文献类型：会议论文

英文题名：A FAST ITERATIVE FEATURES SELECTION FOR THE K-NEAREST NEIGHBOR

作者：Han, Zongtao[1,2] Wang, Wei[3] Li, Zengyuan[1] Chen, Erxue[1] Wang, Qiuping[4] Jiang, Hong[2] Tian, Xin[1]

第一作者：Han, Zongtao

通信作者：Tian, X[1];Wang, W[2]

机构：[1]Chinese Acad Forestry, Inst Forest Resource Informat Tech, Beijing 100091, Peoples R China;[2]Fuzhou Univ, Spatial Informat Res Ctr Fujian, Gongye Rd 525, Fuzhou 350002, Fujian, Peoples R China;[3]State Forestry Adm Peopless Republ China, Acad Forestry Inventory & Planning, Heping Rd 18, Beijing 100714, Peoples R China;[4]Weihais Marine Environm Monitoring Ctr, Dalian Rd 4, Weihai 264209, Peoples R China

会议论文集：IEEE International Geoscience & Remote Sensing Symposium

会议日期：JUL 23-28, 2017

会议地点：Fort Worth, TX

语种：英文

外文关键词：KNN-FIFS; features selection; above-ground biomass

年份：2017

摘要：Recently, multi-source remote sensing data and their derived features such as vegetation indices, texture metrics have been frequently applied to quantitatively estimate forest above-ground biomass (AGB). However, it is still challenging to efficiently select the optimal features for modeling the forest AGB. In this study, a fast, efficient and automatic method has been proposed, called as k-nearest neighbor with fast iterative features selection (KNN-FIFS). This method iteratively pre-select the optimal features which determined by the minimum root mean square error (RMSE) between the forest field data and the k-nearest neighbor (k-NN) estimates based on the leave-one-out (LOO) cross-validation. By use of KNN-FIFS and multi-source data, including Landsat-8 OLI (operational land imager) and its vegetation indices, texture metrics, HV polarization of P-band Synthetic Aperture Radar (SAR) data (HV P), and forest inventory data, were applied to estimate forest AGB over Genhe forest reserve located in Inner Mongolia, China. Afterwards, the model behaviors between KNN-FIFS and stepwise multiple linear regression (SMLR) methods were compared, which showed that the KNN-FIFS method (R-2=0.77 and RMSE = 22.74 t.ha(-1)) was superior to the SMLR method (R-2=0.53 and RMSE = 32.37 t.ha(-1)).