptis","year":"2020","journal-title":"Front. Astron. Space Sci."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"19","DOI":"10.1007\/s10291-020-01055-1","article-title":"GIMLi: Global Ionospheric total electron content model based on machine learning","volume":"25","author":"Zhukov","year":"2021","journal-title":"GPS Solut."}],"container-title":["Remote Sensing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2072-4292\/14\/18\/4521\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T00:28:49Z","timestamp":1760142529000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2072-4292\/14\/18\/4521"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,9,9]]},"references-count":29,"journal-issue":{"issue":"18","published-online":{"date-parts":[[2022,9]]}},"alternative-id":["rs14184521"],"URL":"https:\/\/doi.org\/10.3390\/rs14184521","relation":{},"ISSN":["2072-4292"],"issn-type":[{"value":"2072-4292","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,9,9]]}}}