馬怡茹，呂 新，易 翔，馬露露，祁亞琴，侯彤瑜，張 澤

基于機(jī)器學(xué)習(xí)的棉花葉面積指數(shù)監(jiān)測(cè)

馬怡茹，呂 新，易 翔，馬露露，祁亞琴，侯彤瑜，張 澤※

（石河子大學(xué)農(nóng)學(xué)院/新疆生產(chǎn)建設(shè)兵團(tuán)綠洲生態(tài)農(nóng)業(yè)重點(diǎn)實(shí)驗(yàn)室，石河子 832003）

為實(shí)現(xiàn)基于機(jī)器學(xué)習(xí)和無(wú)人機(jī)高光譜影像進(jìn)行棉花全生育期葉面積指數(shù)（Leaf Area Index, LAI）監(jiān)測(cè)，該研究基于大田種植滴灌棉花，在不同品種及不同施氮處理的小區(qū)試驗(yàn)基礎(chǔ)上，對(duì)無(wú)人機(jī)獲取的高光譜數(shù)據(jù)分別采用一階導(dǎo)（First Derivative, FDR）、二階導(dǎo)（Second Derivative, SDR）、SG（Savitzky-Golay）平滑和多元散射校正（Multiplicative Scatter Correction, MSC）進(jìn)行預(yù)處理，并結(jié)合Pearson相關(guān)系數(shù)法、連續(xù)投影（Successive Projections Algorithm, SPA）、隨機(jī)蛙跳（Shuffled Frog Leaping Algorithm, SFLA）和競(jìng)爭(zhēng)性自適應(yīng)重加權(quán)（Competitive Adaptive Reweighting, CARS）篩選敏感波段，將篩選出的波段，使用偏最小二乘回歸（Partial Least Squares Regression, PLSR）、支持向量回歸（Support Vector Regression, SVR）和隨機(jī)森林回歸（Random Forest Regression, RFR）3種機(jī)器學(xué)習(xí)算法構(gòu)建棉花LAI監(jiān)測(cè)模型。結(jié)果表明：棉花冠層LAI敏感響應(yīng)波段集中在可見(jiàn)光（400～780 nm）和近紅外（900 nm之后）波段；對(duì)比3種機(jī)器學(xué)習(xí)算法，各預(yù)處理下RFR建立的LAI監(jiān)測(cè)模型精度最高，穩(wěn)定性最好，其中以FDR-SFLA-RFR模型最佳，在建模集的決定系數(shù)為0.74，均方根誤差為1.648 3，相對(duì)均方根誤差為26.39%；驗(yàn)證集的決定系數(shù)、均方根誤差分別為0.67和1.622 0，相對(duì)均方根誤差為25.97%。該研究基于無(wú)人機(jī)獲取的棉花冠層光譜反射率，從不同光譜預(yù)處理、波段篩選及建模方法建立的模型中篩選出最佳估算模型用于棉花全生育期LAI監(jiān)測(cè)，研究結(jié)果可為棉花大田精準(zhǔn)管理及變量施肥提供依據(jù)。

棉花；無(wú)人機(jī)；高光譜；機(jī)器學(xué)習(xí)；葉面積指數(shù)

0 引 言

棉花是重要的經(jīng)濟(jì)作物[1]，不同施氮水平對(duì)棉花長(zhǎng)勢(shì)有顯著影響[2-4]。葉面積指數(shù)（Leaf Area Index ,LAI）是反應(yīng)作物冠層結(jié)構(gòu)及長(zhǎng)勢(shì)的重要指標(biāo)之一[5-6]，通過(guò)監(jiān)測(cè)LAI變化可為棉花變量施肥提供依據(jù)[7-8]，因此快速、準(zhǔn)確、無(wú)損的監(jiān)測(cè)棉花LAI對(duì)于指導(dǎo)作物施肥具有重要意義。傳統(tǒng)的LAI監(jiān)測(cè)主要靠人工取樣，需要投入大量人力和時(shí)間成本，存在滯后性，無(wú)法滿(mǎn)足實(shí)時(shí)監(jiān)測(cè)的需要。

遙感技術(shù)能夠?qū)崿F(xiàn)及時(shí)、動(dòng)態(tài)、宏觀(guān)的監(jiān)測(cè)，成為監(jiān)測(cè)作物生長(zhǎng)信息的重要手段。近年來(lái)，國(guó)內(nèi)外大量研究通過(guò)遙感技術(shù)對(duì)作物生物量[9-11]、葉綠素含量[12-14]、水氮含量[15-18]等生理生化參數(shù)進(jìn)行反演。而針對(duì)作物L(fēng)AI的監(jiān)測(cè)，也基于手持光譜儀、無(wú)人機(jī)和衛(wèi)星等遙感手段開(kāi)展了大量研究[19-22]。地面光譜監(jiān)測(cè)具有無(wú)損、精確等優(yōu)點(diǎn)，但由于拍攝范圍以及儀器重量等因素限制，近地光譜不能實(shí)現(xiàn)空間尺度連續(xù)快速監(jiān)測(cè)[23]。此外，有研究表明衛(wèi)星影像在作物L(fēng)AI監(jiān)測(cè)方面具有一定潛力[24]，但由于其影像分辨率在10～60m，多用于森林或大區(qū)域尺度的作物L(fēng)AI監(jiān)測(cè)[25-26]。無(wú)人機(jī)在作物監(jiān)測(cè)方面具有快速、重復(fù)的捕獲能力，且與衛(wèi)星影像相比影像分辨率更高[27]，更適應(yīng)小地塊精確監(jiān)測(cè)。已有學(xué)者基于無(wú)人機(jī)獲取的光譜圖像對(duì)小麥、水稻、玉米等作物的LAI進(jìn)行監(jiān)測(cè)[28-31]。無(wú)人機(jī)可快速獲取大量的高光譜數(shù)據(jù)，其中包含豐富的信息，同時(shí)也存在數(shù)據(jù)冗余的問(wèn)題，機(jī)器學(xué)習(xí)算法因其強(qiáng)大的學(xué)習(xí)能力和對(duì)數(shù)據(jù)深層信息的挖掘和理解能力，越來(lái)越多與遙感技術(shù)相結(jié)合應(yīng)用于作物生長(zhǎng)監(jiān)測(cè)[32-33]。國(guó)內(nèi)外學(xué)者多從光譜信息中提取植被指數(shù)，利用機(jī)器學(xué)習(xí)算法提高監(jiān)測(cè)模型精度[34-36]。

目前通過(guò)光譜數(shù)據(jù)進(jìn)行LAI監(jiān)測(cè)多基于植被指數(shù)建模，而植物冠層的高光譜反射率是對(duì)植被特征最直接的反應(yīng)，與植被指數(shù)相比可以提供更詳細(xì)，更豐富的信息，合理的光譜變換也能夠在一定程度上消除光譜數(shù)據(jù)的背景和噪聲。但高光譜數(shù)據(jù)也具有多重共線(xiàn)性，偏最小二乘模型是多元線(xiàn)性模型的一種延伸，能夠減少數(shù)據(jù)變量間的共線(xiàn)性問(wèn)題，支持向量機(jī)和隨機(jī)森林具有較高的學(xué)習(xí)和預(yù)測(cè)能力，能夠從不同角度克服變量間共線(xiàn)性的問(wèn)題。因此，為提高棉花LAI監(jiān)測(cè)模型精度，本研究使用不同方法對(duì)光譜影像數(shù)據(jù)進(jìn)行預(yù)處理，再分別篩選敏感波段，采用3種不同機(jī)器學(xué)習(xí)算法構(gòu)建LAI監(jiān)測(cè)模型，尋找最佳模型，以期為新疆棉花大田精準(zhǔn)管理及變量施肥提供依據(jù)。

1 材料與方法

1.1 試驗(yàn)區(qū)及試驗(yàn)設(shè)計(jì)

本試驗(yàn)研究區(qū)域位于石河子大學(xué)農(nóng)試場(chǎng)二連（44°19′N(xiāo)，85°59′E）。研究區(qū)為干旱半干旱區(qū)域，年平均降水量125.9～207.7 mm，晝夜溫差大，前茬作物為棉花。試驗(yàn)區(qū)域如圖1所示。

為使模型適應(yīng)于多種環(huán)境，試驗(yàn)設(shè)置不同棉花品種和施氮處理。供試棉花品種為新陸早53號(hào)、新陸早45號(hào)和魯研棉24號(hào)；每個(gè)品種設(shè)置6個(gè)氮處理分別為N0(0 kg/hm2)、N1(120 kg/hm2)、N2(240 kg/hm2)、NC(360 kg/hm2)、N3(480 kg/hm2)、N4(600 kg/hm2)，每個(gè)處理重復(fù)3次，共54個(gè)小區(qū)，各小區(qū)面積為21 m2（2.1 m×10 m）。于2019年4月24日播種，2019年10月15日收獲。新陸早系列按照“一膜三管六行”的機(jī)采棉種植模式；魯研棉24號(hào)按“一膜三管三行”的模式種植。全生育期按新疆“矮、密、早、膜”的高產(chǎn)栽培技術(shù)進(jìn)行大田管理，并注意預(yù)防病蟲(chóng)草害。

1.2 無(wú)人機(jī)高光譜圖像獲取和處理

利用無(wú)人機(jī)搭載Nano-Hyperspecal（美國(guó)）傳感器獲取出苗后第57、66、76、88、98、112及120天的高光譜圖像。無(wú)人機(jī)使用大疆M600Pro（中國(guó)，深圳）六旋翼無(wú)人機(jī)，最大載負(fù)荷10 kg，配備6塊電池，數(shù)據(jù)采集時(shí)飛行高度為100 m。Nano-Hyperspecal為推掃式成像光譜儀，基本參數(shù)如表1所示。無(wú)人機(jī)獲取冠層光譜影像時(shí)每次航線(xiàn)一致，獲取的影像為.hdr格式，將影像數(shù)據(jù)導(dǎo)入Nano自帶的校正軟件SpectralView進(jìn)行校正，校正后的影像導(dǎo)入到ENVI5.1中進(jìn)行圖像拼接和并通過(guò)標(biāo)準(zhǔn)板計(jì)算反射率。

1.3 數(shù)據(jù)采集與預(yù)處理

1.3.1 棉花LAI采集

獲取無(wú)人機(jī)高光譜圖像后，在各小區(qū)內(nèi)隨機(jī)選擇連續(xù)3株具有代表性的樣株，取全株葉片利用LI-3000測(cè)量單株總?cè)~面積，依據(jù)公式（1）計(jì)算葉面積指數(shù)LAI：

表1 Nano-Hyperspecal傳感器主要參數(shù)

1.3.2高光譜數(shù)據(jù)預(yù)處理

無(wú)人機(jī)高光譜影像獲取過(guò)程中由于環(huán)境因素的影響影像會(huì)產(chǎn)生噪音，這種噪音干擾在數(shù)據(jù)獲取過(guò)程中是不可避免的，雖然在圖像拼接過(guò)程中進(jìn)行大氣校正，但仍有部分干擾依然存在。為了有效提取對(duì)棉花LAI敏感的波段，常通過(guò)對(duì)原始光譜進(jìn)行預(yù)處理以突出特征波段、去除背景噪音。本研究采用4種不同的方式：一階導(dǎo)（First Derivative, FDR）、二階導(dǎo)(Second Derivative, SDR)、SG（Savitzky-Golay）平滑及多元散射校正（Multiplicative Scatter Correction, MSC）進(jìn)行光譜預(yù)處理。

1.3.3 特征波段篩選

高光譜影像中包括272個(gè)波段信息，使用全波段建模會(huì)出現(xiàn)數(shù)據(jù)冗余和共線(xiàn)性的問(wèn)題，因此需要從中篩選出敏感波段以降低數(shù)據(jù)維度，減少冗余信息。本研究采用Pearson相關(guān)系數(shù)、連續(xù)投影算法（Successive Projections Algorithm, SPA）、隨機(jī)蛙跳（Shuffled Frog Leaping Algorithm, SFLA）和競(jìng)爭(zhēng)性自適應(yīng)重加權(quán)（Competitive Adaptive Reweighting, CARS）4種方法篩選與棉花LAI相關(guān)性強(qiáng)的特征波段，其中相關(guān)系數(shù)法和SFLA選擇了相關(guān)性最高、選擇概率最高的10個(gè)波段進(jìn)行建模。SPA是將各自波長(zhǎng)投影到其他波長(zhǎng)上計(jì)算其投影向量，并選擇投影向量長(zhǎng)的為特征波段，其結(jié)果為信息最多、共線(xiàn)性現(xiàn)象最少的波段組合[37]。SFLA算法是一種基于青蛙社會(huì)行為的群體智能算法，結(jié)合了確定性方法和隨機(jī)性方法，是求解組合優(yōu)化問(wèn)題的有效工具。CARS算法通過(guò)自適應(yīng)重加權(quán)采樣選擇出PLS模型中回歸系數(shù)絕對(duì)值大的波長(zhǎng)，利用交互驗(yàn)證選出RMSECV最低的子集，選擇出最優(yōu)變量組合[38]，可根據(jù)信息量確定特征波段個(gè)數(shù)。

1.4 模型構(gòu)建與驗(yàn)證

1.4.1 模型構(gòu)建

為克服高光譜數(shù)據(jù)共線(xiàn)性問(wèn)題，本文采用偏最小二乘回歸（Partial Least Squares Regression, PLSR）、支持向量機(jī)回歸（Support Vector Regression, SVR）和隨機(jī)森林回歸（Random Forest Regression, RFR）3種機(jī)器學(xué)習(xí)方法構(gòu)建回歸模型。機(jī)器學(xué)習(xí)被廣泛應(yīng)用于植物生理生化參數(shù)與遙感信息非線(xiàn)性關(guān)系建立，與簡(jiǎn)單線(xiàn)性回歸相比，機(jī)器學(xué)習(xí)更適合基于多變量、多樣本的結(jié)果預(yù)測(cè)，基于Matlab2016a實(shí)現(xiàn)。

1.4.2 精度驗(yàn)證

單次采樣可獲取54個(gè)數(shù)據(jù)集，每個(gè)數(shù)據(jù)集包括54個(gè)地面實(shí)測(cè)數(shù)據(jù)和一架次無(wú)人機(jī)數(shù)據(jù)。全生育期共獲取345個(gè)樣本，按訓(xùn)練集：驗(yàn)證集=2：1進(jìn)行數(shù)據(jù)集劃分，訓(xùn)練集230個(gè)樣本，驗(yàn)證集115個(gè)樣本。以決定系數(shù)（2）、均方根誤差（Root Mean Square Error, RMSE）和相對(duì)均方根誤差（Relative Root Mean Square Error, rRMSE）進(jìn)行LAI估算模型的精度評(píng)估。其中，2越大，模型擬合性越好，RMSE和rRMSE越小，模型精度越高。其計(jì)算公式如下：

2 結(jié)果與分析

2.1 不同LAI值的棉花冠層反射率

圖2a為高光譜影像中不同LAI值對(duì)應(yīng)的冠層反射率，在760～1 000 nm內(nèi)LAI越高冠層反射率越高，且差異明顯。由圖2b可知：在490～760 nm LAI值與冠層反射率呈現(xiàn)負(fù)相關(guān)；760～1 000 nm呈現(xiàn)正相關(guān)。由此表明，無(wú)人機(jī)獲取的棉花冠層高光譜影像能夠有效反應(yīng)棉花LAI值變化。

2.2 特征波段篩選

以不同方法進(jìn)行波段篩選，結(jié)果如表2所示，棉花LAI敏感波段在可見(jiàn)光及近紅外區(qū)域均有分布。其中，原始光譜及SG平滑處理后以Pearson篩選出的特征波段在紅光（700～720 nm）波段較為集中，多為相鄰波段；而經(jīng)過(guò)FDR、SDR及MSC預(yù)處理后以Pearson進(jìn)行波段篩選后其特征波段在可見(jiàn)光（400～780 nm）波段均有分布。SFLA篩選出各預(yù)處理下的敏感波段均勻分布在可見(jiàn)光及近紅外（400～1 000 nm）波段。SPA篩選出的敏感波段多集中在近紅外（780～1 000 nm）波段，篩選結(jié)果較為集中。CARS在各預(yù)處理下篩選出的波段范圍較廣在可見(jiàn)光及近紅外（400～1 000 nm）波段皆有選擇，多集中在近紅外波段，篩選出的波段數(shù)最多。由此可見(jiàn)，不同篩選方法針對(duì)不同預(yù)處理后的光譜特征可在一定程度上實(shí)現(xiàn)數(shù)據(jù)降維。

表2 特征波段篩選結(jié)果

注：FDR為一階導(dǎo)，SDR為二階導(dǎo)，MSC為多元散射校正，Pearson為皮爾遜相關(guān)系數(shù)法，SPA為連投影法，SFLA為隨機(jī)蛙跳法，CARS為競(jìng)爭(zhēng)性自適應(yīng)重加權(quán)算法，下同。

Note: FDR is the first derivative, SDR is the second derivative, MSC is the multiplicative scatter correction, Pearson is the Pearson correlation coefficient method, SPA is the successive projections algorithm, SFLA is the shuffled frog leaping algorithm, and CARS is the competitive adaptive reweigh ting algorithm, the same below.

2.3 基于PLSR的棉花LAI監(jiān)測(cè)模型

PLSR是多元線(xiàn)性回歸、主成分分析以及典型相關(guān)分析的結(jié)合，它要求各變量與估算目標(biāo)間具有較好的線(xiàn)性關(guān)系。結(jié)合表2中篩選出的敏感波段，使用PLSR建模并驗(yàn)證。如圖3，模型建模結(jié)果中2由0.17提升到0.59，RMSE從2.717 2降低到1.911 9，rRMSE從43.50%降低到30.61%。在PLSR模型中的最佳模型為FDR-SFLA組合獲取的光譜信息建立的模型，模型效果最差為SG-Pearson模型。模型驗(yàn)證結(jié)果如圖4，與建模結(jié)果一致，以FDR-SFLA模型的擬合線(xiàn)更趨向于1∶1線(xiàn)，其2=0.59，RMSE=1.731 9，rRMSE=27.73%。

2.4基于SVR的棉花LAI監(jiān)測(cè)模型

SVR是支持向量機(jī)的一種重要形式，能夠有效、準(zhǔn)確解決回歸問(wèn)題。如圖5，不同處理下的SVR模型，其2由0.36提升到0.72，RMSE由2.579 2降低到1.570 8，rRMSE由41.29%降低到25.15%，SG-Pearson和SG-SFLA模型效果最好，但其驗(yàn)證精度與模型結(jié)果存在一定差異。由圖6可知，SG-SFLA模型較SG-Pearson模型驗(yàn)證結(jié)果更好，是由于相比SFLA，Pearson篩選的敏感波段較為集中，而SG平滑降噪同時(shí)使部分特征信息被消除，出現(xiàn)共線(xiàn)性問(wèn)題，導(dǎo)致建模效果較好，而驗(yàn)證結(jié)果較差。綜合對(duì)比模型結(jié)果及驗(yàn)證結(jié)果，F(xiàn)DR-SFLA建模集的2=0.63，RMSE=1.890 8，rRMSE=30.27%，驗(yàn)證集的2=0.63，RMSE=1.7137，rRMSE=27.44%。雖然FD-SFLA的建模效果不是最佳，但建模集與驗(yàn)證集結(jié)果表現(xiàn)一致，且該模型真實(shí)值與預(yù)測(cè)值的線(xiàn)性擬合關(guān)系更趨向于1∶1線(xiàn)。因此，基于SVR算法構(gòu)建的模型中，F(xiàn)DR-SFLA模型效果最好。

2.5 基于RFR的棉花LAI監(jiān)測(cè)模型

隨機(jī)森林是一種廣泛應(yīng)用于分類(lèi)、回歸等領(lǐng)域的機(jī)器學(xué)習(xí)算法，可以提供特征的重要性評(píng)估，從而能洞察特征選擇的過(guò)程。圖7所示，LAI監(jiān)測(cè)模型2由0.47提升到0.74，RMSE由2.152 6降低到1.648 3，rRMSE由34.46%降低到26.39%，其驗(yàn)證與建模結(jié)果表現(xiàn)一致。綜合對(duì)比，RFR構(gòu)建的模型中FDR-SFLA模型效果最好，其2=0.74，RMSE=1.648 3，rRMSE=26.39%，從圖8可看出其真實(shí)值和預(yù)測(cè)值的線(xiàn)性擬合更趨向于1∶1線(xiàn)，其2=0.67，RMSE=1.622 0，rRMSE=25.97%。

綜上所述，對(duì)比不同建模方法的模型精度，RFR模型的模型和驗(yàn)證結(jié)果均優(yōu)于PLSR和SVR；SVR效果優(yōu)于PLSR，但信息冗余導(dǎo)致建模集和驗(yàn)證集結(jié)果出現(xiàn)偏差。RFR模型克服了這一問(wèn)題，去除了冗余信息干擾，有效提升了模型精度。對(duì)比可知，非線(xiàn)性模型性能優(yōu)于線(xiàn)性模型性能，而3種機(jī)器學(xué)習(xí)方法都以FDR-SFLA模型效果最好，相較于其他方法RFR的2提高了20.27%，RMSE降低了3.97%，rRMSE降低了3.90%；驗(yàn)證集的2提高了11.94%，RMSE降低了3.97%，rRMSE降低了3.90%。

3 討 論

本研究對(duì)LAI變化和其光譜響應(yīng)進(jìn)行分析，結(jié)果表明可見(jiàn)光區(qū)域LAI與冠層光譜反射率呈負(fù)相關(guān)，近紅外區(qū)域LAI與冠層光譜反射率呈正相關(guān)，這與前人在冬小麥[39]、油菜[40]和玉米[41]研究中的結(jié)果一致。這是由于植被光譜反射率，在350～800 nm差異主要是由于植物體內(nèi)葉綠素和其他色素的影響，800～1 000 nm的差異來(lái)源于植物細(xì)胞組織的散射，棉花生長(zhǎng)茂盛多片葉子疊加輻射作用下，則會(huì)在近紅外波段產(chǎn)生較高的反射率，因此不同的LAI值的冠層光譜在近紅外區(qū)域差異更明顯。

冠層原始光譜受太陽(yáng)輻射通量，作物結(jié)構(gòu)特征和土壤背景條件影響[42]，光譜預(yù)處理可減少背景噪聲信息，能夠有效提高光譜信息精度[43]。前人研究表明，F(xiàn)DR處理可減輕作物冠層重疊對(duì)反射率的影響，也可最小化土壤或大氣背景噪聲[44]。王玉娜等[45]以不同方法處理原始光譜后估算冬小麥生物量，以FDR處理后的光譜反射率與生物量相關(guān)性更高。Li等[46]發(fā)現(xiàn)750 nm波長(zhǎng)處的一階導(dǎo)數(shù)與LAI具有較高的相關(guān)性，估算模型精度較高，與本研究結(jié)果表現(xiàn)一致。

高光譜分析包括特征波段篩選和回歸建模2個(gè)步驟。波段篩選能夠有效實(shí)現(xiàn)數(shù)據(jù)降維，緩解共線(xiàn)性的問(wèn)題，本研究通過(guò)不同篩選方法篩選出的LAI敏感波段多集中在400～780 nm的可見(jiàn)光波段以及900 nm以后的近紅外波段，這與孫晶京等[47]通過(guò)隨機(jī)蛙跳法篩選出的敏感波段相似。本研究以SFLA法篩選出的敏感波段建模效果最好，Ren等[48]對(duì)比4種波段篩選方法進(jìn)行紅茶評(píng)級(jí)，得到相同結(jié)果。已有研究中的模型，波段篩選有效降低了數(shù)據(jù)維數(shù)，但傳統(tǒng)的線(xiàn)性回歸建模仍然會(huì)出現(xiàn)共線(xiàn)性問(wèn)題。本研究基于不同機(jī)器學(xué)習(xí)算法建立LAI監(jiān)測(cè)模型，其結(jié)果表現(xiàn)為：RFR最佳，SVR次之，PLSR最差。其中以FDR-SFLA-RFR模型精度最佳（模型的2=0.74，RMSE=1.648 3，rRMSE=26.39%；驗(yàn)證集2=0.67，RMSE=1.622 0，rRMSE=25.97%），說(shuō)明RFR對(duì)于棉花LAI監(jiān)測(cè)更有效。RFR是基于樹(shù)的集成學(xué)習(xí)技術(shù)，抗過(guò)擬合能力較強(qiáng)，被廣泛應(yīng)用于長(zhǎng)勢(shì)指標(biāo)監(jiān)測(cè)，并具有更優(yōu)的建模效果，如：Han等[49]通過(guò)機(jī)器學(xué)習(xí)算法估算玉米地上生物量；Lu等[50]基于RGB圖像建立小麥生物量估算模型；Wang等[51]以不同建模方法監(jiān)測(cè)氮營(yíng)養(yǎng)指數(shù)，均以RFR模型的效果最優(yōu)。RFR模型在大樣本預(yù)測(cè)上要比其他算法具有優(yōu)勢(shì)，本研究中RFR模型也表現(xiàn)出較好的預(yù)測(cè)能力。

田明璐等[52]基于無(wú)人機(jī)獲取的光譜數(shù)據(jù)建立植被指數(shù)用于棉花盛蕾期LAI監(jiān)測(cè)，其模型驗(yàn)證集的2=0.85，RMSE=0.02，其結(jié)果優(yōu)于本研究，但其模型僅適用于盛蕾期LAI監(jiān)測(cè)。而本研究建立的模型，可用于棉花全生育期LAI監(jiān)測(cè)，且涉及不同棉花品種。Chen等[53]基于無(wú)人機(jī)獲取的多光譜數(shù)據(jù)建立棉花不同生育期LAI監(jiān)測(cè)模型，其模型的2=0.65，RMSE=0.62，精度低于本研究基于棉花冠層光譜反射率建立的模型。近年來(lái)，為更好實(shí)現(xiàn)棉花生長(zhǎng)信息監(jiān)測(cè)，有學(xué)者引入了機(jī)器視覺(jué)、深度學(xué)習(xí)等技術(shù)，有效提高了監(jiān)測(cè)模型精度[9,54]。為提高模型精度，未來(lái)可考慮引入更多監(jiān)測(cè)技術(shù)以及建模手段。

綜上所述，光譜數(shù)據(jù)采用FDR預(yù)處理，采用SFLA篩選敏感波段，可優(yōu)化模型變量，提高模型精度。RFR能夠有效對(duì)抗噪聲，更適合針對(duì)遙感數(shù)據(jù)進(jìn)行建模，F(xiàn)DR-SFLA-RFR模型在棉花全生育期LAI監(jiān)測(cè)方面具有廣闊的應(yīng)用前景。本研究試驗(yàn)設(shè)置了不同氮處理和不同棉花品種，但本研究的方法是基于特定地點(diǎn)同一年份的棉花冠層光譜數(shù)據(jù)，這限制了模型對(duì)其他數(shù)據(jù)集或其他地域的預(yù)測(cè)能力。因此，要將FDR-SFLA-RFR模型優(yōu)化至更穩(wěn)定精確，還需要從更多年份、種植模式和地區(qū)收集更多的數(shù)據(jù)集進(jìn)行模型校正。

4 結(jié) 論

本研究基于無(wú)人機(jī)獲取棉花冠層高光譜數(shù)據(jù)，通過(guò)不同預(yù)處理和波段篩選方法篩選波段組合，使用偏最小二乘回歸（Partial Least Squares Regression, PLSR）、支持向量回歸（Support Vector Regression, SVR）和隨機(jī)森林回歸（Random Forest Regression, RFR）對(duì)棉花全生育期葉面積指數(shù)LAI進(jìn)行估算，結(jié)果表明：不同LAI的冠層光譜在760～1 000 nm存在明顯差異，冠層光譜與LAI存在明顯的相關(guān)性。對(duì)比不同預(yù)處理下的波段篩選方法可知，基于相關(guān)系數(shù)進(jìn)行波段篩選，篩選出的波段過(guò)于集中，會(huì)出現(xiàn)信息冗余和信息提取不全的現(xiàn)象；而隨機(jī)蛙跳（Shuffled Frog Leaping Algorithm, SFLA）算法篩選出的敏感波段分布均勻，對(duì)棉花LAI敏感的波段多集中在400～780 nm的可見(jiàn)光波段以及900 nm以后的近紅外波段。不同建模方法的棉花LAI估算模型結(jié)果表現(xiàn)為：RFR最佳，SVR次之，PLSR最差，F(xiàn)DR-SFLA-RFR模型最佳，其建模結(jié)果的2為0.74，RMSE為1.648 3，rRMSE為26.39%；驗(yàn)證結(jié)果的2為0.67，RMSE為1.622 0，rRMSE為25.97%。

[1] Khan M A, Wahid A, Ahmad M, et al. World Cotton Production and Consumption: An Overview[M]. Cotton Production and Uses. Pakistan: Multan, 2020: 1-7.

[2] 忠智博，翟國(guó)亮，鄧忠，等. 水氮施量對(duì)膜下滴灌棉花生長(zhǎng)及水氮分布的影響[J]. 灌溉排水學(xué)報(bào)，2020，39(1)：67-76.

Zhong Zhibo, Zhai Guoliang, Deng Zhong, et al. The impact of N application and drip irrigation amount on cotton growth and water and N distributions in soil mulched with film[J]. Journal of Irrigation and Drainage, 2020, 39(1): 67-76. (in Chinese with English abstract）

[3] 馬騰飛，李杰，陳志，等. 施氮對(duì)膜下滴灌棉花生長(zhǎng)發(fā)育及土壤硝態(tài)氮的影響[J]. 新疆農(nóng)業(yè)科學(xué)，2020，57(2)：245-253.

Ma Tengfei, Li Jie, Chen Zhi, et al. Simulating effects of nitrogen application on growth and development and soil nitrate nitrogen of cotton under mulched drip irrigation[J]. Xinjiang Agricultural Sciences, 2020, 57(2): 245-253. (in Chinese with English abstract)

[4] Muharam F M, Delahunty T, Maas S J. Evaluation of nitrogen treatment effects on the reflectance of cotton at different spatial scales[J]. International Journal of Remote Sensing, 2018, 39(23): 8482-8504.

[5] 張宏鳴，劉雯，韓文霆，等. 基于梯度提升樹(shù)算法的夏玉米葉面積指數(shù)反演[J]. 農(nóng)業(yè)機(jī)械學(xué)報(bào)，2019，50(5)：258-266.

Zhang Hongming, Liu Wen, Han Wenting, et al. Inversion of summer maize leaf area index based on gradient boosting decision tree algorithm[J]. Transactions of the Chinese Society for Agricultural Machinery, 2019, 50(5): 258-266. (in Chinese with English abstract)

[6] 陶惠林，徐良驥，馮海寬，等. 基于無(wú)人機(jī)高光譜長(zhǎng)勢(shì)指標(biāo)的冬小麥長(zhǎng)勢(shì)監(jiān)測(cè)[J]. 農(nóng)業(yè)機(jī)械學(xué)報(bào)，2020，51(2)：180-191.

Tao Huilin, Xu Liangji, Feng Haikuan, et al. Monitoring of winter wheat growth based on UAV hyperspectral growth index[J]. Transactions of the Chinese Society for Agricultural Machinery, 2020, 51(2): 180-191. (in Chinese with English abstract)

[7] 尹佳碩. 變量施肥夏玉米高光譜與農(nóng)學(xué)參數(shù)關(guān)聯(lián)模型研究[D]. 保定：河北農(nóng)業(yè)大學(xué)，2018.

Yin Jiashuo. Study on Correlation Model of Hyperspectral and Agronomic Parameters of Summer Maize with Variable Fertilization[D]. Baoding: Hebei Agricultural University, 2018. (in Chinese with English abstract)

[8] 鄧江，谷海斌，王澤，等. 基于無(wú)人機(jī)遙感的棉花主要生育時(shí)期地上生物量估算及驗(yàn)證[J]. 干旱地區(qū)農(nóng)業(yè)研究，2019，37(5)：55-61，69.

Deng Jiang, Gu Haibin, Wang Ze, et al. Estimation and validation of above-ground biomass of cotton during main growth period using Unmanned[J]. Agricultural Research in the Arid Areas, 2019, 37(5): 55-61, 69. (in Chinese with English abstract)

[9] 劉金然. 基于無(wú)人機(jī)遙感影像的棉花主要生長(zhǎng)參數(shù)反演[D]. 濟(jì)南：山東師范大學(xué)，2019.

Liu Jinran. Inversion of Cotton Main Growth Parameters Based on Unmanned Aerial Vehicle (UAV) Sensing Image[D]. Jinan: Shandong Normal University, 2019. (in Chinese with English abstract)

[10] Zhu Y, Zhao C, Yang H, et al. Estimation of maize above-ground biomass based on stem-leaf separation strategy integrated with LiDAR and optical remote sensing data[J]. PeerJ, 2019, 7: e7593.

[11] Haldar D, Dave V, Misra A, et al. Radar vegetation index for assessing cotton crop condition using RISAT-1 data[J]. Geocarto International, 2020, 35(4): 364-375.

[12] 依爾夏提·阿不來(lái)提，白燈莎·買(mǎi)買(mǎi)提艾力，買(mǎi)買(mǎi)提·沙吾提等. 基于高光譜和BP神經(jīng)網(wǎng)絡(luò)的棉花冠層葉綠素含量聯(lián)合估算[J]. 光學(xué)學(xué)報(bào)，2019，39(9)：372-380.

Ershat Ablet, Baidengsha Maimaitiail, Mamat Sawut, et al. Combined estimation of chlorophyll content in cotton canopy based on hyperspectral parameters and back propagation neural network[J]. Acta Optica Sinica, 2019, 39(9): 372-380. (in Chinese with English abstract)

[13] Xie Q, Dash J, Huete A, et al. Retrieval of crop biophysical parameters from Sentinel-2 remote sensing imagery[J]. International Journal of Applied Earth Observation and Geoinformation, 2019, 80: 187-195.

[14] 張卓然，常慶瑞，張廷龍，等. 基于支持向量機(jī)的棉花冠層葉片葉綠素含量高光譜遙感估算[J]. 西北農(nóng)林科技大學(xué)學(xué)報(bào)：自然科學(xué)版，2018，46(11)：39-45.

Zhang Zhuoran, Chang Qingrui, Zhang Yanlong, et al. Hyperspectral estimation of chlorophyll content of cotton canopy leaves based on support vector machine [J]. Journal of Northwest A&F University: Natural Science Edition, 2018, 46(11): 39-45. (in Chinese with English abstract)

[15] 劉馨月. 基于熒光參數(shù)的棉花水分狀況的高光譜遙感監(jiān)測(cè)研究[D]. 石河子：石河子大學(xué)，2018.

Liu Xinyue.Hyperspectral Remote Sensing Monitoring of Cotton Moisture Status Based on Fluorescence Parameters[D]. Shihezi: Shihezi University, 2018. (in Chinese with English abstract)

[16] Tavakoli H, Gebbers R. Assessing nitrogen and water status of winter wheat using a digital camera[J]. Computers and Electronics in Agriculture, 2019, 157: 558-567.

[17] 馬巖川. 基于高光譜遙感的棉花冠層水氮參數(shù)估算[D].北京：中國(guó)農(nóng)業(yè)科學(xué)院，2020.

Ma Yanchuan. Estimation of Water and Nitrogen Parameters in Cotton Canopy Based on Hyperspectral Remote Sensing[D]. Beijng: Chinese Academy of Agricultural Sciences, 2020. (in Chinese with English abstract)

[18] Thorp K R, Thompson A L, Harders S J, et al. High-throughput phenotyping of crop water use efficiency via multispectral drone imagery and a daily soil water balance model[J]. Remote Sensing, 2018, 10(11): 1682.

[19] Fang H, Baret F, Plummer S, et al. An overview of global leaf area index (LAI): Methods, products, validation, and applications[J]. Reviews of Geophysics, 2019, 57(3): 739-799.

[20] Yu L, Shang J, Cheng Z, et al. Assessment of cornfield LAI retrieved from multi-source satellite data using continuous field LAI measurements based on a wireless sensor network[J]. Remote Sensing, 2020, 12(20): 3304.

[21] Singh P, Pandey P C, Petropoulos G P, et al. Hyperspectral remote sensing in precision agriculture: Present status, challenges, and future trends[M]. Hyperspectral Remote Sensing. Netherlands: Elsevier, 2020: 121-146.

[22] Ca?ete-Salinas P, Zamudio F, Yá?ez M, et al. Evaluation of models to determine LAI on poplar stands using spectral indices from Sentinel-2 satellite images[J]. Ecological Modelling, 2020, 428: 109058.

[23] Caballero D, Calvini R, Amigo J M. Hyperspectral Imaging in Crop Fields: Precision Agriculture[M]. Data Handling in Science and Technology. Netherlands: Elsevier, 2020: 453-473.

[24] 易秋香. 基于Sentinel-2多光譜數(shù)據(jù)的棉花葉面積指數(shù)估算[J]. 農(nóng)業(yè)工程學(xué)報(bào)，2019，35(16)：189-197.

Yi Qiuxiang. Remote estimation of cotton LAI using Sentinel-2 multispectral data[J]. Transactions of the Chinese Society of Agricultural Engineering (Transactions of the CSAE), 2019, 35(16): 189-197. (in Chinese with English abstract)

[25] Pasqualotto N, Delegido J, Van Wittenberghe S, et al. Multi-crop green LAI estimation with a new simple sentinel-2 LAI index (SeLI)[J]. Sensors, 2019, 19(4): 904.

[26] Li S, Yuan F, Ata-UI-Karim S T, et al. Combining color indices and textures of UAV-based digital imagery for rice LAI estimation[J]. Remote Sensing, 2019, 11(15): 1763.

[27] Wang J, Xiao X, Bajgain R, et al. Estimating leaf area index and aboveground biomass of grazing pastures using Sentinel-1, Sentinel-2 and Landsat images[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2019, 154: 189-201.

[28] Tao H, Feng H, Xu L, et al. Estimation of crop growth parameters using UAV-based hyperspectral remote sensing data[J]. Sensors, 2020, 20(5): 1296.

[29] Zhu W, Sun Z, Huang Y, et al. Improving Field-scale wheat LAI retrieval based on UAV remote-sensing observations and optimized VI-LUTs[J]. Remote Sensing, 2019, 11(20): 2456.

[30] 陳曉凱，李粉玲，王玉娜，等. 無(wú)人機(jī)高光譜遙感估算冬小麥葉面積指數(shù)[J]. 農(nóng)業(yè)工程學(xué)報(bào)，2020，36(22)：40-49.

Chen Xiaokai, Li Fenling, Wang Yuna, et al. Estimation of winter wheat leaf area index based on UAV hyperspectral remote sensing[J]. Transactions of the Chinese Society of Agricultural Engineering (Transactions of the CSAE), 2020, 36(22): 40-49. (in Chinese with English abstract)

[31] Peng Y, Li Y, Dai C, et al. Remote prediction of yield based on LAI estimation in oilseed rape under different planting methods and nitrogen fertilizer applications[J]. Agricultural and Forest Meteorology, 2019, 271: 116-125.

[32] Rehman T U, Mahmud M S, Chang Y K, et al. Current and future applications of statistical machine learning algorithms for agricultural machine vision systems[J]. Computers and electronics in agriculture, 2019, 156: 585-605.

[33] Zha H, Miao Y, Wang T, et al. Improving unmanned aerial vehicle remote sensing-based rice nitrogen nutrition index prediction with machine learning[J]. Remote Sensing, 2020, 12(2): 215.

[34] Duan B, Liu Y, Gong Y, et al. Remote estimation of rice LAI based on fourier spectrum texture from UAV image[J]. Plant Methods, 2019, 15(1): 1-12.

[35] Mao H, Meng J, Ji F, et al. Comparison of machine learning regression algorithms for cotton leaf area index retrieval using Sentinel-2 spectral bands[J]. Applied Sciences, 2019, 9(7): 1459.

[36] Cao J, Zhang Z, Tao F, et al. Integrating Multi-Source Data for Rice Yield Prediction across China using Machine Learning and Deep Learning Approaches[J]. Agricultural and Forest Meteorology, 2021, 297: 108275.

[37] Araújo M C U, Saldanha T C B, Galvao R K H, et al. The successive projections algorithm for variable selection in spectroscopic multicomponent analysis[J]. Chemometrics and Intelligent Laboratory Systems, 2001, 57(2): 65-73.

[38] Li H, Liang Y, Xu Q, et al. Key wavelengths screening using competitive adaptive reweighted sampling method for multivariate calibration[J]. Analytica chimica acta, 2009, 648(1): 77-84.

[39] 郭建彪，馬新明，時(shí)雷，等. 冬小麥葉面積指數(shù)的品種差異性與高光譜估算研究[J]. 麥類(lèi)作物學(xué)報(bào)，2018，38(3)：340-347.

Guo Jianbiao, Ma Xinming, Shi Lei, et al. Variety variation and hyperspectral estimate model of leaf area index of winter wheat[J]. Journal of Triticeae Crops, 2018, 38(3): 340-347. (in Chinese with English abstract)

[40] 李嵐?jié)?，李靜，明金，等. 冬油菜葉面積指數(shù)高光譜監(jiān)測(cè)最佳波寬與有效波段研究[J]. 農(nóng)業(yè)機(jī)械學(xué)報(bào)，2018，49(2)：156-165.

Li Lantao, Li Jing, Ming Jin, et al. Selection optimization of hyperspectral bandwidth and effective wavelength for predicting leaf area index in winter oilseed rape[J]. Transactions of the Chinese Society for Agricultural Machinery, 2018, 49(2): 156-165. (in Chinese with English abstract)

[41] 程雪，賀炳彥，黃耀歡，等. 基于無(wú)人機(jī)高光譜數(shù)據(jù)的玉米葉面積指數(shù)估算[J]. 遙感技術(shù)與應(yīng)用，2019，34(4)：775-784.

Cheng Xue, He Bingyan, Huang Yaohuan, et al. Estimation of corn leaf area index based on UAV hyperspectral image[J]. Remote Sensing Technology and Application, 2019, 34(4): 775-784. (in Chinese with English abstract)

[42] Baldocchi D D, Ryu Y, Dechant B, et al. Outgoing near‐infrared radiation from vegetation scales with canopy photosynthesis across a spectrum of function, structure, Physiological Capacity, and Weather[J]. Journal of Geophysical Research: Biogeosciences, 2020, 125(7): 1-17.

[43] Li L, Lin D, Wang J, et al. Multivariate analysis models based on full spectra range and effective wavelengths using different transformation techniques for rapid estimation of leaf nitrogen concentration in winter wheat[J]. Frontiers in plant science, 2020, 11: 755.

[44] Ihuoma S O, Madramootoo C A. Sensitivity of spectral vegetation indices for monitoring water stress in tomato plants[J]. Computers and Electronics in Agriculture, 2019, 163: 104860.

[45] 王玉娜，李粉玲，王偉東，等. 基于連續(xù)投影算法和光譜變換的冬小麥生物量高光譜遙感估算[J]. 麥類(lèi)作物學(xué)報(bào)，2020，40(11)：1389-1398.

Wang Yuna, Li Fenling, Wang Weidong, et al. Hyper-spectral remote sensing estimation of shoot biomass of winter wheat based on SPA and transformation spectra[J]. Journal of Triticeae Crops, 2020, 40(11): 1389-1398. (in Chinese with English abstract)

[46] Li X, Zhang Y, Bao Y, et al. Exploring the best hyperspectral features for LAI estimation using partial least squares regression[J]. Remote Sensing, 2014, 6(7): 6221-6241.

[47] 孫晶京，楊武德，馮美臣，等. 基于隨機(jī)蛙跳和支持向量機(jī)的冬小麥葉面積指數(shù)估算[J]. 山西農(nóng)業(yè)大學(xué)學(xué)報(bào)：自然科學(xué)版，2020，40(5)：120-128.

Sun Jingjing, Yang Wude, Feng Meichen, et al. Estimation of winter wheat leaf area index based on random leapfrog and support vector regression approach[J]. Journal of Shanxi Agricultural University: Natural Science Edition, 2020, 40(5): 120-128. (in Chinese with English abstract)

[48] Ren G, Wang Y, Ning J, et al. Highly identification of keemun black tea rank based on cognitive spectroscopy: Near infrared spectroscopy combined with feature variable selection[J]. Spectrochimica Acta Part A: Molecular and Biomolecular Spectroscopy, 2020, 230: 118079.

[49] Han L, Yang G, Dai H, et al. Modeling maize above-ground biomass based on machine learning approaches using UAV remote-sensing data[J]. Plant Methods, 2019, 15(1): 1-19.

[50] Lu N, Zhou J, Han Z, et al. Improved estimation of aboveground biomass in wheat from RGB imagery and point cloud data acquired with a low-cost unmanned aerial vehicle system[J]. Plant Methods, 2019, 15(1): 1-16.

[51] Wang X, Miao Y, Dong R, et al. Machine learning-based in-season nitrogen status diagnosis and side-dress nitrogen recommendation for corn[J]. European Journal of Agronomy, 2021, 123: 126193.

[52] 田明璐，班松濤，常慶瑞，等. 基于低空無(wú)人機(jī)成像光譜儀影像估算棉花葉面積指數(shù)[J]. 農(nóng)業(yè)工程學(xué)報(bào)，2016，32(21)：102-108.

Tian Minglu, Ban Songtao, Changqingrui, et al. Use of hyperspectral images from UAV-based imaging spectroradiometer to estimate cotton leaf area index[J]. Transactions of the Chinese Society of Agricultural Engineering (Transactions of the CSAE), 2016, 32(21): 102-108. (in Chinese with English abstract).

[53] Chen P. Cotton Leaf Area Index Estimation Using Unmanned Aerial Vehicle Multi-Spectral Images[C]. IGARSS 2019-2019 IEEE International Geoscience and Remote Sensing Symposium. IEEE, 2019: 6251-6254.

[54] Paul A, Ghosh S, Das A K, et al. A review on agricultural advancement based on computer vision and machine learning[M]. Emerging Technology in Modelling and Graphics. Springer, Singapore, 2020: 567-581.

Monitoring of cotton leaf area index using machine learning

Ma Yiru, Lyu Xin, Yi Xiang, Ma Lulu, Qi Yaqin, Hou Tongyu, Zhang Ze※

(/,832003,)

Leaf area index (LAI) is one of the most important indicators that characterize canopy structure and growth of crops. LAI changes can therefore greatly contribute to the variable rate fertilization of cotton. It is of great significance to monitor LAI quickly, accurately, and non-destructively, thereby guiding crop fertilization in modern agriculture. The traditional LAI monitoring relies mainly on manual sampling with high labor intensity and time-consuming. Furthermore, the lagging data cannot meet the needs of real-time monitoring. Most studies on crop LAI have also been made using remote sensing in recent years, such as hand-held spectrometers, unmanned aerial vehicles, and satellites. Nevertheless, the near-earth surface spectrum cannot be used to continuously and rapidly monitor at the spatial scale, due to the limited shooting range and the weight of the instrument. Satellite images are mostly used for the plant LAI monitoring at forest or large regional scale, particularly on the resolution of 10-60m. Alternatively, an Unmanned Aerial Vehicle (UAV) has the potential to fast capture high resolution images repeatedly, suitable for accurate crop monitoring of small plots. Many efforts have been made to monitor the LAI of wheat, rice, corn and others using spectral images under UAVs. Since spectral technology can monitor timely and dynamically, and in macro mode, the resulting LAI spectral data really determines the vegetation index. As such, the hyperspectral reflectance of plant canopy can provide much richer information of vegetation characteristics, compared with vegetation index. However, a large amount of hyperspectral data under UAVs normally presents data redundancy and high multicollinearity. Reasonable spectral transformation can also be utilized to remove the background and noise of hyperspectral data. Correspondingly, machine learning has widely been applied to crop growth monitoring for deep information in data, particularly combined with remote sensing. Great ability of learning and prediction can be achieved using the partial least squares (PLS) model (an extension of multicollinearity model), Support Vector Machine (SVM), and Random Forest (RF), in order to reduce the collinearity between variables in different ways. In this study, the UAV hyperspectral data was preprocessed using the First Derivative (FDR), the Second Derivative (SDR), Savitzky-Golay(SG) smoothing, and Multiple Scatter Correction (MSC) under the plot experiments of different varieties and nitrogen treatments. Sensitive bands were also selected using the Pearson correlation coefficient, Successive Projections Algorithm (SPA), Shuffled Frog Leaping Algorithm (SFLA), and Competitive Adaptive Reweighting (CARS). A cotton LAI monitoring model was finally constructed to calculate the reflectance of selected bands using the Partial Least Square Regression(PLSR), Support Vector Regression (SVR), and Random Forest Regression (RFR). The results showed that the canopy spectra of different LAI were significantly different from 760-1000 nm, where there was a significant correlation between the canopy spectrum and LAI. The sensitive response band of LAI in the cotton canopy was concentrated in the visible light (400-780 nm) and near-infrared (after 900 nm). The highest precision and stability were achieved in the RFR model under each pretreatment for LAI monitoring. Among them, the FDR-SFLA-RFR model performed the best, where the determination coefficient, Root Mean Square Error (RMSE), and relative RMSE for the modeling dataset were 0.74, 1.648 3, and 26.39%, respectively. In the verification dataset, the determination coefficient, RMSE and relative RMSE were 0.67, 1.622 0, and 25.97%, respectively. Consequently, the optimal estimation model can be rationally selected to represent the UAV spectral reflectance of the canopy using various pretreatments, band selecting, and modeling. The findings can provide the potential basis to accurately manage the variable fertilization in cotton fields.

cotton; UAV; hyperspectral; machine learning; leaf area index

馬怡茹，呂新，易翔，等. 基于機(jī)器學(xué)習(xí)的棉花葉面積指數(shù)監(jiān)測(cè)[J]. 農(nóng)業(yè)工程學(xué)報(bào)，2021，37(13)：152-162.

10.11975/j.issn.1002-6819.2021.13.018 http://www.tcsae.org

Ma Yiru, Lyu Xin, Yi Xiang, et al. Monitoring of cotton leaf area index using machine learning[J]. Transactions of the Chinese Society of Agricultural Engineering (Transactions of the CSAE), 2021, 37(13): 152-162. (in Chinese with English abstract) doi：10.11975/j.issn.1002-6819.2021.13.018 http://www.tcsae.org

2021-01-07

2021-06-10

兵團(tuán)重點(diǎn)領(lǐng)域科技攻關(guān)計(jì)劃（2020AB005）；兵團(tuán)重大科技計(jì)劃項(xiàng)目（2018AA004）

馬怡茹，研究方向?yàn)檗r(nóng)業(yè)信息化。Email：mayiru@stu.shzu.edu.cn

張澤，博士，副教授，碩士生導(dǎo)師，研究方向?yàn)檗r(nóng)業(yè)信息化技術(shù)及應(yīng)用。Email：zhangze1227@163.com

10.11975/j.issn.1002-6819.2021.13.018

S147.2

A

1002-6819(2021)-13-0152-11