【摘要】：森林生物量的估算對(duì)于全球碳平衡和環(huán)境保護(hù)至關(guān)重要。通過遙感等手段提取與森林生物量相關(guān)的單波段特征、植被指數(shù)、紋理特征、地形因子等特征參數(shù),特征數(shù)量往往較多,影響預(yù)測(cè)精度。該文提出了一種后向迭代的隨機(jī)森林(RF-RFE)特征選擇方法,即利用隨機(jī)森林算法計(jì)算特征重要度,采用后向迭代的方法逐步簡化特征參數(shù)。以內(nèi)蒙古大興安嶺地區(qū)的激流河林場(chǎng)為研究區(qū)域,以實(shí)驗(yàn)區(qū)2012年"資源三號(hào)"遙感影像和森林資源3類調(diào)查的樣地?cái)?shù)據(jù)為數(shù)據(jù)源,使用RF-RFE算法進(jìn)行特征選擇分析。實(shí)驗(yàn)結(jié)果表明,在森林生物量遙感反演過程中的RF-RFE特征選擇不但能降低時(shí)間復(fù)雜度,而且保證了特征選擇的精度。
[Abstract]:Estimation of forest biomass is critical to global carbon balance and environmental protection. The single band feature, vegetation index, texture feature, terrain factor and other characteristic parameters related to forest biomass are extracted by remote sensing, and the number of features is often large, which affects the prediction accuracy. In this paper, a backward iterative stochastic forest (RF-RFE) feature selection method is proposed, in which the feature importance is calculated by the stochastic forest algorithm, and the feature parameters are simplified step by the backward iterative method. Taking the Jiluhe forest farm in Daxinganling area of Inner Mongolia as the research area, and taking the remote sensing image of "resource 3" in the experimental area in 2012 and the sample data of forest resources investigation as data sources, the feature selection analysis was carried out by using RF-RFE algorithm. The experimental results show that RF-RFE feature selection can not only reduce the time complexity but also ensure the accuracy of feature selection.
【作者單位】： 山東農(nóng)業(yè)大學(xué)信息科學(xué)與工程學(xué)院;中國測(cè)繪科學(xué)研究院;
【基金】：國家“863計(jì)劃”項(xiàng)目(2013AA122003) 國家質(zhì)量監(jiān)督檢驗(yàn)檢疫總局公益性行業(yè)科研專項(xiàng)(201410308)
【分類號(hào)】：S771.8;TP751

【相似文獻(xiàn)】

相關(guān)期刊論文 前2條

1 徐新良;曹明奎;;森林生物量遙感估算與應(yīng)用分析[J];地球信息科學(xué);2006年04期

2 ;[J];;年期

相關(guān)會(huì)議論文 前1條

1 何紅艷;郭志華;趙憲文;;遙感在森林地上生物量估算中的現(xiàn)狀及展望[A];第十五屆全國遙感技術(shù)學(xué)術(shù)交流會(huì)論文摘要集[C];2005年

相關(guān)碩士學(xué)位論文 前1條

1 林岳峰;光學(xué)與雷達(dá)遙感數(shù)據(jù)聯(lián)合反演森林生物量方法研究[D];電子科技大學(xué);2016年

，

本文編號(hào)：2190670