Random Forest Classification of Wetland Landcovers from Multi-Sensor   Data in the Arid Region of Xinjiang, China

doi:10.3390/rs8110954

CORC > 北京大学 > 地球与空间科学学院

	Random Forest Classification of Wetland Landcovers from Multi-Sensor Data in the Arid Region of Xinjiang, China
	Tian, Shaohong ; Zhang, Xianfeng ; Tian, Jie ; Sun, Quan
刊名	REMOTE SENSING
	2016
关键词	random forest object-oriented phenology arid wetland classification texture LAND-COVER CLASSIFICATION BP NEURAL-NETWORK POYANG LAKE LIDAR DATA IMAGERY BASIN AREA RADAR TREES
DOI	10.3390/rs8110954
英文摘要	The wetland classification from remotely sensed data is usually difficult due to the extensive seasonal vegetation dynamics and hydrological fluctuation. This study presents a random forest classification approach for the retrieval of the wetland landcover in the arid regions by fusing the Pleiade-1B data with multi-date Landsat-8 data. The segmentation of the Pliade-1B multispectral image data was performed based on an object-oriented approach, and the geometric and spectral features were extracted for the segmented image objects. The normalized difference vegetation index (NDVI) series data were also calculated from the multi-date Landsat-8 data, reflecting vegetation phenological changes in its growth cycle. The feature set extracted from the two sensors data was optimized and employed to create the random forest model for the classification of the wetland landcovers in the Ertix River in northern Xinjiang, China. Comparison with other classification methods such as support vector machine and artificial neural network classifiers indicates that the random forest classifier can achieve accurate classification with an overall accuracy of 93% and the Kappa coefficient of 0.92. The classification accuracy of the farming lands and water bodies that have distinct boundaries with the surrounding land covers was improved 5%-10% by making use of the property of geometric shapes. To remove the difficulty in the classification that was caused by the similar spectral features of the vegetation covers, the phenological difference and the textural information of co-occurrence gray matrix were incorporated into the classification, and the main wetland vegetation covers in the study area were derived from the two sensors data. The inclusion of phenological information in the classification enables the classification errors being reduced down, and the overall accuracy was improved approximately 10%. The results show that the proposed random forest classification by fusing multi-sensor data can retrieve better wetland landcover information than the other classifiers, which is significant for the monitoring and management of the wetland ecological resources in arid areas.; China Ministry of Science and Technology [2012BAH27B03]; Xinjiang production and Construction Corps [2014AB021]; SCI(E); ARTICLE; shaohongtian@pku.edu.cn; xfzhang@pku.edu.cn; tian.jay@gmail.com; sunquan@pku.edu.cn; 11; 8
语种	英语
内容类型	期刊论文
源URL	[http://ir.pku.edu.cn/handle/20.500.11897/458573]
专题	地球与空间科学学院
推荐引用方式 GB/T 7714	Tian, Shaohong,Zhang, Xianfeng,Tian, Jie,et al. Random Forest Classification of Wetland Landcovers from Multi-Sensor Data in the Arid Region of Xinjiang, China[J]. REMOTE SENSING,2016.
APA	Tian, Shaohong,Zhang, Xianfeng,Tian, Jie,&Sun, Quan.(2016).Random Forest Classification of Wetland Landcovers from Multi-Sensor Data in the Arid Region of Xinjiang, China.REMOTE SENSING.
MLA	Tian, Shaohong,et al."Random Forest Classification of Wetland Landcovers from Multi-Sensor Data in the Arid Region of Xinjiang, China".REMOTE SENSING (2016).