{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,2]],"date-time":"2026-05-02T13:05:48Z","timestamp":1777727148943,"version":"3.51.4"},"reference-count":51,"publisher":"MDPI AG","issue":"1","license":[{"start":{"date-parts":[[2025,3,16]],"date-time":"2025-03-16T00:00:00Z","timestamp":1742083200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Machine Learning and Knowledge Extraction Journal [MAKE]","award":["Invitation with a 100% discount sent via email on September 4, 2024"],"award-info":[{"award-number":["Invitation with a 100% discount sent via email on September 4, 2024"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["MAKE"],"abstract":"<jats:p>Equatorial plasma bubbles (EPBs) are regions of depleted electron density that form in the Earth\u2019s ionosphere due to Rayleigh\u2013Taylor instability. These bubbles can cause signal scintillation, leading to signal loss and errors in position calculations. EPBs can be detected in images captured by All-Sky Imager (ASI) systems. This study proposes a low-cost automatic detection method for EPBs in ASI data that can be used for both real-time detection and classification purposes. This method utilizes Two-Dimensional Principal Component Analysis (2DPCA) with Recursive Feature Elimination (RFE), in conjunction with a Random Forest machine learning model, to create an Explainable Artificial Intelligence (XAI) model capable of extracting image features to automatically detect EPBs with the lowest possible dimensionality. This led to having a small-sized and extremely fast-trained model that could be used to identify EPBs within the captured ASI images. A set of 2458 images, classified into two categories\u2014Event and Empty\u2014were used to build the database. This database was randomly split into two subsets: a training dataset (80%) and a testing dataset (20%). The produced XAI model demonstrated slightly higher detection accuracy compared to the standard 2DPCA model while being significantly smaller in size. Furthermore, the proposed model\u2019s performance has been evaluated and compared with other deep learning baseline models (ResNet18, Inception-V3, VGG16, and VGG19) in the same environment.<\/jats:p>","DOI":"10.3390\/make7010026","type":"journal-article","created":{"date-parts":[[2025,3,17]],"date-time":"2025-03-17T06:36:23Z","timestamp":1742193383000},"page":"26","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Automatic Detection of Equatorial Plasma Bubbles in Airglow Images Using Two-Dimensional Principal Component Analysis and Explainable Artificial Intelligence"],"prefix":"10.3390","volume":"7","author":[{"given":"Moheb","family":"Yacoub","sequence":"first","affiliation":[{"name":"Department of Space Environment, Institute of Basic and Applied Sciences, Egypt-Japan University of Science and Technology (E-JUST), New Borg El-Arab City 21934, Alexandria, Egypt"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Moataz","family":"Abdelwahab","sequence":"additional","affiliation":[{"name":"Department of Electronics and Communication Engineering, Egypt-Japan University of Science and Technology (E-JUST), P.O. Box 179, New Borg El-Arab City 21934, Alexandria, Egypt"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kazuo","family":"Shiokawa","sequence":"additional","affiliation":[{"name":"Institute for Space-Earth Environmental Research (ISEE), Nagoya University, Nagoya 464-8601, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6853-8630","authenticated-orcid":false,"given":"Ayman","family":"Mahrous","sequence":"additional","affiliation":[{"name":"Department of Space Environment, Institute of Basic and Applied Sciences, Egypt-Japan University of Science and Technology (E-JUST), New Borg El-Arab City 21934, Alexandria, Egypt"},{"name":"Department of Physics, Faculty of Science, Helwan University, Helwan, Cairo 11795, Egypt"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2025,3,16]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"2309","DOI":"10.1029\/97RS01802","article-title":"Imaging coherent backscatter radar observations of topside equatorial spread F","volume":"32","author":"Hysell","year":"1997","journal-title":"Radio Sci."},{"key":"ref_2","unstructured":"Kelley, M.C. (1989). The Earth\u2019s Ionosphere, Academic Press."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"26795","DOI":"10.1029\/96JA00760","article-title":"Scintillations, plasma drift, and neutral winds in the equatorial ionosphere after sunset","volume":"101","author":"Basu","year":"1996","journal-title":"J. Geophys. Res."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"731","DOI":"10.1029\/1999RS002310","article-title":"Fading timescales associated with GPS signals and potential consequences","volume":"36","author":"Kintner","year":"2001","journal-title":"Radio Sci."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"1436","DOI":"10.1029\/2002GL016503","article-title":"GPS occultation sensor observations of ionospheric scintillation","volume":"30","author":"Straus","year":"2003","journal-title":"Geophys. Res. Lett."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"1333","DOI":"10.5047\/eps.2013.08.005","article-title":"The ionospheric bubble index deduced from magnetic field and plasma observations onboard swarm","volume":"65","author":"Park","year":"2013","journal-title":"Earth Planets Space"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"10503","DOI":"10.1029\/JA087iA12p10503","article-title":"Coordinated airborne and satellite measurements of equatorial plasma depletions","volume":"87","author":"Weber","year":"1982","journal-title":"J. Geophys. Res."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"2057","DOI":"10.1029\/95JA01398","article-title":"Images of transequatorial F region bubbles in 630- and 777-nm emissions compared with satellite measurements","volume":"102","author":"Tinsley","year":"1997","journal-title":"J. Geophys. Res."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"29153","DOI":"10.1029\/2001JA900109","article-title":"ROCSAT-1 ionospheric plasma and electrodynamics instrument observations of equatorial spread F: An early transitional scale result","volume":"106","author":"Su","year":"2001","journal-title":"J. Geophys. Res."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"2003","DOI":"10.1029\/2002GL015509","article-title":"Observations of equatorial spread-F from Haleakala, Hawaii","volume":"29","author":"Kelley","year":"2002","journal-title":"Geophys. Res. Lett."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1029\/2007JA012661","article-title":"Optical observations of the growth and day-to-day variability of equatorial plasma bubbles","volume":"113","author":"Makela","year":"2008","journal-title":"J. Geophys. Res. Space Phys."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"7791","DOI":"10.1029\/92JA01839","article-title":"Determination of the quenching rate of the O(1D) by O(3P) from rocket-borne optical (630 nm) and electron density data","volume":"98","author":"Sobral","year":"1993","journal-title":"J. Geophys. Res."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"1219","DOI":"10.1016\/S0273-1177(01)00201-0","article-title":"Ionospheric plasma bubble zonal drift: A methodology using OI 630 nm all-sky imaging systems","volume":"27","author":"Pimenta","year":"2001","journal-title":"Adv. Space Res."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"712","DOI":"10.1029\/JA083iA02p00712","article-title":"North-south aligned equatorial depletions","volume":"83","author":"Weber","year":"1978","journal-title":"J. Geophys. Res."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"7641","DOI":"10.1029\/JA087iA09p07641","article-title":"Airglow characteristics of equatorial plasma depletions","volume":"87","author":"Mendillo","year":"1982","journal-title":"J. Geophys. Res."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"1699","DOI":"10.1029\/97GL01207","article-title":"High-resolution OI (630 nm) image measurements of F-region depletion drifts during the Guara campaign","volume":"24","author":"Taylor","year":"1997","journal-title":"Geophys. Res. Lett."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"1053","DOI":"10.1007\/s00585-999-1053-x","article-title":"Observations of day-to-day variability in precursor signatures to equatorial F-region plasma depletions","volume":"17","author":"Fagundes","year":"1999","journal-title":"Ann. Geophys."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"3109","DOI":"10.5194\/angeo-22-3109-2004","article-title":"Analysis of the seasonal variations of equatorial plasma bubble occurrence observed from Haleakala. Hawaii","volume":"22","author":"Makela","year":"2004","journal-title":"Ann. Geophys."},{"key":"ref_19","first-page":"A09303","article-title":"Observations and modeling of the coupled latitude-altitude patterns of equatorial plasma depletions","volume":"110","author":"Mendillo","year":"2005","journal-title":"J. Geophys. Res."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"A07307","DOI":"10.1029\/2006JA012055","article-title":"Observations of plasma depletions in 557.7-nm images over Kavalur","volume":"112","author":"Rajesh","year":"2007","journal-title":"J. Geophys. Res. Space Phys."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"749","DOI":"10.5194\/angeo-29-749-2011","article-title":"Airglow observations over the equatorial ionization anomaly zone in Taiwan","volume":"29","author":"Liu","year":"2011","journal-title":"Ann. Geophys."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"43","DOI":"10.1186\/s40623-015-0202-6","article-title":"Airglow-imaging observation of plasma bubble disappearance at geomagnetically conjugate points","volume":"67","author":"Shiokawa","year":"2015","journal-title":"Earth Planet Space"},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"2222","DOI":"10.1002\/2014JA020398","article-title":"Geomagnetically conjugate observation of plasma bubbles and thermospheric neutral winds at low latitudes","volume":"120","author":"Fukushima","year":"2015","journal-title":"J. Geophys. Res. Space Phys."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"12430","DOI":"10.1002\/2017JA024602","article-title":"First study on the occurrence frequency of equatorial plasma bubbles over West Africa using an all-sky airglow imager and GNSS receivers","volume":"122","author":"Okoh","year":"2017","journal-title":"J. Geophys. Res. Space Phys."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"e2020JA028308","DOI":"10.1029\/2020JA028308","article-title":"Observation of an intriguing equatorial plasma bubble event over Indian sector","volume":"126","author":"Ghodpage","year":"2021","journal-title":"J. Geophys. Res. Space Phys."},{"key":"ref_26","first-page":"397","article-title":"Interaction between equatorial plasma bubbles and a medium-scale traveling ionospheric disturbance, observed by OI 630 nm airglow imaging at Bom Jesus de Lapa, Brazil","volume":"5","author":"Wrasse","year":"2021","journal-title":"Earth Planet. Phys."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"663","DOI":"10.1016\/j.asr.2023.09.013","article-title":"Airglow observed by a full-band imager together with multi-instruments in Taiwan during nighttime of 1 November 2021","volume":"73","author":"Liu","year":"2024","journal-title":"Adv. Space Res."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"163","DOI":"10.5194\/angeo-24-163-2006","article-title":"A global climatology for equatorial plasma bubbles in the topside ionosphere","volume":"24","author":"Gentile","year":"2006","journal-title":"Ann. Geophys."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"628","DOI":"10.1002\/2015JA021900","article-title":"Effects of solar and geomagnetic activities on the zonal drift of equatorial plasma bubbles","volume":"121","author":"Huang","year":"2016","journal-title":"J. Geophys. Res. Space Phys."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"3014","DOI":"10.1002\/2017JA025072","article-title":"Climatology of the occurrence rate and amplitudes of local time distinguished equatorial plasma depletions observed by Swarm satellite","volume":"123","author":"Wan","year":"2018","journal-title":"J. Geophys. Res. Space Phys."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"e2023EA002935","DOI":"10.1029\/2023EA002935","article-title":"Automated detection and tracking of equatorial plasma bubbles utilizing Global-Scale Observations of the Limb and Disk (GOLD) 135.6 nm Data","volume":"10","author":"Adkins","year":"2023","journal-title":"Earth Space Sci."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"5990","DOI":"10.1016\/j.asr.2024.03.014","article-title":"Optimizing a deep learning framework for accurate detection of the Earth\u2019s ionospheric plasma structures from all-sky airglow images","volume":"73","author":"Chakrabarti","year":"2024","journal-title":"Adv. Space Res."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"131","DOI":"10.1109\/TPAMI.2004.1261097","article-title":"Two-dimensional PCA: A new approach to appearance-based face representation and recognition","volume":"26","author":"Yang","year":"2004","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"247","DOI":"10.1007\/s40328-013-0024-6","article-title":"Ionospheric anomaly related to M=6.6, 26 August 2012, Tobelo earthquake near Indonesia: Two-dimensional principal component analysis","volume":"48","author":"Lin","year":"2013","journal-title":"Acta Geod. Geophys."},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"1245","DOI":"10.1007\/s11069-021-05093-x","article-title":"Generalized two-dimensional principal component analysis and two artificial neural network models to detect traveling ionospheric disturbances","volume":"111","author":"Lin","year":"2022","journal-title":"Nat. Hazards"},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"53650","DOI":"10.1109\/ACCESS.2019.2912564","article-title":"Detecting all possible ionospheric precursors by kernel-based two-dimensional principal component analysis","volume":"7","author":"Lin","year":"2019","journal-title":"IEEE Access"},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"8789","DOI":"10.1109\/TIE.2020.3013492","article-title":"Two-dimensional principal component analysis-based convolutional autoencoder for wafer map defect detection","volume":"68","author":"Yu","year":"2021","journal-title":"IEEE Trans. Ind. Electron."},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"21","DOI":"10.1007\/s00138-023-01371-9","article-title":"Randomized nonlinear two-dimensional principal component analysis network for object recognition","volume":"34","author":"Sun","year":"2023","journal-title":"Mach. Vis. Appl."},{"key":"ref_39","doi-asserted-by":"crossref","unstructured":"Wang, L., You, Z.H., and Yan, X. (2018). Using two-dimensional principal component analysis and rotation forest for prediction of protein-protein interactions. Sci. Rep., 8.","DOI":"10.1038\/s41598-018-30694-1"},{"key":"ref_40","doi-asserted-by":"crossref","unstructured":"Abdelwahab, M.M., and Abdelrahman, S.A. (2017, January 6\u20139). Four layers image representation for prediction of lung cancer genetic mutations based on 2DPCA. Proceedings of the 2017 IEEE 60th International Midwest Symposium on Circuits and Systems (MWSCAS), Boston, MA, USA.","DOI":"10.1109\/MWSCAS.2017.8052994"},{"key":"ref_41","unstructured":"Lundberg, S.M., and Lee, S.-I. (2017). A Unified Approach to Interpreting Model Predictions. Adv. Neural Inf. Process. Syst. (NeurIPS), 30."},{"key":"ref_42","doi-asserted-by":"crossref","unstructured":"Ribeiro, M.T., Singh, S., and Guestrin, C. (2016, January 13\u201317). \u201cWhy should I trust you?\u201d Explaining the predictions of any classifier. Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, San Francisco, CA, USA.","DOI":"10.1145\/2939672.2939778"},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"101243","DOI":"10.1016\/j.cogsys.2024.101243","article-title":"Post-hoc vs ante-hoc explanations: xAI design guidelines for data scientists","volume":"86","author":"Retzlaff","year":"2024","journal-title":"Cogn. Syst. Res."},{"key":"ref_44","unstructured":"Gonzalez, R.C., and Wintz, P. (1997). Digital Image Processing. Addison-Wesley. [3rd ed.]."},{"key":"ref_45","unstructured":"Carsten, H. (2007). The Radon Transform, Aalborg University. VGIS, 07gr721."},{"key":"ref_46","doi-asserted-by":"crossref","first-page":"1997","DOI":"10.1016\/S0031-3203(02)00040-7","article-title":"From image vector to matrix: A straightforward image projection technique\u2014IMPCA vs","volume":"35","author":"Yang","year":"2002","journal-title":"PCA. Pattern Recognit."},{"key":"ref_47","first-page":"7314599","article-title":"A Cross-Modal Image and Text Retrieval Method Based on Efficient Feature Extraction and Interactive Learning CAE","volume":"1","author":"Yin","year":"2022","journal-title":"Sci. Program."},{"key":"ref_48","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1023\/A:1010933404324","article-title":"Random Forests","volume":"45","author":"Breiman","year":"2001","journal-title":"Mach. Learn."},{"key":"ref_49","doi-asserted-by":"crossref","first-page":"389","DOI":"10.1023\/A:1012487302797","article-title":"Gene selection for cancer classification using support vector machines","volume":"46","author":"Guyon","year":"2002","journal-title":"Mach. Learn."},{"key":"ref_50","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., and Wojna, Z. (2016, January 27\u201330). Rethinking the inception architecture for computer vision. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA.","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref_51","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., and Sun, J. (2016, January 27\u201330). Deep residual learning for image recognition. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA.","DOI":"10.1109\/CVPR.2016.90"}],"container-title":["Machine Learning and Knowledge Extraction"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2504-4990\/7\/1\/26\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T16:54:40Z","timestamp":1760028880000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2504-4990\/7\/1\/26"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,3,16]]},"references-count":51,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2025,3]]}},"alternative-id":["make7010026"],"URL":"https:\/\/doi.org\/10.3390\/make7010026","relation":{},"ISSN":["2504-4990"],"issn-type":[{"value":"2504-4990","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,3,16]]}}}