{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,9]],"date-time":"2026-03-09T13:58:13Z","timestamp":1773064693816,"version":"3.50.1"},"reference-count":52,"publisher":"MDPI AG","issue":"3","license":[{"start":{"date-parts":[[2021,1,28]],"date-time":"2021-01-28T00:00:00Z","timestamp":1611792000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100000104","name":"National Aeronautics and Space Administration","doi-asserted-by":"publisher","award":["80NSSC20K0130"],"award-info":[{"award-number":["80NSSC20K0130"]}],"id":[{"id":"10.13039\/100000104","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["OAC\u20131730250"],"award-info":[{"award-number":["OAC\u20131730250"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["CNS\u20130821258, CNS\u20131228778, OAC\u20131726023"],"award-info":[{"award-number":["CNS\u20130821258, CNS\u20131228778, OAC\u20131726023"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Remote Sensing"],"abstract":"<jats:p>Identifying dust aerosols from passive satellite images is of great interest for many applications. In this study, we developed five different machine-learning (ML) based algorithms, including Logistic Regression, K Nearest Neighbor, Random Forest (RF), Feed Forward Neural Network (FFNN), and Convolutional Neural Network (CNN), to identify dust aerosols in the daytime satellite images from the Visible Infrared Imaging Radiometer Suite (VIIRS) under cloud-free conditions on a global scale. In order to train the ML algorithms, we collocated the state-of-the-art dust detection product from the Cloud-Aerosol Lidar with Orthogonal Polarization (CALIOP) with the VIIRS observations along the CALIOP track. The 16 VIIRS M-band observations with the center wavelength ranging from deep blue to thermal infrared, together with solar-viewing geometries and pixel time and locations, are used as the predictor variables. Four different sets of training input data are constructed based on different combinations of VIIRS pixel and predictor variables. The validation and comparison results based on the collocated CALIOP data indicate that the FFNN method based on all available predictor variables is the best performing one among all methods. It has an averaged dust detection accuracy of about 81%, 89%, and 85% over land, ocean and whole globe, respectively, compared with collocated CALIOP. When applied to off-track VIIRS pixels, the FFNN method retrieves geographical distributions of dust that are in good agreement with on-track results as well as CALIOP statistics. For further evaluation, we compared our results based on the ML algorithms to NOAA\u2019s Aerosol Detection Product (ADP), which is a product that classifies dust, smoke, and ash using physical-based methods. The comparison reveals both similarity and differences. Overall, this study demonstrates the great potential of ML methods for dust detection and proves that these methods can be trained on the CALIOP track and then applied to the whole granule of VIIRS granule.<\/jats:p>","DOI":"10.3390\/rs13030456","type":"journal-article","created":{"date-parts":[[2021,1,28]],"date-time":"2021-01-28T09:03:45Z","timestamp":1611824625000},"page":"456","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":41,"title":["Machine Learning Based Algorithms for Global Dust Aerosol Detection from Satellite Images: Inter-Comparisons and Evaluation"],"prefix":"10.3390","volume":"13","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8942-1092","authenticated-orcid":false,"given":"Jangho","family":"Lee","sequence":"first","affiliation":[{"name":"Department of Atmospheric Sciences, Texas A&amp;M University, College Station, TX 77840, USA"}]},{"given":"Yingxi Rona","family":"Shi","sequence":"additional","affiliation":[{"name":"Joint Center for Earth Systems Technology, University of Maryland, Baltimore County, Baltimore, MD 21250, USA"},{"name":"Climate and Radiation Laboratory (613), NASA Goddard Space Flight Center, Greenbelt, MD 20771, USA"}]},{"given":"Changjie","family":"Cai","sequence":"additional","affiliation":[{"name":"Department of Occupational and Environmental Health, University of Oklahoma, Oklahoma City, OK 73019, USA"}]},{"given":"Pubu","family":"Ciren","sequence":"additional","affiliation":[{"name":"I M Systems Group Inc., Rockville, MD 20852, USA"},{"name":"Center for Satellite Applications and Research, National Oceanic and Atmospheric Administration, College Park, MD 20740, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9933-1170","authenticated-orcid":false,"given":"Jianwu","family":"Wang","sequence":"additional","affiliation":[{"name":"Joint Center for Earth Systems Technology, University of Maryland, Baltimore County, Baltimore, MD 21250, USA"},{"name":"Department of Information Systems, University of Maryland, Baltimore County, Baltimore, MD 21250, USA"}]},{"given":"Aryya","family":"Gangopadhyay","sequence":"additional","affiliation":[{"name":"Department of Information Systems, University of Maryland, Baltimore County, Baltimore, MD 21250, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9491-1654","authenticated-orcid":false,"given":"Zhibo","family":"Zhang","sequence":"additional","affiliation":[{"name":"Joint Center for Earth Systems Technology, University of Maryland, Baltimore County, Baltimore, MD 21250, USA"},{"name":"Department of Physics, University of Maryland, Baltimore County, Baltimore, MD 21250, USA"}]}],"member":"1968","published-online":{"date-parts":[[2021,1,28]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"281","DOI":"10.1038\/ngeo474","article-title":"Influence of Patagonian glaciers on Antarctic dust deposition during the last glacial period","volume":"2","author":"Sugden","year":"2009","journal-title":"Nat. Geosci."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"557","DOI":"10.1038\/ngeo583","article-title":"Asian dust transported one full circuit around the globe","volume":"2","author":"Uno","year":"2009","journal-title":"Nat. Geosci."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"3396","DOI":"10.1073\/pnas.96.7.3396","article-title":"Long-range transport of mineral dust in the global atmosphere: Impact of African dust on the environment of the southeastern United States","volume":"96","author":"Prospero","year":"1999","journal-title":"Proc. Natl. Acad. Sci. USA"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"284","DOI":"10.1007\/s10393-004-0120-8","article-title":"Dust storms and their impact on ocean and human health: Dust in Earth\u2019s atmosphere","volume":"1","author":"Griffin","year":"2004","journal-title":"EcoHealth"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"347","DOI":"10.1016\/j.scitotenv.2012.06.082","article-title":"Dust storms and the risk of asthma admissions to hospitals in Kuwait","volume":"433","author":"Thalib","year":"2012","journal-title":"Sci. Total Environ."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"10715","DOI":"10.5194\/acp-18-10715-2018","article-title":"Ice cloud microphysical trends observed by the Atmospheric Infrared Sounder","volume":"18","author":"Kahn","year":"2018","journal-title":"Atmos. Chem. Phys."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"17099","DOI":"10.1029\/98JD00900","article-title":"Derivation of aerosol properties from satellite measurements of backscattered ultraviolet radiation: Theoretical basis","volume":"103","author":"Torres","year":"1998","journal-title":"J. Geophys. Res. Atmos."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"109","DOI":"10.1016\/j.atmosres.2003.11.001","article-title":"Vertical distribution of Saharan dust based on 2.5-year model predictions","volume":"70","author":"Alpert","year":"2004","journal-title":"Atmos. Res."},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Moorthy, K.K., Babu, S.S., Satheesh, S.K., Srinivasan, J., and Dutt, C.B.S. (2007). Dust absorption over the \u201cGreat Indian Desert\u201d inferred using ground-based and satellite remote sensing. J. Geophys. Res. Atmos., 112.","DOI":"10.1029\/2006JD007690"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"3903","DOI":"10.1080\/01431160600646359","article-title":"Development of a new over-water Advanced Very High Resolution Radiometer dust detection algorithm","volume":"27","author":"Evan","year":"2006","journal-title":"Int. J. Remote Sens."},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Zhu, A., Ramanathan, V., Li, F., and Kim, D. (2007). Dust plumes over the Pacific, Indian, and Atlantic oceans: Climatology and radiative impact. J. Geophys. Res. Atmos., 112.","DOI":"10.1029\/2007JD008427"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"229","DOI":"10.1016\/0169-555X(95)00105-E","article-title":"Calibration of GOES-VISSR, visible-band satellite data and its application to the analysis of a dust storm at Owens Lake, California","volume":"17","author":"MacKinnon","year":"1996","journal-title":"Geomorphology"},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Torres, O., Tanskanen, A., Veihelmann, B., Ahn, C., Braak, R., Bhartia, P.K., Veefkind, P., and Levelt, P. (2007). Aerosols and surface UV products from Ozone Monitoring Instrument observations: An overview. J. Geophys. Res. Atmos., 112.","DOI":"10.1029\/2007JD008809"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"949","DOI":"10.5194\/amt-6-949-2013","article-title":"Critical evaluation of the MODIS Deep Blue aerosol optical depth product for data assimilation over North Africa","volume":"6","author":"Shi","year":"2013","journal-title":"Atmos. Meas. Tech."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"1073","DOI":"10.4209\/aaqr.2011.11.0206","article-title":"Asian dust detection from the satellite observations of moderate resolution imaging spectroradiometer (MODIS)","volume":"12","author":"Zhao","year":"2012","journal-title":"Aerosol Air Qual. Res."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"1127","DOI":"10.1007\/s12040-015-0585-6","article-title":"Dust storm detection using random forests and physical-based approaches over the Middle East","volume":"124","author":"Souri","year":"2015","journal-title":"J. Earth Syst. Sci."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"896","DOI":"10.1175\/JTECH-D-12-00079.1","article-title":"Detection of optically thin mineral dust aerosol layers over the ocean using MODIS","volume":"30","author":"Cho","year":"2013","journal-title":"J. Atmos. Ocean. Technol."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"525","DOI":"10.1109\/36.823947","article-title":"Detection of dust over deserts using satellite data in the solar wavelengths","volume":"38","author":"Kaufman","year":"2000","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"256","DOI":"10.1175\/1520-0442(1988)001<0256:SDOSDO>2.0.CO;2","article-title":"Satellite detection of Saharan dust: Optimized imaging during nighttime","volume":"1","author":"Legrand","year":"1988","journal-title":"J. Clim."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"2347","DOI":"10.3390\/rs2102347","article-title":"Dust and smoke detection for multi-channel imagers","volume":"2","author":"Zhao","year":"2010","journal-title":"Remote Sens."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"1211","DOI":"10.1175\/2010BAMS3009.1","article-title":"The CALIPSO mission: A global 3D view of aerosols and clouds","volume":"91.9","author":"Winker","year":"2010","journal-title":"Bull. Am. Meteorol. Soc."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"2310","DOI":"10.1175\/2009JTECHA1281.1","article-title":"Overview of the CALIPSO Mission and CALIOP Data Processing Algorithms","volume":"26","author":"Winker","year":"2009","journal-title":"J. Atmos. Ocean. Technol."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"1953","DOI":"10.5194\/acp-10-1953-2010","article-title":"Saharan dust infrared optical depth and altitude retrieved from AIRS: A focus over North Atlantic\u2013comparison to MODIS and CALIPSO","volume":"10","author":"Peyridieu","year":"2010","journal-title":"Atmos. Chem. Phys."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"4770","DOI":"10.1002\/2013JD020855","article-title":"Dust aerosol index (DAI) algorithm for MODIS","volume":"119","author":"Ciren","year":"2014","journal-title":"J. Geophys. Res. Atmos."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"e2020EA001221","DOI":"10.1029\/2020EA001221","article-title":"Dust Aerosol Retrieval over the Oceans with the MODIS\/VIIRS Dark Target algorithm. Part I: Dust Detection","volume":"7","author":"Zhou","year":"2020","journal-title":"Earth Space Sci."},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Shi, P., Song, Q., Patwardhan, J., Zhang, Z., Wang, J., and Gangopadhyay, A. (2019, January 24\u201327). A hybrid algorithm for mineral dust detection using satellite data. Proceedings of the 15th International Conference on eScience (eScience), San Diego, CA, USA.","DOI":"10.1109\/eScience.2019.00012"},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"101059","DOI":"10.1016\/j.ecoinf.2020.101059","article-title":"Application of remote sensing techniques and machine learning algorithms in dust source detection and dust source susceptibility mapping","volume":"56","author":"Boroughani","year":"2020","journal-title":"Ecol. Inform."},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Hou, P., Guo, P., Wu, P., Wang, J., Gangopadhyay, A., and Zhang, Z. (2020, January 14\u201317). A Deep Learning Model for Detecting Dust in Earth\u2019s Atmosphere from Satellite Remote Sensing Data. Proceedings of the 2020 IEEE International Conference on Smart Computing (SMARTCOMP), Bologna, Italy.","DOI":"10.1109\/SMARTCOMP50058.2020.00045"},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"1263","DOI":"10.1016\/j.asr.2019.11.027","article-title":"Developing a dust storm detection method combining Support Vector Machine and satellite data in typical dust regions of Asia","volume":"65","author":"Shi","year":"2020","journal-title":"Adv. Space Res."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"7648","DOI":"10.1080\/01431161.2013.822660","article-title":"Statistical and neural pattern recognition methods for dust aerosol detection","volume":"34","author":"Rosiles","year":"2013","journal-title":"Int. J. Remote Sens."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"8304","DOI":"10.1002\/2013JD021355","article-title":"View angle dependence of MODIS liquid water path retrievals in warm oceanic clouds","volume":"119","author":"Seethala","year":"2014","journal-title":"J. Geophys. Res. Atmos."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"1519","DOI":"10.1175\/2010JTECHA1432.1","article-title":"Viewing geometry dependencies in MODIS cloud products","volume":"27","author":"Maddux","year":"2010","journal-title":"J. Atmos. Ocean. Technol."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"4132","DOI":"10.1002\/2015JD023161","article-title":"Frequency and causes of failed MODIS cloud property retrievals for liquid phase clouds over global oceans","volume":"120","author":"Cho","year":"2015","journal-title":"J. Geophys. Res. Atmos."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"2257","DOI":"10.5194\/amt-13-2257-2020","article-title":"A machine-learning-based cloud detection and thermodynamic-phase classification algorithm using passive spectral observations","volume":"13","author":"Wang","year":"2020","journal-title":"Atmos. Meas. Tech."},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"1198","DOI":"10.1175\/2009JTECHA1229.1","article-title":"The CALIPSOLidar Cloud and Aerosol Discrimination: Version 2 Algorithm and Initial Assessment of Performance","volume":"26","author":"Liu","year":"2009","journal-title":"J. Atmos. Ocean. Technol."},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"703","DOI":"10.5194\/amt-12-703-2019","article-title":"Discriminating between clouds and aerosols in the CALIOP version 4.1 data products","volume":"12","author":"Liu","year":"2019","journal-title":"Atmos. Meas. Tech."},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"6107","DOI":"10.5194\/amt-11-6107-2018","article-title":"The CALIPSO version 4 automated aerosol classification and lidar ratio selection algorithm","volume":"11","author":"Kim","year":"2018","journal-title":"Atmos. Meas. Tech."},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"2034","DOI":"10.1175\/2009JTECHA1228.1","article-title":"Fully Automated Detection of Cloud and Aerosol Layers in the CALIPSO Lidar Measurements","volume":"26","author":"Vaughan","year":"2009","journal-title":"J. Atmos. Ocean. Technol."},{"key":"ref_39","doi-asserted-by":"crossref","unstructured":"Holz, R.E., Ackerman, S.A., Nagle, F.W., Frey, R., Dutcher, S., and Kuehn, R.E. (2008). Global Moderate Resolution Imaging Spectroradiometer (MODIS) cloud detection and height evaluation using CALIOP. J. Geophys. Res. Atmos., 112.","DOI":"10.1029\/2008JD009837"},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"2877","DOI":"10.5194\/acp-16-2877-2016","article-title":"Shortwave direct radiative effects of above-cloud aerosols over global oceans derived from 8 years of CALIOP and MODIS observations","volume":"16","author":"Zhang","year":"2016","journal-title":"Atmos. Chem. Phys."},{"key":"ref_41","unstructured":"Ciren, P., and Kondragunta, S. (2020, December 06). NOAA\/NESDIS\/STAR Algorithm Theoretical Basis Document: JPSS Aerosol Detection Product, Available online: https:\/\/www.star.nesdis.noaa.gov\/smcd\/spb\/aq\/AerosolWatch\/docs\/JPSS_VIIRS_EPS_ADP_ATBD_V1.3_20180606.pdf."},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"352","DOI":"10.1016\/S1532-0464(03)00034-0","article-title":"Logistic regression and artificial neural network classification models: A methodology review","volume":"35","author":"Dreiseitl","year":"2002","journal-title":"J. Biomed. Inform."},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"715","DOI":"10.1016\/j.rse.2010.10.013","article-title":"Satellite image-based maps: Scientific inference or pretty pictures?","volume":"115","author":"McRoberts","year":"2011","journal-title":"Remote Sens. Environ."},{"key":"ref_44","doi-asserted-by":"crossref","first-page":"193","DOI":"10.1080\/01431160410001716923","article-title":"Mapping insect-induced tree defoliation and mortality using coarse spatial resolution satellite imagery","volume":"26","author":"Fraser","year":"2005","journal-title":"Int. J. Remote Sens."},{"key":"ref_45","doi-asserted-by":"crossref","first-page":"1123","DOI":"10.14358\/PERS.77.11.1123","article-title":"Estimating aboveground carbon of Moso bamboo forests using the k nearest neighbors technique and satellite imagery","volume":"77","author":"Zhou","year":"2011","journal-title":"Photogramm. Eng. Remote Sens."},{"key":"ref_46","doi-asserted-by":"crossref","first-page":"217","DOI":"10.1080\/01431160412331269698","article-title":"Random forest classifier for remote sensing classification","volume":"26","author":"Pal","year":"2005","journal-title":"Int. J. Remote Sens."},{"key":"ref_47","doi-asserted-by":"crossref","first-page":"1225","DOI":"10.1016\/S0895-4356(96)00002-9","article-title":"Advantages and disadvantages of using artificial neural networks versus logistic regression for predicting medical outcomes","volume":"49","author":"Tu","year":"1996","journal-title":"J. Clin. Epidemiol."},{"key":"ref_48","unstructured":"Krizhevsky, A., Sutskever, I., and Hinton, G.E. (2012). Imagenet classification with deep convolutional neural networks. Adv. Neural Inf. Process. Syst., 1097\u20131105."},{"key":"ref_49","doi-asserted-by":"crossref","first-page":"136","DOI":"10.1080\/2150704X.2016.1235299","article-title":"SatCNN: Satellite image dataset classification using agile convolutional neural networks","volume":"8","author":"Zhong","year":"2017","journal-title":"Remote Sens. Lett."},{"key":"ref_50","doi-asserted-by":"crossref","unstructured":"Cai, K., and Wang, H. (2017, January 24\u201326). Cloud classification of satellite image based on convolutional neural networks. Proceedings of the 2017 8th IEEE International Conference on Software Engineering and Service Science, Beijing, China.","DOI":"10.1109\/ICSESS.2017.8343049"},{"key":"ref_51","unstructured":"Andrew, H., Botambekov, D., and Walther, A. (2016, August 16). NOAA\/NESDIS\/STAR Algorithm Theoretical Basis Document: A Na\u00efve Bayesian Cloud Mask Delivered to NOAA Enterprise, Available online: https:\/\/www.star.nesdis.noaa.gov\/jpss\/documents\/ATBD\/ATBD_EPS_Cloud_Mask_v1.2.pdf."},{"key":"ref_52","doi-asserted-by":"crossref","first-page":"259","DOI":"10.5194\/acp-19-259-2019","article-title":"Characterizing the 2015 Indonesia fire event using modified MODIS aerosol retrievals","volume":"19","author":"Shi","year":"2019","journal-title":"Atmos. Chem. Phys."}],"container-title":["Remote Sensing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2072-4292\/13\/3\/456\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T05:16:34Z","timestamp":1760159794000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2072-4292\/13\/3\/456"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,1,28]]},"references-count":52,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2021,2]]}},"alternative-id":["rs13030456"],"URL":"https:\/\/doi.org\/10.3390\/rs13030456","relation":{"has-preprint":[{"id-type":"doi","id":"10.20944\/preprints202012.0177.v1","asserted-by":"object"}]},"ISSN":["2072-4292"],"issn-type":[{"value":"2072-4292","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,1,28]]}}}