Efficiency of Extreme Gradient Boosting for Imbalanced Land Cover Classification Using an Extended Margin and Disagreement Performance

doi:10.3390/ijgi8070315

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

	Efficiency of Extreme Gradient Boosting for Imbalanced Land Cover Classification Using an Extended Margin and Disagreement Performance
	Sun, Fei ; Wang, Run 2; Wan, Bo 2; Su, Yanjun 1; Guo, Qinghua 1; Huang, Youxin ; Wu, Xincai
刊名	ISPRS INTERNATIONAL JOURNAL OF GEO-INFORMATION
	2019
卷号	8 期号:7
关键词	gradient boosting trees margin class imbalance very-high resolution (VHR) remote sensing land cover classification disagreement performance
ISSN号	2220-9964
DOI	10.3390/ijgi8070315
文献子类	Article
英文摘要	Imbalanced learning is a methodological challenge in remote sensing communities, especially in complex areas where the spectral similarity exists between land covers. Obtaining high-confidence classification results for imbalanced class issues is highly important in practice. In this paper, extreme gradient boosting (XGB), a novel tree-based ensemble system, is employed to classify the land cover types in Very-high resolution (VHR) images with imbalanced training data. We introduce an extended margin criterion and disagreement performance to evaluate the efficiency of XGB in imbalanced learning situations and examine the effect of minority class spectral separability on model performance. The results suggest that the uncertainty of XGB associated with correct classification is stable. The average probability-based margin of correct classification provided by XGB is 0.82, which is about 46.30% higher than that by random forest (RF) method (0.56). Moreover, the performance uncertainty of XGB is insensitive to spectral separability after the sample imbalance reached a certain level (minority:majority > 10:100). The impact of sample imbalance on the minority class is also related to its spectral separability, and XGB performs better than RF in terms of user accuracy for the minority class with imperfect separability. The disagreement components of XGB are better and more stable than RF with imbalanced samples, especially for complex areas with more types. In addition, appropriate sample imbalance helps to improve the trade-off between the recognition accuracy of XGB and the sample cost. According to our analysis, this margin-based uncertainty assessment and disagreement performance can help users identify the confidence level and error component in similar classification performance (overall, producer, and user accuracies).
学科主题	Computer Science, Information Systems ; Geography, Physical ; Remote Sensing
出版地	BASEL
WOS关键词	RANDOM FOREST ; DIVERSITY ; MACHINE ; MAPREDUCE ; FRAMEWORK ; QUANTITY
WOS研究方向	Computer Science ; Physical Geography ; Remote Sensing
语种	英语
出版者	MDPI
WOS记录号	WOS:000478616400001
资助机构	National Key Research & Development (R& D) Plan of China [2017YFB0503600] ; National Natural Science Foundation of ChinaNational Natural Science Foundation of China (NSFC) [41674100]
内容类型	期刊论文
源URL	[http://ir.ibcas.ac.cn/handle/2S10CLM1/19802]
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, Hubei, Peoples R China 2.China Univ Geosci, Sch Geog & Informat Engn, 388 Lumo Rd, Wuhan 430074, Hubei, Peoples R China 3.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	Sun, Fei,Wang, Run,Wan, Bo,et al. Efficiency of Extreme Gradient Boosting for Imbalanced Land Cover Classification Using an Extended Margin and Disagreement Performance[J]. ISPRS INTERNATIONAL JOURNAL OF GEO-INFORMATION,2019,8(7).
APA	Sun, Fei.,Wang, Run.,Wan, Bo.,Su, Yanjun.,Guo, Qinghua.,...&Wu, Xincai.(2019).Efficiency of Extreme Gradient Boosting for Imbalanced Land Cover Classification Using an Extended Margin and Disagreement Performance.ISPRS INTERNATIONAL JOURNAL OF GEO-INFORMATION,8(7).
MLA	Sun, Fei,et al."Efficiency of Extreme Gradient Boosting for Imbalanced Land Cover Classification Using an Extended Margin and Disagreement Performance".ISPRS INTERNATIONAL JOURNAL OF GEO-INFORMATION 8.7(2019).