Artificial Mangrove Species Mapping Using Pleiades-1: An Evaluation of Pixel-Based and Object-Based Classifications with Selected Machine Learning Algorithms

doi:10.3390/rs10020294

CORC > 植物研究所 > 中国科学院植物研究所 > 植被与环境变化国家重点实验室

	Artificial Mangrove Species Mapping Using Pleiades-1: An Evaluation of Pixel-Based and Object-Based Classifications with Selected Machine Learning Algorithms
	Wang, Dezhi 2; Wan, Bo 2; Qiu, Penghua 1; Su, Yanjun 3; Guo, Qinghua 3; Wu, Xincai 2
刊名	REMOTE SENSING
	2018
卷号	10 期号:2
关键词	artificial mangrove object-based pixel-based decision tree random forest support vector machine
DOI	10.3390/rs10020294
文献子类	Article
英文摘要	In the dwindling natural mangrove today, mangrove reforestation projects are conducted worldwide to prevent further losses. Due to monoculture and the low survival rate of artificial mangroves, it is necessary to pay attention to mapping and monitoring them dynamically. Remote sensing techniques have been widely used to map mangrove forests due to their capacity for large-scale, accurate, efficient, and repetitive monitoring. This study evaluated the capability of a 0.5-m Pleiades-1 in classifying artificial mangrove species using both pixel-based and object-based classification schemes. For comparison, three machine learning algorithmsdecision tree (DT), support vector machine (SVM), and random forest (RF)were used as the classifiers in the pixel-based and object-based classification procedure. The results showed that both the pixel-based and object-based approaches could recognize the major discriminations between the four major artificial mangrove species. However, the object-based method had a better overall accuracy than the pixel-based method on average. For pixel-based image analysis, SVM produced the highest overall accuracy (79.63%); for object-based image analysis, RF could achieve the highest overall accuracy (82.40%), and it was also the best machine learning algorithm for classifying artificial mangroves. The patches produced by object-based image analysis approaches presented a more generalized appearance and could contiguously depict mangrove species communities. When the same machine learning algorithms were compared by McNemar's test, a statistically significant difference in overall classification accuracy between the pixel-based and object-based classifications only existed in the RF algorithm. Regarding species, monoculture and dominant mangrove species Sonneratia apetala group 1 (SA1) as well as partly mixed and regular shape mangrove species Hibiscus tiliaceus (HT) could well be identified. However, for complex and easily-confused mangrove species Sonneratia apetala group 2 (SA2) and other occasionally presented mangroves species (OT), only major distributions could be extracted, with an accuracy of about two-thirds. This study demonstrated that more than 80% of artificial mangroves species distribution could be mapped.
学科主题	Environmental Sciences ; Geosciences, Multidisciplinary ; Remote Sensing ; Imaging Science & Photographic Technology
电子版国际标准刊号	2072-4292
出版地	BASEL
WOS关键词	RANDOM FOREST ; LAND-COVER ; IMAGE CLASSIFICATION ; ACCURACY ASSESSMENT ; IKONOS ; WORLDVIEW-2 ; INTEGRATION ; ECOSYSTEMS
语种	英语
出版者	MDPI
WOS记录号	WOS:000427542100138
资助机构	National Key Research & Development (R&D) Plan of China [2016YFB0502304] ; National Science Foundation of ChinaNational Natural Science Foundation of China (NSFC) [41361090]
内容类型	期刊论文
源URL	[http://ir.ibcas.ac.cn/handle/2S10CLM1/20378]
专题	植被与环境变化国家重点实验室
作者单位	1.Natl Engn Res Ctr Geog Informat Syst, Wuhan 430074, Peoples R China 2.China Univ Geosci Wuhan, Fac Informat Engn, Wuhan 430074, Hubei, Peoples R China 3.Hainan Normal Univ, Coll Geog & Environm Sci, Haikou 571158, Hainan, Peoples R China 4.Chinese Acad Sci, Inst Bot, State Key Lab Vegetat & Environm Change, Beijing 100093, Peoples R China
推荐引用方式 GB/T 7714	Wang, Dezhi,Wan, Bo,Qiu, Penghua,et al. Artificial Mangrove Species Mapping Using Pleiades-1: An Evaluation of Pixel-Based and Object-Based Classifications with Selected Machine Learning Algorithms[J]. REMOTE SENSING,2018,10(2).
APA	Wang, Dezhi,Wan, Bo,Qiu, Penghua,Su, Yanjun,Guo, Qinghua,&Wu, Xincai.(2018).Artificial Mangrove Species Mapping Using Pleiades-1: An Evaluation of Pixel-Based and Object-Based Classifications with Selected Machine Learning Algorithms.REMOTE SENSING,10(2).
MLA	Wang, Dezhi,et al."Artificial Mangrove Species Mapping Using Pleiades-1: An Evaluation of Pixel-Based and Object-Based Classifications with Selected Machine Learning Algorithms".REMOTE SENSING 10.2(2018).