干旱区生态环境知识资源中心(Arid): Pixel and Object-Based Machine Learning Classification Schemes for Lithological Mapping Enhancement of Semi-Arid Regions Using Sentinel-2A Imagery: A Case Study of the Southern Moroccan Meseta

Arid

DOI	10.1109/ACCESS.2021.3107294
	Pixel and Object-Based Machine Learning Classification Schemes for Lithological Mapping Enhancement of Semi-Arid Regions Using Sentinel-2A Imagery: A Case Study of the Southern Moroccan Meseta
	Serbouti, Imane; Raji, Mohammed; Hakdaoui, Mustapha; Pradhan, Biswajeet; Lee, Chang-Wook; Alamri, Abdullah M.
通讯作者	Pradhan, B (corresponding author), Univ Technol Sydney, Fac Engn & Informat Technol, Ctr Adv Modelling & Geospatial Informat Syst CAMG, Ultimo, NSW 2007, Australia. ; Pradhan, B (corresponding author), Univ Kebangsaan Malaysia, Earth Observat Ctr, Inst Climate Change, Bangi 43600, Malaysia. ; Lee, CW (corresponding author), Kangwon Natl Univ, Div Sci Educ, Chuncheon Si 24341, Gangwon Do, South Korea.
来源期刊	IEEE ACCESS
ISSN	2169-3536
出版年	2021
卷号	9 页码:119262-119278
英文摘要	Mapping lithological units of an area using remote sensing data can be broadly grouped into pixel-based (PBIA), sub-pixel based (SPBIA) and object-based (GEOBIA) image analysis approaches. Since it is not only the datasets adequacy but also the correct classification selection that infiuences the lithological mapping. This research is intended to analyze and evaluate the efficiency of these three approaches for lithological mapping in semi-arid areas, by using Sentinel-2A data and many algorithms for image enhancement and spectral analysis, in particular two specialized Band Ratio (BR) and the Independent component analysis (ICA), for that reason the Paleozoic Massif of Skhour Rehamna, situated in the western Moroccan Meseta was chosen. In this study, the support vector machine (SVM) that is theoretically more efficient machine learning algorithm (MLA) in geological mapping is used in PBIA and GEOBIA approaches. The evaluation and comparison of the performance of these different methods showed that SVMGEOBIA approach gives the highest overall classification accuracy (OA approximate to 93%) and kappa coefficient (K) of 0, 89, while SPBIA classification showed OA of approximately 89% and kappa coefficient of 0, 84, whereas the lithological maps resulted from SVM-PBIA method exhibit salt and pepper noise, with a lower OA of 87% and kappa coefficient of 0, 80 comparing them with the other classification approaches. From the results of this comparative study, we can conclude that the SVM-GEOBIA classification approach is the most suitable technique for lithological mapping in semi-arid regions, where outcrops are often inaccessible, which complicates classic cartographic work.
英文关键词	Lithological mapping sentinel-2A SVM-GEOBIA remote sensing moroccan meseta
类型	Article
语种	英语
开放获取类型	gold
收录类别	SCI-E
WOS记录号	WOS:000692565200001
WOS关键词	OPHIOLITE COMPLEX ; HYPERSPECTRAL DATA ; ASTER ; FEATURES ; AREA ; DISCRIMINATION ; SEGMENTATION ; ALGORITHMS ; EVOLUTION ; ACCURACY
WOS类目	Computer Science, Information Systems ; Engineering, Electrical & Electronic ; Telecommunications
WOS研究方向	Computer Science ; Engineering ; Telecommunications
来源机构	King Saud University
资源类型	期刊论文
条目标识符	http://119.78.100.177/qdio/handle/2XILL650/363552
作者单位	[Serbouti, Imane; Raji, Mohammed; Hakdaoui, Mustapha] Hassan II Univ Casablanca, Fac Sci Ben MSik, Dept Geol, Lab Appl Geol Geomat & Environm, Casablanca 20000, Morocco; [Pradhan, Biswajeet] Univ Technol Sydney, Fac Engn & Informat Technol, Ctr Adv Modelling & Geospatial Informat Syst CAMG, Ultimo, NSW 2007, Australia; [Pradhan, Biswajeet] Univ Kebangsaan Malaysia, Earth Observat Ctr, Inst Climate Change, Bangi 43600, Malaysia; [Lee, Chang-Wook] Kangwon Natl Univ, Div Sci Educ, Chuncheon Si 24341, Gangwon Do, South Korea; [Alamri, Abdullah M.] King Saud Univ, Coll Sci, Dept Geol & Geophys, Riyadh 11451, Saudi Arabia
推荐引用方式 GB/T 7714	Serbouti, Imane,Raji, Mohammed,Hakdaoui, Mustapha,et al. Pixel and Object-Based Machine Learning Classification Schemes for Lithological Mapping Enhancement of Semi-Arid Regions Using Sentinel-2A Imagery: A Case Study of the Southern Moroccan Meseta[J]. King Saud University,2021,9:119262-119278.
APA	Serbouti, Imane,Raji, Mohammed,Hakdaoui, Mustapha,Pradhan, Biswajeet,Lee, Chang-Wook,&Alamri, Abdullah M..(2021).Pixel and Object-Based Machine Learning Classification Schemes for Lithological Mapping Enhancement of Semi-Arid Regions Using Sentinel-2A Imagery: A Case Study of the Southern Moroccan Meseta.IEEE ACCESS,9,119262-119278.
MLA	Serbouti, Imane,et al."Pixel and Object-Based Machine Learning Classification Schemes for Lithological Mapping Enhancement of Semi-Arid Regions Using Sentinel-2A Imagery: A Case Study of the Southern Moroccan Meseta".IEEE ACCESS 9(2021):119262-119278.