Comparison of RFE-DL and stacking ensemble learning algorithms for classifying mangrove species on UAV multispectral images
•Classification of mangrove species using the UAV multispectral image and DSM.•RFE-based variable selection improves classification performance of DL algorithms.•SEL algorithm outperforms DL algorithms in mapping mangrove species.•SEL algorithm achieves the highest overall accuracy of 92.2%.•XGBoost...
Uloženo v:
| Vydáno v: | International journal of applied earth observation and geoinformation Ročník 112; s. 102890 |
|---|---|
| Hlavní autoři: | , , , , , , , , |
| Médium: | Journal Article |
| Jazyk: | angličtina |
| Vydáno: |
Elsevier B.V
01.08.2022
Elsevier |
| Témata: | |
| ISSN: | 1569-8432, 1872-826X |
| On-line přístup: | Získat plný text |
| Tagy: |
Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
|
| Abstract | •Classification of mangrove species using the UAV multispectral image and DSM.•RFE-based variable selection improves classification performance of DL algorithms.•SEL algorithm outperforms DL algorithms in mapping mangrove species.•SEL algorithm achieves the highest overall accuracy of 92.2%.•XGBoost model has the highest importance in SEL model.
Mangroves are highly productive wetland ecosystems, located at the interlocking area of tropical and subtropical coastal zones. Accurately mapping the distribution, quality and quantity of species are crucial for mangrove management, protection, and restoration. This study proposed a mangrove species mapping approach by combining recursive feature elimination (RFE) with deep learning (DL) algorithms, and further assess the effectiveness of feature selection for DL (DeeplabV3+ and PSPNet) algorithm to improve classification accuracy under the high dimensional UAV image datasets. We constructed an ensemble learning models (SEL) by stacking five base models (Random Forest, XGBoost, LightGBM, CatBoost, and AdaBoost), and evaluate the classification ability of mangrove species between SEL and RFE-DL algorithms. Comparison of the classifications of mangrove species was to evaluate the accuracy differences between SEL and base models. Results indicated that: (1) RFE algorithm could improve the classification accuracy of DL algorithms. RFE-DL models using the optimal features achieved 94.8% of overall accuracy (OA), which was 0.2%-8.5% higher than only using the original multispectral bands; (2) SEL algorithm produced better classification performance than RFE-DL with a higher 1.6%-12.7% of overall accuracy. Mcnemar's test showed the classifications of mangrove species were significant differences between the three algorithms; (3) the SEL algorithm had a strong and stable ability for classifying mangrove species. The OA of six classification scenarios was from 75.5% to 92.2%, and the highest OA using SEL algorithm was 0.8%-4.2% higher than base models; (4) XGBoost algorithm had the highest importance, while AdaBoost had the lowest importance in the SEL-based classifications. |
|---|---|
| AbstractList | Mangroves are highly productive wetland ecosystems, located at the interlocking area of tropical and subtropical coastal zones. Accurately mapping the distribution, quality and quantity of species are crucial for mangrove management, protection, and restoration. This study proposed a mangrove species mapping approach by combining recursive feature elimination (RFE) with deep learning (DL) algorithms, and further assess the effectiveness of feature selection for DL (DeeplabV3+ and PSPNet) algorithm to improve classification accuracy under the high dimensional UAV image datasets. We constructed an ensemble learning models (SEL) by stacking five base models (Random Forest, XGBoost, LightGBM, CatBoost, and AdaBoost), and evaluate the classification ability of mangrove species between SEL and RFE-DL algorithms. Comparison of the classifications of mangrove species was to evaluate the accuracy differences between SEL and base models. Results indicated that: (1) RFE algorithm could improve the classification accuracy of DL algorithms. RFE-DL models using the optimal features achieved 94.8% of overall accuracy (OA), which was 0.2%-8.5% higher than only using the original multispectral bands; (2) SEL algorithm produced better classification performance than RFE-DL with a higher 1.6%-12.7% of overall accuracy. Mcnemar's test showed the classifications of mangrove species were significant differences between the three algorithms; (3) the SEL algorithm had a strong and stable ability for classifying mangrove species. The OA of six classification scenarios was from 75.5% to 92.2%, and the highest OA using SEL algorithm was 0.8%-4.2% higher than base models; (4) XGBoost algorithm had the highest importance, while AdaBoost had the lowest importance in the SEL-based classifications. •Classification of mangrove species using the UAV multispectral image and DSM.•RFE-based variable selection improves classification performance of DL algorithms.•SEL algorithm outperforms DL algorithms in mapping mangrove species.•SEL algorithm achieves the highest overall accuracy of 92.2%.•XGBoost model has the highest importance in SEL model. Mangroves are highly productive wetland ecosystems, located at the interlocking area of tropical and subtropical coastal zones. Accurately mapping the distribution, quality and quantity of species are crucial for mangrove management, protection, and restoration. This study proposed a mangrove species mapping approach by combining recursive feature elimination (RFE) with deep learning (DL) algorithms, and further assess the effectiveness of feature selection for DL (DeeplabV3+ and PSPNet) algorithm to improve classification accuracy under the high dimensional UAV image datasets. We constructed an ensemble learning models (SEL) by stacking five base models (Random Forest, XGBoost, LightGBM, CatBoost, and AdaBoost), and evaluate the classification ability of mangrove species between SEL and RFE-DL algorithms. Comparison of the classifications of mangrove species was to evaluate the accuracy differences between SEL and base models. Results indicated that: (1) RFE algorithm could improve the classification accuracy of DL algorithms. RFE-DL models using the optimal features achieved 94.8% of overall accuracy (OA), which was 0.2%-8.5% higher than only using the original multispectral bands; (2) SEL algorithm produced better classification performance than RFE-DL with a higher 1.6%-12.7% of overall accuracy. Mcnemar's test showed the classifications of mangrove species were significant differences between the three algorithms; (3) the SEL algorithm had a strong and stable ability for classifying mangrove species. The OA of six classification scenarios was from 75.5% to 92.2%, and the highest OA using SEL algorithm was 0.8%-4.2% higher than base models; (4) XGBoost algorithm had the highest importance, while AdaBoost had the lowest importance in the SEL-based classifications. Mangroves are highly productive wetland ecosystems, located at the interlocking area of tropical and subtropical coastal zones. Accurately mapping the distribution, quality and quantity of species are crucial for mangrove management, protection, and restoration. This study proposed a mangrove species mapping approach by combining recursive feature elimination (RFE) with deep learning (DL) algorithms, and further assess the effectiveness of feature selection for DL (DeeplabV3+ and PSPNet) algorithm to improve classification accuracy under the high dimensional UAV image datasets. We constructed an ensemble learning models (SEL) by stacking five base models (Random Forest, XGBoost, LightGBM, CatBoost, and AdaBoost), and evaluate the classification ability of mangrove species between SEL and RFE-DL algorithms. Comparison of the classifications of mangrove species was to evaluate the accuracy differences between SEL and base models. Results indicated that: (1) RFE algorithm could improve the classification accuracy of DL algorithms. RFE-DL models using the optimal features achieved 94.8% of overall accuracy (OA), which was 0.2%-8.5% higher than only using the original multispectral bands; (2) SEL algorithm produced better classification performance than RFE-DL with a higher 1.6%-12.7% of overall accuracy. Mcnemar's test showed the classifications of mangrove species were significant differences between the three algorithms; (3) the SEL algorithm had a strong and stable ability for classifying mangrove species. The OA of six classification scenarios was from 75.5% to 92.2%, and the highest OA using SEL algorithm was 0.8%-4.2% higher than base models; (4) XGBoost algorithm had the highest importance, while AdaBoost had the lowest importance in the SEL-based classifications. |
| ArticleNumber | 102890 |
| Author | Fu, Bolin Fan, Donglin Lan, Guiwen Deng, Tengfang Yao, Hang He, Hongchang Liang, Yiyin He, Wen He, Xu |
| Author_xml | – sequence: 1 givenname: Bolin surname: Fu fullname: Fu, Bolin email: fubolin@glut.edu.cn organization: College of Geomatics and Geoinformation, Guilin University of Technology, Guilin 541006, China – sequence: 2 givenname: Xu surname: He fullname: He, Xu organization: College of Geomatics and Geoinformation, Guilin University of Technology, Guilin 541006, China – sequence: 3 givenname: Hang surname: Yao fullname: Yao, Hang organization: College of Geomatics and Geoinformation, Guilin University of Technology, Guilin 541006, China – sequence: 4 givenname: Yiyin surname: Liang fullname: Liang, Yiyin organization: College of Geomatics and Geoinformation, Guilin University of Technology, Guilin 541006, China – sequence: 5 givenname: Tengfang surname: Deng fullname: Deng, Tengfang organization: College of Geomatics and Geoinformation, Guilin University of Technology, Guilin 541006, China – sequence: 6 givenname: Hongchang surname: He fullname: He, Hongchang email: HHe_glut@126.com organization: College of Geomatics and Geoinformation, Guilin University of Technology, Guilin 541006, China – sequence: 7 givenname: Donglin surname: Fan fullname: Fan, Donglin organization: College of Geomatics and Geoinformation, Guilin University of Technology, Guilin 541006, China – sequence: 8 givenname: Guiwen surname: Lan fullname: Lan, Guiwen organization: College of Geomatics and Geoinformation, Guilin University of Technology, Guilin 541006, China – sequence: 9 givenname: Wen surname: He fullname: He, Wen organization: Guangxi Key Laboratory of Plant Conservation and Restoration Ecology in Karst Terrain, Guangxi Institute of Botany, Guangxi Zhuang Autonomous Region and Chinese Academy of Sciences, Guilin 541006, China |
| BookMark | eNp9UctuFDEQHKEgkQQ-gJuPXGbxa17iFC0JRFoJCRHEzWp72oMXj73Ys5Eifh5PNlw45OR2dVfZXXVRnYUYsKreMrphlLXv95s9TBtOOS933g_0RXXO-o7XPW9_nJW6aYe6l4K_qi5y3lPKuq7tz6s_2zgfILkcA4mWfL25rj_uCISR5AXMLxcmgiHjrD0Sj5DCioCfYnLLzzkTGxMxHnJ29mFtzRCmFO-R5AMah5kU3bur72Q--sWt2JLAEzfDhPl19dKCz_jm6bys7m6uv20_17svn263V7vaSDEstTadRWFBDgDjKEamW0SOjdbYCWrHRiDTo-bWiNKmrZEcrEapLZXGCisuq9uT7hhhrw6pvJ4eVASnHoGYJgVpccajGgUzgsPAtKCyw3GAUci2bRoqe6YbVrTenbQOKf4-Yl7U7LJB7yFgPGbFO9ZzOTC5jnanUZNizgmtMm6BxcVQPHBeMarW6NRelejUGp06RVeY7D_mv08_x_lw4mBx8t5hUrn4HwyOLhXXy6ruGfZfnnu2Qw |
| CitedBy_id | crossref_primary_10_1016_j_ecolind_2023_110870 crossref_primary_10_1080_10106049_2025_2547928 crossref_primary_10_1080_10095020_2024_2387457 crossref_primary_10_1111_geb_13852 crossref_primary_10_3389_ffgc_2025_1599510 crossref_primary_10_1016_j_jag_2025_104577 crossref_primary_10_1109_JSTARS_2025_3534238 crossref_primary_10_1007_s11769_025_1534_1 crossref_primary_10_1080_15481603_2023_2286746 crossref_primary_10_3389_fpls_2023_1181887 crossref_primary_10_1080_17538947_2024_2420824 crossref_primary_10_1080_27658511_2024_2307229 crossref_primary_10_3389_fpls_2022_1047479 crossref_primary_10_1071_WF23124 crossref_primary_10_1080_17538947_2025_2497488 crossref_primary_10_1109_JSTARS_2025_3595373 crossref_primary_10_1080_15481603_2025_2480422 crossref_primary_10_1111_jph_70160 crossref_primary_10_1080_17538947_2025_2520472 crossref_primary_10_1080_15472450_2025_2543838 crossref_primary_10_3389_fmars_2022_1113387 crossref_primary_10_1080_17538947_2025_2528619 crossref_primary_10_1080_01431161_2025_2532836 crossref_primary_10_1080_10095020_2025_2540570 crossref_primary_10_1038_s41598_024_84977_x crossref_primary_10_1080_01431161_2025_2546156 crossref_primary_10_1080_17538947_2025_2515269 crossref_primary_10_3389_frsen_2025_1606549 crossref_primary_10_1080_17538947_2024_2346277 crossref_primary_10_1109_JSTARS_2025_3563951 crossref_primary_10_3389_fmars_2023_1243116 crossref_primary_10_3389_fpls_2023_1272049 crossref_primary_10_1109_ACCESS_2025_3569344 crossref_primary_10_1117_1_JRS_18_014509 |
| Cites_doi | 10.1016/j.rse.2005.11.007 10.1016/j.rse.2019.111223 10.1016/j.isprsjprs.2007.08.007 10.1038/nclimate2734 10.1109/TGRS.2019.2919472 10.1111/gcb.15275 10.1016/j.isprsjprs.2015.08.002 10.2747/1548-1603.49.5.623 10.3390/rs11182114 10.1016/j.isprsjprs.2020.12.010 10.1016/j.ecolind.2021.108173 10.3390/rs12162602 10.1016/j.rse.2021.112403 10.1016/j.rse.2018.11.032 10.1109/JSTARS.2020.2994335 10.1016/j.rse.2011.12.004 10.1080/01431161.2012.718463 10.3390/rs9030247 10.3390/rs10050778 10.1016/j.rse.2017.09.029 10.3390/rs11171986 10.1016/S0893-6080(05)80023-1 10.3390/rs11212479 10.1613/jair.594 10.1016/j.isprsjprs.2021.07.011 10.1146/annurev-environ-101718-033302 10.3390/rs13081529 10.3390/rs10010089 10.1016/j.foreco.2021.119739 10.1080/13658810903174803 10.1016/j.agrformet.2019.107744 10.3390/rs11121461 10.3390/rs70506380 10.1016/j.isprsjprs.2019.11.019 10.3390/rs13234910 10.3390/rs11070808 10.1016/j.rse.2019.111467 10.1016/j.ecolind.2019.105979 10.1109/TKDE.2004.29 10.1016/j.rse.2017.11.009 10.3390/rs12081270 10.1111/gcb.12341 |
| ContentType | Journal Article |
| Copyright | 2022 The Author(s) |
| Copyright_xml | – notice: 2022 The Author(s) |
| DBID | 6I. AAFTH AAYXX CITATION 7S9 L.6 DOA |
| DOI | 10.1016/j.jag.2022.102890 |
| DatabaseName | ScienceDirect Open Access Titles Elsevier:ScienceDirect:Open Access CrossRef AGRICOLA AGRICOLA - Academic DOAJ Directory of Open Access Journals |
| DatabaseTitle | CrossRef AGRICOLA AGRICOLA - Academic |
| DatabaseTitleList | AGRICOLA |
| Database_xml | – sequence: 1 dbid: DOA name: DOAJ Directory of Open Access Journals url: https://www.doaj.org/ sourceTypes: Open Website |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Engineering Environmental Sciences |
| EISSN | 1872-826X |
| ExternalDocumentID | oai_doaj_org_article_d31c32a91b3047ed9ad3466550481b51 10_1016_j_jag_2022_102890 S1569843222000929 |
| GroupedDBID | 29J 4.4 5GY 6I. AAFTH AAQXK AAXUO ABFYP ABLST ABQEM ABQYD ABYKQ ACLVX ACRLP ACSBN ADBBV ADMUD AFKWA AFTJW AFXIZ AGYEJ AHEUO AIKHN AJBFU AJOXV AKIFW ALMA_UNASSIGNED_HOLDINGS AMFUW AMRAJ ASPBG ATOGT AVWKF AZFZN BKOJK BLECG EBS EJD FDB FEDTE FIRID FYGXN GROUPED_DOAJ HVGLF IMUCA KCYFY KOM M41 O-L P-8 P-9 P2P R2- RIG ROL SDF SDG SES SPC SSE SSJ T5K ~02 AAHBH AALRI AATTM AAXKI AAYWO AAYXX ABJNI ABWVN ACLOT ACRPL ADNMO ADVLN AEIPS AFJKZ AGQPQ AIIUN AITUG ANKPU APXCP CITATION EFJIC EFKBS 7S9 L.6 |
| ID | FETCH-LOGICAL-c439t-bc7fe3fa49aadd3d1b6ee2e5bbe730fd53e1bdb2fc3dd306c42afbe4bf04cf3f3 |
| IEDL.DBID | DOA |
| ISICitedReferencesCount | 108 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000844331400003&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| ISSN | 1569-8432 |
| IngestDate | Fri Oct 03 12:50:52 EDT 2025 Mon Sep 29 06:10:51 EDT 2025 Tue Nov 18 22:28:52 EST 2025 Sat Nov 29 07:03:35 EST 2025 Fri Feb 23 02:36:32 EST 2024 |
| IsDoiOpenAccess | true |
| IsOpenAccess | true |
| IsPeerReviewed | true |
| IsScholarly | true |
| Keywords | Mangrove species UAV multispectral images DeeplabV3+ and PSPNet algorithm Image segmentation and feature selection Stacking ensemble learning algorithm |
| Language | English |
| License | This is an open access article under the CC BY-NC-ND license. |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-c439t-bc7fe3fa49aadd3d1b6ee2e5bbe730fd53e1bdb2fc3dd306c42afbe4bf04cf3f3 |
| Notes | ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 23 |
| OpenAccessLink | https://doaj.org/article/d31c32a91b3047ed9ad3466550481b51 |
| PQID | 2718249141 |
| PQPubID | 24069 |
| ParticipantIDs | doaj_primary_oai_doaj_org_article_d31c32a91b3047ed9ad3466550481b51 proquest_miscellaneous_2718249141 crossref_citationtrail_10_1016_j_jag_2022_102890 crossref_primary_10_1016_j_jag_2022_102890 elsevier_sciencedirect_doi_10_1016_j_jag_2022_102890 |
| PublicationCentury | 2000 |
| PublicationDate | August 2022 2022-08-00 20220801 2022-08-01 |
| PublicationDateYYYYMMDD | 2022-08-01 |
| PublicationDate_xml | – month: 08 year: 2022 text: August 2022 |
| PublicationDecade | 2020 |
| PublicationTitle | International journal of applied earth observation and geoinformation |
| PublicationYear | 2022 |
| Publisher | Elsevier B.V Elsevier |
| Publisher_xml | – name: Elsevier B.V – name: Elsevier |
| References | Zorzi, Maset, Fusiello, Crosilla (b0290) 2019; 57 Jiang, Zhang, Yan, Qi, Fu, Fan, Chen (b0120) 2021; 13 Liu, Wu (b0155) 2018; 68 Torabzadeh, Leiterer, Hueni, Schaepman, Morsdorf (b0225) 2019; 279 Al-Najjar, Kalantar, Pradhan, Saeidi, Halin, Ueda, Mansor (b0015) 2019; 11 Cao, Liu, Zhuo, Liu, Zhu, Peng (b0045) 2021; 102 Yang, Weisberg, Bristow (b0255) 2012; 119 Lottering, Govender, Peerbhay, Lottering (b0175) 2020; 159 Friess, Rogers, Lovelock, Krauss, Hamilton, Lee, Lucas, Primavera, Rajkaran, Shi (b0075) 2019; 44 Bhatnagar, Gill, Ghosh (b0025) 2020; 12 Wang, Jia, Yin, Tian (b0235) 2019; 231 Fu, Xie, He, Zuo, Sun, Liu, Huang, Fan, Gao (b0085) 2021; 131 Zhao, Jiang, Li, Chen, Lu (b0270) 2021; 105 Husson, Reese, Ecke (b0110) 2017; 9 Li, Wang, Cui, Hodgson (b0140) 2021; 179 Filippi, Jensen (b0070) 2006; 100 Drǎguţ, Tiede, Levick (b0060) 2010; 24 Mallinis, Koutsias, Tsakiri-Strati, Karteris (b0180) 2008; 63 Wang, Fei, Zhang, Chen, Wang, Tsou, Liu, Lu (b0240) 2018; 10 Lou, Fu, He, Li, Tang, Lin, Fan, Gao (b0170) 2020; 12 Zhao, Shi, Qi, Wang, Jia (b0265) 2017 Zhang, Zhang, Li, Liu, Cai, Lin (b0275) 2020; 13 Diniz, Cortinhas, Nerino, Rodrigues, Sadeck, Adami, Souza-Filho (b0055) 2019; 11 Li, Wong, Fung (b0150) 2019; 11 Taddeo, Dronova, Depsky (b0215) 2019; 234 Dronova (b0065) 2015; 7 Long, Li, Lin, Zhang (b0165) 2021; 102 Aasen, Burkart, Bolten, Bareth (b0005) 2015; 108 Wolpert (b0250) 1992; 5 Polikar (b0200) 2012 Healey, Cohen, Yang, Kenneth Brewer, Brooks, Gorelick, Hernandez, Huang, Joseph Hughes, Kennedy, Loveland, Moisen, Schroeder, Stehman, Vogelmann, Woodcock, Yang, Zhu (b0105) 2018; 204 Li, Jia, Zhang, Ren, Wen (b0135) 2019; 11 Murdiyarso, Purbopuspito, Kauffman, Warren, Sasmito, Donato, Manuri, Krisnawati, Taberima, Kurnianto (b0190) 2015; 5 Zhong, Hu, Zhou (b0280) 2019; 221 Fu, Liu, He, Lan, He, Liu, Huang, Fan, Zhao, Jia (b0080) 2021; 104 Agaton, Collera (b0010) 2022; 503 Liu, Fu, Fan, Zuo, Xie, He, Liu, Huang, Gao, Zhao (b0160) 2021; 103 Ting, Witten (b0220) 1999; 10 Zhou, Yang, Li, Cai, Yang, Xia (b0285) 2021; 13 Cai, Li, Zhang, Lin (b0035) 2020; 92 Cao, Leng, Liu, Liu, He, Zhu (b0040) 2018; 10 Villoslada, Bergamo, Ward, Burnside, Joyce, Bunce, Sepp (b0230) 2020; 111 Kim, Yeom (b0130) 2014; 1–23 Goldberg, Lagomasino, Thomas, Fatoyinbo (b0100) 2020; 26 Moffett, Gorelick (b0185) 2012; 34 Pastor-Guzman, Dash, Atkinson (b0195) 2018; 205 Ghimire, Rogan, Galiano, Panday, Neeti (b0090) 2012; 49 Stoian, Poulain, Inglada, Poughon, Derksen (b0210) 2019; 11 Zhang, Zhang, Li, Liu, Cai, Lin (b0260) 2020; 13 Jia, Wang, Zhang, Mao, Wang (b0115) 2018; 73 Kattenborn, Leitloff, Schiefer, Hinz (b0125) 2021; 173 Chen, Zhu, Papandreou, Schroff, Adam (b0050) 2018 Saintilan, Wilson, Rogers, Rajkaran, Krauss (b0205) 2013; 20 Ghosh, Joshi (b0095) 2014; 26 Li, Wong, Fung (b0145) 2021; 258 Webb, Zheng (b0245) 2004; 16 Al-Najjar (10.1016/j.jag.2022.102890_b0015) 2019; 11 Wang (10.1016/j.jag.2022.102890_b0240) 2018; 10 Ting (10.1016/j.jag.2022.102890_b0220) 1999; 10 Lottering (10.1016/j.jag.2022.102890_b0175) 2020; 159 Cao (10.1016/j.jag.2022.102890_b0040) 2018; 10 Fu (10.1016/j.jag.2022.102890_b0085) 2021; 131 Webb (10.1016/j.jag.2022.102890_b0245) 2004; 16 Mallinis (10.1016/j.jag.2022.102890_b0180) 2008; 63 Murdiyarso (10.1016/j.jag.2022.102890_b0190) 2015; 5 Villoslada (10.1016/j.jag.2022.102890_b0230) 2020; 111 Wang (10.1016/j.jag.2022.102890_b0235) 2019; 231 Diniz (10.1016/j.jag.2022.102890_b0055) 2019; 11 Stoian (10.1016/j.jag.2022.102890_b0210) 2019; 11 Ghimire (10.1016/j.jag.2022.102890_b0090) 2012; 49 Saintilan (10.1016/j.jag.2022.102890_b0205) 2013; 20 Husson (10.1016/j.jag.2022.102890_b0110) 2017; 9 Zhang (10.1016/j.jag.2022.102890_b0260) 2020; 13 Wolpert (10.1016/j.jag.2022.102890_b0250) 1992; 5 Zhang (10.1016/j.jag.2022.102890_b0275) 2020; 13 Ghosh (10.1016/j.jag.2022.102890_b0095) 2014; 26 Liu (10.1016/j.jag.2022.102890_b0160) 2021; 103 Polikar (10.1016/j.jag.2022.102890_b0200) 2012 Moffett (10.1016/j.jag.2022.102890_b0185) 2012; 34 Dronova (10.1016/j.jag.2022.102890_b0065) 2015; 7 Zhong (10.1016/j.jag.2022.102890_b0280) 2019; 221 Jiang (10.1016/j.jag.2022.102890_b0120) 2021; 13 Zhao (10.1016/j.jag.2022.102890_b0265) 2017 Liu (10.1016/j.jag.2022.102890_b0155) 2018; 68 Goldberg (10.1016/j.jag.2022.102890_b0100) 2020; 26 Taddeo (10.1016/j.jag.2022.102890_b0215) 2019; 234 Zhou (10.1016/j.jag.2022.102890_b0285) 2021; 13 Drǎguţ (10.1016/j.jag.2022.102890_b0060) 2010; 24 Pastor-Guzman (10.1016/j.jag.2022.102890_b0195) 2018; 205 Filippi (10.1016/j.jag.2022.102890_b0070) 2006; 100 Long (10.1016/j.jag.2022.102890_b0165) 2021; 102 Li (10.1016/j.jag.2022.102890_b0145) 2021; 258 Friess (10.1016/j.jag.2022.102890_b0075) 2019; 44 Cai (10.1016/j.jag.2022.102890_b0035) 2020; 92 Yang (10.1016/j.jag.2022.102890_b0255) 2012; 119 Fu (10.1016/j.jag.2022.102890_b0080) 2021; 104 Lou (10.1016/j.jag.2022.102890_b0170) 2020; 12 Cao (10.1016/j.jag.2022.102890_b0045) 2021; 102 Li (10.1016/j.jag.2022.102890_b0150) 2019; 11 Bhatnagar (10.1016/j.jag.2022.102890_b0025) 2020; 12 Chen (10.1016/j.jag.2022.102890_b0050) 2018 Li (10.1016/j.jag.2022.102890_b0140) 2021; 179 Aasen (10.1016/j.jag.2022.102890_b0005) 2015; 108 Kattenborn (10.1016/j.jag.2022.102890_b0125) 2021; 173 Kim (10.1016/j.jag.2022.102890_b0130) 2014; 1–23 Healey (10.1016/j.jag.2022.102890_b0105) 2018; 204 Li (10.1016/j.jag.2022.102890_b0135) 2019; 11 Zorzi (10.1016/j.jag.2022.102890_b0290) 2019; 57 Torabzadeh (10.1016/j.jag.2022.102890_b0225) 2019; 279 Zhao (10.1016/j.jag.2022.102890_b0270) 2021; 105 Jia (10.1016/j.jag.2022.102890_b0115) 2018; 73 Agaton (10.1016/j.jag.2022.102890_b0010) 2022; 503 |
| References_xml | – year: 2017 ident: b0265 article-title: Pyramid Scene Parsing Network publication-title: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). IEEE – volume: 13 start-page: 4910 year: 2021 ident: b0285 article-title: Object-based wetland vegetation classification using multi-feature selection of unoccupied aerial vehicle RGB imagery publication-title: Remote Sens. – volume: 10 start-page: 89 year: 2018 ident: b0040 article-title: Object-based mangrove species classification using unmanned aerial vehicle hyperspectral images and digital surface models publication-title: Remote Sens. – volume: 68 start-page: 298 year: 2018 end-page: 307 ident: b0155 article-title: Crown-level tree species classification from AISA hyperspectral imagery using an innovative pixel-weighting approach publication-title: Int. J. Appl. Earth Obs. Geoinf. – volume: 10 start-page: 271 year: 1999 end-page: 289 ident: b0220 article-title: Issues in Stacked Generalization publication-title: J. Artif. Intell. Res. – volume: 10 start-page: 778 year: 2018 ident: b0240 article-title: Assessing texture features to classify coastal wetland vegetation from high spatial resolution imagery using Completed Local Binary Patterns (CLBP) publication-title: Remote Sensing – volume: 57 start-page: 8255 year: 2019 end-page: 8261 ident: b0290 article-title: Full-waveform airborne LiDAR data classification using convolutional neural networks publication-title: IEEE Trans. Geosci. Remote Sens. – volume: 279 year: 2019 ident: b0225 article-title: Tree species classification in a temperate mixed forest using a combination of imaging spectroscopy and airborne laser scanning publication-title: Agric. For. Meteorol. – volume: 5 start-page: 1089 year: 2015 end-page: 1092 ident: b0190 article-title: The potential of Indonesian mangrove forests for global climate change mitigation publication-title: Nat. Clim. Change – volume: 108 start-page: 245 year: 2015 end-page: 259 ident: b0005 article-title: Generating 3D hyperspectral information with lightweight UAV snapshot cameras for vegetation monitoring: from camera calibration to quality assurance publication-title: ISPRS J. Photogrammetry Remote Sens. – volume: 16 start-page: 980 year: 2004 end-page: 991 ident: b0245 article-title: Multistrategy ensemble learning: reducing error by combining ensemble learning techniques publication-title: IEEE Trans. Knowl. Data Eng. – volume: 11 start-page: 2479 year: 2019 ident: b0135 article-title: Incorporating the plant phenological trajectory into mangrove species mapping with dense time series sentinel-2 imagery and the google earth engine platform publication-title: Remote Sens. – volume: 102 year: 2021 ident: b0165 article-title: Mapping the vegetation distribution and dynamics of a wetland using adaptive-stacking and Google Earth Engine based on multi-source remote sensing data publication-title: Int. J. Appl. Earth Obs. Geoinf. – volume: 205 start-page: 71 year: 2018 end-page: 84 ident: b0195 article-title: Remote sensing of mangrove forest phenology and its environmental drivers publication-title: Remote Sens. Environ. – volume: 204 start-page: 717 year: 2018 end-page: 728 ident: b0105 article-title: Mapping forest change using stacked generalization: an ensemble approach publication-title: Remote Sens. Environ. – volume: 231 year: 2019 ident: b0235 article-title: A review of remote sensing for mangrove forests: 1956–2018 publication-title: Remote Sens. Environ. – start-page: 833 year: 2018 end-page: 851 ident: b0050 article-title: Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation publication-title: Computer Vision – ECCV 2018 – volume: 102 year: 2021 ident: b0045 article-title: Combining UAV-based hyperspectral and LiDAR data for mangrove species classification using the rotation forest algorithm publication-title: Int. J. Appl. Earth Obs. Geoinf. – volume: 258 year: 2021 ident: b0145 article-title: Mapping multi-layered mangroves from multispectral, hyperspectral, and LiDAR data publication-title: Remote Sens. Environ. – volume: 234 year: 2019 ident: b0215 article-title: Spectral vegetation indices of wetland greenness: responses to vegetation structure, composition, and spatial distribution publication-title: Remote Sens. Environ. – volume: 221 start-page: 430 year: 2019 end-page: 443 ident: b0280 article-title: Deep learning based multi-temporal crop classification publication-title: Remote Sens. Environ. – volume: 26 start-page: 298 year: 2014 end-page: 311 ident: b0095 article-title: A comparison of selected classification algorithms for mapping bamboo patches in lower Gangetic plains using very high resolution WorldView 2 imagery publication-title: Int. J. Appl. Earth Obs. Geoinf. – volume: 100 start-page: 512 year: 2006 end-page: 530 ident: b0070 article-title: Fuzzy learning vector quantization for hyperspectral coastal vegetation classification publication-title: Remote Sens. Environ. – volume: 103 year: 2021 ident: b0160 article-title: Study on transfer learning ability for classifying marsh vegetation with multi-sensor images using DeepLabV3+ and HRNet deep learning algorithms publication-title: Int. J. Appl. Earth Obs. Geoinf. – volume: 11 start-page: 1986 year: 2019 ident: b0210 article-title: Land cover maps production with high resolution satellite image time series and convolutional neural networks: adaptations and limits for operational systems publication-title: Remote Sens. – volume: 503 year: 2022 ident: b0010 article-title: Now or later? Optimal timing of mangrove rehabilitation under climate change uncertainty publication-title: For. Ecol. Manage. – volume: 13 start-page: 2264 year: 2020 end-page: 2275 ident: b0260 article-title: Classification of Paddy Rice using a stacked generalization approach and the spectral mixture method based on MODIS time series publication-title: IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens. – volume: 12 start-page: 1270 year: 2020 ident: b0170 article-title: An Optimized object-based random forest algorithm for marsh vegetation mapping using high-spatial-resolution GF-1 and ZY-3 data publication-title: Remote Sens. – volume: 1–23 year: 2014 ident: b0130 article-title: Effect of red-edge and texture features for object-based paddy rice crop classification using RapidEye multi-spectral satellite image data publication-title: Int. J. Remote Sens. – volume: 11 start-page: 2114 year: 2019 ident: b0150 article-title: Classification of mangrove species using combined WordView-3 and LiDAR data in Mai Po nature reserve, Hong Kong publication-title: Remote Sens. – volume: 92 year: 2020 ident: b0035 article-title: Mapping wetland using the object-based stacked generalization method based on multi-temporal optical and SAR data publication-title: Int. J. Appl. Earth Obs. Geoinf. – volume: 11 start-page: 808 year: 2019 ident: b0055 article-title: Brazilian mangrove status: three decades of satellite data analysis publication-title: Remote Sens. – volume: 7 start-page: 6380 year: 2015 end-page: 6413 ident: b0065 article-title: Object-based image analysis in wetland research: a review publication-title: Remote Sens. – volume: 20 start-page: 147 year: 2013 end-page: 157 ident: b0205 article-title: Mangrove expansion and salt marsh decline at mangrove poleward limits publication-title: Glob. Change Biol. – volume: 9 start-page: 247 year: 2017 ident: b0110 article-title: Combining spectral data and a DSM from UAS-images for improved classification of non-submerged aquatic vegetation publication-title: Remote Sens. – start-page: 1 year: 2012 end-page: 34 ident: b0200 article-title: Ensemble Learning publication-title: Ensemble Machine Learning – volume: 49 start-page: 623 year: 2012 end-page: 643 ident: b0090 article-title: An evaluation of bagging, boosting, and random forests for land-cover classification in cape Cod, Massachusetts, USA publication-title: GISci. Remote Sens. – volume: 131 year: 2021 ident: b0085 article-title: Synergy of multi-temporal polarimetric SAR and optical image satellite for mapping of marsh vegetation using object-based random forest algorithm publication-title: Ecol. Ind. – volume: 179 start-page: 121 year: 2021 end-page: 132 ident: b0140 article-title: Mapping salt marsh along coastal South Carolina using U-Net publication-title: ISPRS J. Photogramm. Remote Sens. – volume: 44 start-page: 89 year: 2019 end-page: 115 ident: b0075 article-title: The state of the World’s Mangrove forests: past, present, and future publication-title: Annu. Rev. Environ. Resour. – volume: 104 year: 2021 ident: b0080 article-title: Comparison of optimized object-based RF-DT algorithm and SegNet algorithm for classifying Karst wetland vegetation communities using ultra-high spatial resolution UAV data publication-title: Int. J. Appl. Earth Obs. Geoinf. – volume: 105 year: 2021 ident: b0270 article-title: Integration of ZiYuan-3 multispectral and stereo imagery for mapping urban vegetation using the hierarchy-based classifier publication-title: Int. J. Appl. Earth Obs. Geoinf. – volume: 26 start-page: 5844 year: 2020 end-page: 5855 ident: b0100 article-title: Global declines in human-driven mangrove loss publication-title: Glob. Change Biol. – volume: 13 start-page: 2264 year: 2020 end-page: 2275 ident: b0275 article-title: Classification of Paddy Rice using a stacked generalization approach and the spectral mixture method based on MODIS time series publication-title: IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens. – volume: 12 start-page: 2602 year: 2020 ident: b0025 article-title: Drone image segmentation using machine and deep learning for mapping raised bog vegetation communities publication-title: Remote Sens. – volume: 63 start-page: 237 year: 2008 end-page: 250 ident: b0180 article-title: Object-based classification using Quickbird imagery for delineating forest vegetation polygons in a Mediterranean test site publication-title: ISPRS J. Photogramm. Remote Sens. – volume: 111 year: 2020 ident: b0230 article-title: Fine scale plant community assessment in coastal meadows using UAV based multispectral data publication-title: Ecol. Ind. – volume: 5 start-page: 241 year: 1992 end-page: 259 ident: b0250 article-title: Stacked generalization publication-title: Neural Netw. – volume: 159 start-page: 271 year: 2020 end-page: 280 ident: b0175 article-title: Comparing partial least squares (PLS) discriminant analysis and sparse PLS discriminant analysis in detecting and mapping Solanum mauritianum in commercial forest plantations using image texture publication-title: ISPRS J. Photogramm. Remote Sens. – volume: 73 start-page: 535 year: 2018 end-page: 545 ident: b0115 article-title: Monitoring loss and recovery of mangrove forests during 42 years: the achievements of mangrove conservation in China publication-title: Int. J. Appl. Earth Obs. Geoinf. – volume: 13 start-page: 1529 year: 2021 ident: b0120 article-title: High-resolution mangrove forests classification with machine learning using worldview and UAV hyperspectral data publication-title: Remote Sens. – volume: 24 start-page: 859 year: 2010 end-page: 871 ident: b0060 article-title: ESP: a tool to estimate scale parameter for multiresolution image segmentation of remotely sensed data publication-title: Int. J. Geographical Information Sci. – volume: 119 start-page: 62 year: 2012 end-page: 71 ident: b0255 article-title: Landsat remote sensing approaches for monitoring long-term tree cover dynamics in semi-arid woodlands: comparison of vegetation indices and spectral mixture analysis publication-title: Remote Sens. Environ. – volume: 11 start-page: 1461 year: 2019 ident: b0015 article-title: Land cover classification from fused DSM and UAV images using convolutional neural networks publication-title: Remote Sens. – volume: 173 start-page: 24 year: 2021 end-page: 49 ident: b0125 article-title: Review on Convolutional Neural Networks (CNN) in vegetation remote sensing publication-title: ISPRS J. Photogramm. Remote Sens. – volume: 34 start-page: 1332 year: 2012 end-page: 1354 ident: b0185 article-title: Distinguishing wetland vegetation and channel features with object-based image segmentation publication-title: Int. J. Remote Sens. – year: 2017 ident: 10.1016/j.jag.2022.102890_b0265 article-title: Pyramid Scene Parsing Network – volume: 105 year: 2021 ident: 10.1016/j.jag.2022.102890_b0270 article-title: Integration of ZiYuan-3 multispectral and stereo imagery for mapping urban vegetation using the hierarchy-based classifier publication-title: Int. J. Appl. Earth Obs. Geoinf. – volume: 100 start-page: 512 year: 2006 ident: 10.1016/j.jag.2022.102890_b0070 article-title: Fuzzy learning vector quantization for hyperspectral coastal vegetation classification publication-title: Remote Sens. Environ. doi: 10.1016/j.rse.2005.11.007 – volume: 231 year: 2019 ident: 10.1016/j.jag.2022.102890_b0235 article-title: A review of remote sensing for mangrove forests: 1956–2018 publication-title: Remote Sens. Environ. doi: 10.1016/j.rse.2019.111223 – volume: 63 start-page: 237 year: 2008 ident: 10.1016/j.jag.2022.102890_b0180 article-title: Object-based classification using Quickbird imagery for delineating forest vegetation polygons in a Mediterranean test site publication-title: ISPRS J. Photogramm. Remote Sens. doi: 10.1016/j.isprsjprs.2007.08.007 – volume: 5 start-page: 1089 year: 2015 ident: 10.1016/j.jag.2022.102890_b0190 article-title: The potential of Indonesian mangrove forests for global climate change mitigation publication-title: Nat. Clim. Change doi: 10.1038/nclimate2734 – volume: 57 start-page: 8255 year: 2019 ident: 10.1016/j.jag.2022.102890_b0290 article-title: Full-waveform airborne LiDAR data classification using convolutional neural networks publication-title: IEEE Trans. Geosci. Remote Sens. doi: 10.1109/TGRS.2019.2919472 – volume: 26 start-page: 5844 year: 2020 ident: 10.1016/j.jag.2022.102890_b0100 article-title: Global declines in human-driven mangrove loss publication-title: Glob. Change Biol. doi: 10.1111/gcb.15275 – volume: 26 start-page: 298 year: 2014 ident: 10.1016/j.jag.2022.102890_b0095 article-title: A comparison of selected classification algorithms for mapping bamboo patches in lower Gangetic plains using very high resolution WorldView 2 imagery publication-title: Int. J. Appl. Earth Obs. Geoinf. – volume: 108 start-page: 245 year: 2015 ident: 10.1016/j.jag.2022.102890_b0005 article-title: Generating 3D hyperspectral information with lightweight UAV snapshot cameras for vegetation monitoring: from camera calibration to quality assurance publication-title: ISPRS J. Photogrammetry Remote Sens. doi: 10.1016/j.isprsjprs.2015.08.002 – volume: 73 start-page: 535 year: 2018 ident: 10.1016/j.jag.2022.102890_b0115 article-title: Monitoring loss and recovery of mangrove forests during 42 years: the achievements of mangrove conservation in China publication-title: Int. J. Appl. Earth Obs. Geoinf. – volume: 49 start-page: 623 year: 2012 ident: 10.1016/j.jag.2022.102890_b0090 article-title: An evaluation of bagging, boosting, and random forests for land-cover classification in cape Cod, Massachusetts, USA publication-title: GISci. Remote Sens. doi: 10.2747/1548-1603.49.5.623 – volume: 11 start-page: 2114 year: 2019 ident: 10.1016/j.jag.2022.102890_b0150 article-title: Classification of mangrove species using combined WordView-3 and LiDAR data in Mai Po nature reserve, Hong Kong publication-title: Remote Sens. doi: 10.3390/rs11182114 – volume: 173 start-page: 24 year: 2021 ident: 10.1016/j.jag.2022.102890_b0125 article-title: Review on Convolutional Neural Networks (CNN) in vegetation remote sensing publication-title: ISPRS J. Photogramm. Remote Sens. doi: 10.1016/j.isprsjprs.2020.12.010 – volume: 131 year: 2021 ident: 10.1016/j.jag.2022.102890_b0085 article-title: Synergy of multi-temporal polarimetric SAR and optical image satellite for mapping of marsh vegetation using object-based random forest algorithm publication-title: Ecol. Ind. doi: 10.1016/j.ecolind.2021.108173 – volume: 12 start-page: 2602 year: 2020 ident: 10.1016/j.jag.2022.102890_b0025 article-title: Drone image segmentation using machine and deep learning for mapping raised bog vegetation communities publication-title: Remote Sens. doi: 10.3390/rs12162602 – volume: 1–23 year: 2014 ident: 10.1016/j.jag.2022.102890_b0130 article-title: Effect of red-edge and texture features for object-based paddy rice crop classification using RapidEye multi-spectral satellite image data publication-title: Int. J. Remote Sens. – volume: 258 year: 2021 ident: 10.1016/j.jag.2022.102890_b0145 article-title: Mapping multi-layered mangroves from multispectral, hyperspectral, and LiDAR data publication-title: Remote Sens. Environ. doi: 10.1016/j.rse.2021.112403 – volume: 92 year: 2020 ident: 10.1016/j.jag.2022.102890_b0035 article-title: Mapping wetland using the object-based stacked generalization method based on multi-temporal optical and SAR data publication-title: Int. J. Appl. Earth Obs. Geoinf. – volume: 221 start-page: 430 year: 2019 ident: 10.1016/j.jag.2022.102890_b0280 article-title: Deep learning based multi-temporal crop classification publication-title: Remote Sens. Environ. doi: 10.1016/j.rse.2018.11.032 – volume: 13 start-page: 2264 year: 2020 ident: 10.1016/j.jag.2022.102890_b0260 article-title: Classification of Paddy Rice using a stacked generalization approach and the spectral mixture method based on MODIS time series publication-title: IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens. doi: 10.1109/JSTARS.2020.2994335 – volume: 119 start-page: 62 year: 2012 ident: 10.1016/j.jag.2022.102890_b0255 article-title: Landsat remote sensing approaches for monitoring long-term tree cover dynamics in semi-arid woodlands: comparison of vegetation indices and spectral mixture analysis publication-title: Remote Sens. Environ. doi: 10.1016/j.rse.2011.12.004 – volume: 34 start-page: 1332 year: 2012 ident: 10.1016/j.jag.2022.102890_b0185 article-title: Distinguishing wetland vegetation and channel features with object-based image segmentation publication-title: Int. J. Remote Sens. doi: 10.1080/01431161.2012.718463 – volume: 9 start-page: 247 year: 2017 ident: 10.1016/j.jag.2022.102890_b0110 article-title: Combining spectral data and a DSM from UAS-images for improved classification of non-submerged aquatic vegetation publication-title: Remote Sens. doi: 10.3390/rs9030247 – volume: 10 start-page: 778 year: 2018 ident: 10.1016/j.jag.2022.102890_b0240 article-title: Assessing texture features to classify coastal wetland vegetation from high spatial resolution imagery using Completed Local Binary Patterns (CLBP) publication-title: Remote Sensing doi: 10.3390/rs10050778 – volume: 204 start-page: 717 year: 2018 ident: 10.1016/j.jag.2022.102890_b0105 article-title: Mapping forest change using stacked generalization: an ensemble approach publication-title: Remote Sens. Environ. doi: 10.1016/j.rse.2017.09.029 – volume: 11 start-page: 1986 year: 2019 ident: 10.1016/j.jag.2022.102890_b0210 article-title: Land cover maps production with high resolution satellite image time series and convolutional neural networks: adaptations and limits for operational systems publication-title: Remote Sens. doi: 10.3390/rs11171986 – volume: 102 year: 2021 ident: 10.1016/j.jag.2022.102890_b0165 article-title: Mapping the vegetation distribution and dynamics of a wetland using adaptive-stacking and Google Earth Engine based on multi-source remote sensing data publication-title: Int. J. Appl. Earth Obs. Geoinf. – volume: 5 start-page: 241 year: 1992 ident: 10.1016/j.jag.2022.102890_b0250 article-title: Stacked generalization publication-title: Neural Netw. doi: 10.1016/S0893-6080(05)80023-1 – volume: 68 start-page: 298 year: 2018 ident: 10.1016/j.jag.2022.102890_b0155 article-title: Crown-level tree species classification from AISA hyperspectral imagery using an innovative pixel-weighting approach publication-title: Int. J. Appl. Earth Obs. Geoinf. – volume: 11 start-page: 2479 year: 2019 ident: 10.1016/j.jag.2022.102890_b0135 article-title: Incorporating the plant phenological trajectory into mangrove species mapping with dense time series sentinel-2 imagery and the google earth engine platform publication-title: Remote Sens. doi: 10.3390/rs11212479 – volume: 10 start-page: 271 year: 1999 ident: 10.1016/j.jag.2022.102890_b0220 article-title: Issues in Stacked Generalization publication-title: J. Artif. Intell. Res. doi: 10.1613/jair.594 – volume: 179 start-page: 121 year: 2021 ident: 10.1016/j.jag.2022.102890_b0140 article-title: Mapping salt marsh along coastal South Carolina using U-Net publication-title: ISPRS J. Photogramm. Remote Sens. doi: 10.1016/j.isprsjprs.2021.07.011 – volume: 44 start-page: 89 year: 2019 ident: 10.1016/j.jag.2022.102890_b0075 article-title: The state of the World’s Mangrove forests: past, present, and future publication-title: Annu. Rev. Environ. Resour. doi: 10.1146/annurev-environ-101718-033302 – volume: 13 start-page: 1529 year: 2021 ident: 10.1016/j.jag.2022.102890_b0120 article-title: High-resolution mangrove forests classification with machine learning using worldview and UAV hyperspectral data publication-title: Remote Sens. doi: 10.3390/rs13081529 – volume: 10 start-page: 89 year: 2018 ident: 10.1016/j.jag.2022.102890_b0040 article-title: Object-based mangrove species classification using unmanned aerial vehicle hyperspectral images and digital surface models publication-title: Remote Sens. doi: 10.3390/rs10010089 – volume: 13 start-page: 2264 year: 2020 ident: 10.1016/j.jag.2022.102890_b0275 article-title: Classification of Paddy Rice using a stacked generalization approach and the spectral mixture method based on MODIS time series publication-title: IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens. doi: 10.1109/JSTARS.2020.2994335 – volume: 503 year: 2022 ident: 10.1016/j.jag.2022.102890_b0010 article-title: Now or later? Optimal timing of mangrove rehabilitation under climate change uncertainty publication-title: For. Ecol. Manage. doi: 10.1016/j.foreco.2021.119739 – volume: 24 start-page: 859 year: 2010 ident: 10.1016/j.jag.2022.102890_b0060 article-title: ESP: a tool to estimate scale parameter for multiresolution image segmentation of remotely sensed data publication-title: Int. J. Geographical Information Sci. doi: 10.1080/13658810903174803 – volume: 279 year: 2019 ident: 10.1016/j.jag.2022.102890_b0225 article-title: Tree species classification in a temperate mixed forest using a combination of imaging spectroscopy and airborne laser scanning publication-title: Agric. For. Meteorol. doi: 10.1016/j.agrformet.2019.107744 – volume: 11 start-page: 1461 year: 2019 ident: 10.1016/j.jag.2022.102890_b0015 article-title: Land cover classification from fused DSM and UAV images using convolutional neural networks publication-title: Remote Sens. doi: 10.3390/rs11121461 – volume: 7 start-page: 6380 year: 2015 ident: 10.1016/j.jag.2022.102890_b0065 article-title: Object-based image analysis in wetland research: a review publication-title: Remote Sens. doi: 10.3390/rs70506380 – volume: 159 start-page: 271 year: 2020 ident: 10.1016/j.jag.2022.102890_b0175 article-title: Comparing partial least squares (PLS) discriminant analysis and sparse PLS discriminant analysis in detecting and mapping Solanum mauritianum in commercial forest plantations using image texture publication-title: ISPRS J. Photogramm. Remote Sens. doi: 10.1016/j.isprsjprs.2019.11.019 – volume: 13 start-page: 4910 year: 2021 ident: 10.1016/j.jag.2022.102890_b0285 article-title: Object-based wetland vegetation classification using multi-feature selection of unoccupied aerial vehicle RGB imagery publication-title: Remote Sens. doi: 10.3390/rs13234910 – volume: 104 year: 2021 ident: 10.1016/j.jag.2022.102890_b0080 article-title: Comparison of optimized object-based RF-DT algorithm and SegNet algorithm for classifying Karst wetland vegetation communities using ultra-high spatial resolution UAV data publication-title: Int. J. Appl. Earth Obs. Geoinf. – start-page: 833 year: 2018 ident: 10.1016/j.jag.2022.102890_b0050 article-title: Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation – volume: 11 start-page: 808 year: 2019 ident: 10.1016/j.jag.2022.102890_b0055 article-title: Brazilian mangrove status: three decades of satellite data analysis publication-title: Remote Sens. doi: 10.3390/rs11070808 – volume: 234 year: 2019 ident: 10.1016/j.jag.2022.102890_b0215 article-title: Spectral vegetation indices of wetland greenness: responses to vegetation structure, composition, and spatial distribution publication-title: Remote Sens. Environ. doi: 10.1016/j.rse.2019.111467 – volume: 111 year: 2020 ident: 10.1016/j.jag.2022.102890_b0230 article-title: Fine scale plant community assessment in coastal meadows using UAV based multispectral data publication-title: Ecol. Ind. doi: 10.1016/j.ecolind.2019.105979 – volume: 102 year: 2021 ident: 10.1016/j.jag.2022.102890_b0045 article-title: Combining UAV-based hyperspectral and LiDAR data for mangrove species classification using the rotation forest algorithm publication-title: Int. J. Appl. Earth Obs. Geoinf. – volume: 103 year: 2021 ident: 10.1016/j.jag.2022.102890_b0160 article-title: Study on transfer learning ability for classifying marsh vegetation with multi-sensor images using DeepLabV3+ and HRNet deep learning algorithms publication-title: Int. J. Appl. Earth Obs. Geoinf. – volume: 16 start-page: 980 year: 2004 ident: 10.1016/j.jag.2022.102890_b0245 article-title: Multistrategy ensemble learning: reducing error by combining ensemble learning techniques publication-title: IEEE Trans. Knowl. Data Eng. doi: 10.1109/TKDE.2004.29 – volume: 205 start-page: 71 year: 2018 ident: 10.1016/j.jag.2022.102890_b0195 article-title: Remote sensing of mangrove forest phenology and its environmental drivers publication-title: Remote Sens. Environ. doi: 10.1016/j.rse.2017.11.009 – volume: 12 start-page: 1270 year: 2020 ident: 10.1016/j.jag.2022.102890_b0170 article-title: An Optimized object-based random forest algorithm for marsh vegetation mapping using high-spatial-resolution GF-1 and ZY-3 data publication-title: Remote Sens. doi: 10.3390/rs12081270 – volume: 20 start-page: 147 year: 2013 ident: 10.1016/j.jag.2022.102890_b0205 article-title: Mangrove expansion and salt marsh decline at mangrove poleward limits publication-title: Glob. Change Biol. doi: 10.1111/gcb.12341 – start-page: 1 year: 2012 ident: 10.1016/j.jag.2022.102890_b0200 article-title: Ensemble Learning |
| SSID | ssj0017768 |
| Score | 2.6003053 |
| Snippet | •Classification of mangrove species using the UAV multispectral image and DSM.•RFE-based variable selection improves classification performance of DL... Mangroves are highly productive wetland ecosystems, located at the interlocking area of tropical and subtropical coastal zones. Accurately mapping the... |
| SourceID | doaj proquest crossref elsevier |
| SourceType | Open Website Aggregation Database Enrichment Source Index Database Publisher |
| StartPage | 102890 |
| SubjectTerms | algorithms data collection DeeplabV3+ and PSPNet algorithm Image segmentation and feature selection Mangrove species spatial data species Stacking ensemble learning algorithm UAV multispectral images wetlands |
| Title | Comparison of RFE-DL and stacking ensemble learning algorithms for classifying mangrove species on UAV multispectral images |
| URI | https://dx.doi.org/10.1016/j.jag.2022.102890 https://www.proquest.com/docview/2718249141 https://doaj.org/article/d31c32a91b3047ed9ad3466550481b51 |
| Volume | 112 |
| WOSCitedRecordID | wos000844331400003&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| journalDatabaseRights | – providerCode: PRVAON databaseName: DOAJ Directory of Open Access Journals customDbUrl: eissn: 1872-826X dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0017768 issn: 1569-8432 databaseCode: DOA dateStart: 20200101 isFulltext: true titleUrlDefault: https://www.doaj.org/ providerName: Directory of Open Access Journals |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV1LT9wwELYqxAEOFSxFbHnIlXqqFJHYzuvIY1c9VKuqKhU3y4_xsmg3qbILF_48YydZthzg0mvi2FFmPP4mM_MNIV91zHNlTRIZndvI80xGhSrRVYFEaEg1MBWHZhP5ZFLc3pY_N1p9-Zywlh64_XDnlieGM3xc-wAR2FJZLrIMgbVAxBWKp1mcl70z1cUP8rwtgkuzMioEZ308M2R23aspOoaMedqCwhvjjRMpEPf_czC9MtHh3BnvkY8dYKQX7Yvukw9QDcjuBo3ggByOXqrVcGi3XZcH5Olq3WWQ1o7-Go-i6x9UVZYiJjT-JzlFLxYWeg60ax8xpWo-rZvZ6m6xpAhoqfHwehaqoehCVdOmfgTq6zPRxaY4783FHxqyEkPNZoPrzxZoo5afyM149Pvqe9R1W4gMgpJVpE3ugDslSoU2j9tEZwAMxaUBrYCzKYdEW82c4Xg7zoxgymkQ2sXCOO74Idmq6gqOCBWpj65CmqOgUeiqYFAgUEB9SR1OD0MS919cmo6K3HfEmMs-5-xeopCkF5JshTQk39aP_G15ON4afOnFuB7oKbTDBVQs2SmWfE-xhkT0SiA7NNKiDJxq9tbaX3qFkbhTffhFVVA_LCVDGIDObiKSz__j_Y7Jjl-2TUY8IVur5gFOybZ5RIE3Z2E7PAMJWg97 |
| linkProvider | Directory of Open Access Journals |
| openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Comparison+of+RFE-DL+and+stacking+ensemble+learning+algorithms+for+classifying+mangrove+species+on+UAV+multispectral+images&rft.jtitle=International+journal+of+applied+earth+observation+and+geoinformation&rft.au=Fu%2C+Bolin&rft.au=He%2C+Xu&rft.au=Yao%2C+Hang&rft.au=Liang%2C+Yiyin&rft.date=2022-08-01&rft.issn=1569-8432&rft.volume=112+p.102890-&rft_id=info:doi/10.1016%2Fj.jag.2022.102890&rft.externalDBID=NO_FULL_TEXT |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1569-8432&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1569-8432&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1569-8432&client=summon |