摘要
【目的】针对多源遥感数据及其派生特征因子数据维度高、信息冗余、易造成估测模型过拟合等问题,从高维度遥感特征因子中高效优化特征组合,优化区域森林地上生物量(AGB)的k最近邻(k-NN)估测模型。【方法】提出基于快速迭代特征选择的k最近邻法(KNN-FIFS),以森林资源样地调查数据计算的森林AGB为参考,以留一法交叉验证(LOO)相应的k-NN模型反演的森林AGB均方根误差(RMSE)最小为原则,依次迭代选取遥感特征,优化区域森林AGB的k-NN估测模型。以大兴安岭根河森林保护区为研究区,结合Landsat-8 OLI各波段光谱信息、植被指数、纹理、地形因子、机载合成孔径雷达(SAR)P-波段HV极化后向散射强度信息(PHV)以及森林资源样地调查数据,利用KNN-FIFS方法估测研究区森林AGB,并与多元线性逐步回归法(SMLR)进行对比分析。【结果】利用KNN-FIFS方法,得到当k为3,特征组合为PHV、短波红外波段一均一性(H6)、短波红外波段一二阶矩(S6)、短波红外波段二二阶矩(S7)、海蓝波段相关性(Cr1)、近红外波段相关性(Cr5)、海蓝波段相异性(D1)、增强型植被指数(EVI)时,研究区森林AGB估测结果最优,其精度(R^2=0.77,RMSE=22.74 t·hm^(-2))显著优于SMLR估测精度(R^2=0.53,RMSE=32.37 t·hm^(-2))。【结论】KNN-FIFS方法相比SMLR更适用于森林AGB多源遥感估测;KNN-FIFS方法可以从高维度遥感特征因子中高效选取相关特征进行森林AGB估测。
【Objective】Aiming at the over-fitting problem caused by information redundancy from multi-source remote sensing data and their derived high-dimensional features,this study is to effectively pre-select the optimal feature combination to optimize the k-nearest neighbor(k-NN)for regional forest above-ground biomass(AGB)estimation.【Method】This study proposed a fast iterative features selection method for k-NN method(KNN-FIFS).This method iteratively pre-select the optimal features which determined by the minimum root mean square error(RMSE)between the measured forest AGB values and the k-NN estimates based on the leave-one-out(LOO)cross-validation.Based on KNN-FIFS,multi-source data,including Landsat-8 OLI and its vegetation indices,texture metrics,topographic factors,HV polarization of P-band synthetic aperture radar(SAR)data,and forest inventory data(P HV),were used to estimate forest AGB over Daxing’an Mountain Genhe forest reserve located in Inner Mongolia.Afterwards,the model behaviors between KNN-FIFS and stepwise multiple linear regression(SMLR)method were compared.【Result】For KNN-FIFS method,the best configuration was that one with k of 3,the remotely sensed features using P HV,second moment of 1 st and 2 nd short-wave infrared bands(S6,S7),homogeneity of 1 st short-wave infrared band(H6),correlation of coastal aerosol(Cr1),correlation of the near infrared(Cr5),dissimilarity of coastal aerosol(D1)and the enhanced vegetation index(EVI).This configuration generated the most accurate estimates with R 2=0.77 and RMSE=22.74 t·hm-2,which performed much better than SMLR with R 2=0.53 and RMSE=32.37 t·hm-2.【Conclusion】KNN-FIFS is a more suitable method for forest AGB estimation than SMLR.KNN-FIFS can efficiently select the optimal feature combination to estimate regional forest AGB by use of multi-source remote sensing data with high-dimensional information.
作者
韩宗涛
江洪
王威
李增元
陈尔学
闫敏
田昕
Han Zongtao;Jiang Hong;Wang Wei;Li Zengyuan;Chen Erxue;Yan Min;Tian Xin(Key Laboratory of Spatial Data Mining&Information Sharing of Ministry of Education National Engineering Research Center of Geo-spatial Information Technology,Fuzhou University Fuzhou 350002;Research Institute of Forest Resource Information Techniques,CAF Beijing 100091;Academy of Forestry Inventory and Planning, National Forestry and Grassland Administration Beijing 100714;Fujian Collaborative Innovation Center for Big Data Applications in Governments Fuzhou 350003)
出处
《林业科学》
EI
CAS
CSCD
北大核心
2018年第9期70-79,共10页
Scientia Silvae Sinicae
基金
中央级公益性科研院所基本科研业务费专项资金“森林资源动态变化时空连续监测方法研究”(CAFYBB2017QC005)。
