{"refrec":{"BRefID":448995,"RR":"<b>Pinkaew, S.; Koedsin, W.; Chan, J.C.; Huete, A.</b> (2025). Large-scale mangrove mapping in Thailand using multi-sensor ensemble machine learning with sentinel-1/2 and SRTM data. <i>Remote Sensing Applications 40</i>: 101744. <a href=\"https://dx.doi.org/10.1016/j.rsase.2025.101744\" target=\"_blank\">https://dx.doi.org/10.1016/j.rsase.2025.101744</a>","BEntID":446833,"PublicFlag":1,"CheckedFlag":1,"wosflag":null,"vabbflag":null,"RefStringPartII":". <i>Remote Sensing Applications 40</i>: 101744. <a href=\"https://dx.doi.org/10.1016/j.rsase.2025.101744\" target=\"_blank\">https://dx.doi.org/10.1016/j.rsase.2025.101744</a>","DocTypID":8,"DocType":"Journal article","MarineFlag":0,"FreshFlag":0,"BrackishFlag":0,"TerrestrialFlag":0,"Authorstring":"Pinkaew, S.; Koedsin, W.; Chan, J.C.; Huete, A.","OrigTitleTranslFlag":0,"Authorstringtrunc":"Pinkaew, S. <i>et al.</i>","Englishabstract":"Mangrove ecosystems provide critical ecological services but face increasing pressure from anthropogenic activities and climate change. Accurate large-scale mapping is essential for effective conservation strategies. We produced a 2024 national mangrove map by merging Sentinel-2 multispectral imagery, Sentinel-1 synthetic-aperture radar (SAR) backscatter and a Shuttle Radar Topography Mission (SRTM) digital elevation model (DEM). The analysis domain comprised all Global Mangrove Watch (2023) polygons with a 2 km buffer. From these layers we derived 23 predictors, including six spectral bands, six vegetation indices (e.g., Normalized Difference Vegetation Index, NDVI; Enhanced Vegetation Index, EVI; Mangrove Vegetation Index, MVI), four radar texture metrics (VV, VH, VV/VH ratio, contrast) and terrain variables(elevation, slope, aspect). Five widely used machine-learning classifiers-Random Forest (RF), Support Vector Machine (SVM), Classification and Regression Tree (CART), Gradient Tree Boosting (GTB) and XGBoost-were combined through soft voting after grid-based hyper-parameter tuning. The ensemble achieved an overall accuracy of 97.0 %, outperforming individual models (95.8-96.9 %). Feature-importance analysis identified MVI as the strongest discriminator (0.209-0.720), followed by VV contrast (0.052-0.097) and elevation (0.044-0.089). The final map shows 2557 km2 of mangroves distributed across 24 provinces, with 75 % located along the Andaman Sea coast. By blending complementary optical, radar and topographic information in a fully scriptbased Google Earth Engine (GEE) workflow, the study delivers an operationally scalable tool for national monitoring that supports conservation planning, carbon accounting and climateadaptation policies.","AbstractOtherLang":null,"BibLvlCode":"AS","StandardTitle":"Large-scale mangrove mapping in Thailand using multi-sensor ensemble machine learning with sentinel-1/2 and SRTM data","OrigTitleLangCode":"en","OrigTitleLangCodeExtended":"eng","OrigTitleLangID":15,"DateLastModified":{"date":"2026-10-05 01:50:03.718606","timezone_type":1,"timezone":"+02:00"},"AuthorKeywords":"Mangrove mapping;Ensemble machine learning;Multi-sensor fusion;Random forest;XGBoost;discrimination;ecosystems;forests;carbon","OtherDescriptors":null,"Notes":null,"AnaPub":2025,"MonPub":null,"DateUpdate":"2026-09-28","DateCreate":"2026-09-28","SecASFANote":null,"ConfID":null,"PeerRev":0,"VlizCoreFlag":1,"WoScode":"WOS:001590196400002","VABBcode":null,"OpenAcc":0,"DOI":"10.1016/j.rsase.2025.101744"},"refs":null,"anarec":{"AnaID":448995,"PubliDate":2025,"Pagination":"101744","XtraPublOfAnaID":null,"ISBN":null,"Volume":"40","Issue":null,"BRefMon":null,"BRefMonRR":null,"BRefXtra":null,"BRefXtraRR":null,"SerBRefID":415770,"SerRR":"Remote Sensing Applications. Elsevier: Amsterdam.  ISSN 2352-9385; e-ISSN 2352-9385","StandardTitleSer":"Remote Sensing Applications","ISSN":"2352-9385","AbbrevSer":null,"StandardTitleMon":null,"StartPage":null,"Pages":null,"ToPubliDate":null,"BRefBibLvlCode":"S","SerNotes":null},"monrec":null,"serrec":null,"relations":null,"relationsRev":null,"addrec":null,"othpubs":null,"ownerships":null,"authors":[{"AutName":"Pinkaew","Firstname":"Surachet","Initials":"S.","Affiliation":"Prince of Songkla University","Discriminator":null,"CorporateFlag":0,"BEntID":446833,"AutID":634906,"OrderNr":1,"DegrID":null,"EditorFlag":0,"CorrespFlag":0,"IllustratorFlag":0,"ReviserFlag":0,"TranslatorFlag":0,"InsAcronym":null,"InsFSN":null,"ORCID":"0009-0000-2065-0869","PersID":null,"InsID":null},{"AutName":"Koedsin","Firstname":"Werapong","Initials":"W.","Affiliation":"Prince of Songkla University","Discriminator":null,"CorporateFlag":0,"BEntID":446833,"AutID":634905,"OrderNr":2,"DegrID":null,"EditorFlag":0,"CorrespFlag":0,"IllustratorFlag":0,"ReviserFlag":0,"TranslatorFlag":0,"InsAcronym":null,"InsFSN":null,"ORCID":"0000-0002-4411-9148","PersID":null,"InsID":null},{"AutName":"Chan","Firstname":"Jonathan Cheung-Wai","Initials":"J.C.","Affiliation":"VUB Faculty of Engineering","Discriminator":null,"CorporateFlag":0,"BEntID":446833,"AutID":639114,"OrderNr":3,"DegrID":null,"EditorFlag":0,"CorrespFlag":0,"IllustratorFlag":0,"ReviserFlag":0,"TranslatorFlag":0,"InsAcronym":null,"InsFSN":null,"ORCID":"0000-0002-3741-1124","PersID":18754,"InsID":null},{"AutName":"Huete","Firstname":"Alfredo","Initials":"A.","Affiliation":"University of Technology Sydney School of Life Sciences","Discriminator":null,"CorporateFlag":0,"BEntID":446833,"AutID":634910,"OrderNr":4,"DegrID":null,"EditorFlag":0,"CorrespFlag":0,"IllustratorFlag":0,"ReviserFlag":0,"TranslatorFlag":0,"InsAcronym":null,"InsFSN":null,"ORCID":"0000-0003-2809-2376","PersID":null,"InsID":null}],"mapdetails":null,"datasets":null,"monographs":null,"monparts":null,"serparts":null,"BEntOpen":null,"BEntPrivate":null,"availability":[{"BInstID":null,"LibID":36,"BRefID":"448995","Acronym":"VLIZ","Library":"Vlaams Instituut voor de Zee","ReqLink":1,"InternalReq":1,"LoggedInReq":1,"InsPub":1,"InsID":36,"PublicFlag":1,"LendableFLag":1}],"litstyles":null,"thespers":null,"arch2discl":null,"SERpubls":[{"PublName":"Elsevier","City":"Amsterdam"}],"MONpubls":null,"pictures":[],"thestermsPath":null,"thestermsASFA":null,"taxtermsASFA":null,"geotermsASFA":null,"collections":null,"conf":null,"proj":null,"Physdatasets":null,"spcols":{"222":{"SpName":"BMB - Belgische Mariene Bibliografie","SpColID":222,"ParSpColID":null,"TopParID":null,"ShortName":"BMB","URLLocation":null,"LibID":36,"OpenRepoFlag":null,"SpTypID":null,"TopParIDNotWebsite":null,"SpColPath":"BMB"}},"doi":null,"publs":null,"serparttypes":null,"monauthors":null,"MParts":null,"SParts":null,"hLibs":null,"langs":null,"urls":[{"URL":"https://dx.doi.org/10.1016/j.rsase.2025.101744","externalID":"10.1016/j.rsase.2025.101744","URLTypeCode":"DOI","URLID":168955,"URLTypID":13,"URLType":"DOI","URLPrefix":"http://dx.doi.org/"}],"thesterms":null,"taxterms":null,"geoterms":null,"othterms":null,"asfacodes":null,"asfa2codes":null,"thestermsFRIS":null,"taxtermsFRIS":null,"geotermsFRIS":null,"othtermsFRIS":null,"resmessage":"","complete":1,"sessions":{"newSesName":"VLIZ2000\\administrator","newSesDate":{"date":"2026-09-28 08:22:36.000000","timezone_type":3,"timezone":"Europe/Brussels"},"updSesName":"VLIZ2000\\administrator","updSesDate":{"date":"2026-09-28 08:22:36.000000","timezone_type":3,"timezone":"Europe/Brussels"}}}