Citrus Huanglongbing Terminator: How Hyperspectral Technology Achieves Precise Prevention and Control in Orchards

當超市貨(huò)架(jià)上(shàng)飽滿的臍橙閃(shǎn)爍著誘人的橙(chéng)紅色(sè)，很少有人(rén)知(zhī)道這(zhè)份甜(tián)蜜(mì)背(bèi)後(hòu)潛伏(fú)著一場持(chí)續百年的“柑橘世(shì)界大戰"。黃龍病，柑(gān)橘產業的(dí)頭號威脅，被(bèi)稱(chēng)為柑(gān)橘(jú)的“癌(ái)症(zhèng)"，一旦感(gǎn)染隻(zhī)能砍樹。該(gāi)病症狀最早(zǎo)在18世(shì)紀(jì)被發(fā)現，我(wǒ)國1919年(nián)開始(shǐ)報(bào)告(gào)此病。自2021年(nián)起(qǐ)，廣(guǎng)西(xī)柑(gān)桔(jié)產區(qū)連(lián)續兩年遭受(shòu)木虱疫(yì)害(hài)，果園(yuán)普遍(biàn)感(gǎn)染黃龍病(bìng)，導(dǎo)致(zhì)葉片黃(huáng)化(huà)和(hé)果實(shí)畸(jī)變(biàn)。

麵(miàn)對(duì)葉(yè)片黃(huáng)化(huà)，果(guǒ)實(shí)畸變的染病(bìng)果(guǒ)樹(shù)，傳統(tǒng)防(fáng)控如同“盲(máng)人摸(mō)象(xiàng)"——人(rén)工巡查工作量(liáng)大效率(shuài)低(dī)，常錯過防治(zhì)時機(jī)，而噴灑農藥(yào)和(hé)砍伐病樹也(yě)未(wèi)能解決問題(tí)。如(rú)今，通(tōng)過高光譜遙(yáo)感(gǎn)技(jì)術(shù)，在葉片(piàn)尚未泛(fàn)黃(huáng)時(shí)識(shí)別黃(huáng)龍病，提前把(bǎ)握(wò)防控窗口期(qī)。這(zhè)串隱藏(cáng)在(zài)光(guāng)譜(pǔ)波段裏(lǐ)的“柑橘密碼"，正在重新定義人(rén)類與病(bìng)害的(dí)博(bó)弈(yì)規則。

When plump navel oranges flash their enticing orange-red color on supermarket shelves, few realize that this sweetness is overshadowed by a century-long "World War of Citrus." Huanglongbing (HLB), the number one threat to the citrus industry, is often referred to as the “cancer" of citrus; once infected, the trees must be cut down. The symptoms of this disease were first discovered in the 18th century, and it was first reported in China in 1919. Since 2021, the citrus-growing regions of Guangxi have suffered from severe infestations by the Asian citrus psyllid for two consecutive years, leading to widespread HLB infection that results in yellowing leaves and deformed fruit.

Faced with infected trees exhibiting yellowing leaves and deformities, traditional control methods resemble "blind men trying to touch an elephant"—manual inspections are labor-intensive and inefficient, often missing critical prevention opportunities, while pesticide spraying and tree removal have not effectively resolved the issue. Nowadays, using hyperspectral remote sensing technology, HLB can be identified before the leaves turn yellow, allowing for proactive control measures during the crucial prevention window. This hidden “citrus code" embedded in the spectral bands is redefining the rules of engagement between humans and disease.

當無人(rén)機搭(dā)載400~1000nm波段的高光(guāng)譜相機掠過(guò)果園，每(měi)片(piàn)葉(yè)子都會留下(xià)光(guāng)譜(pǔ)“指紋"。由於(yú)患(huàn)病(bìng)葉(yè)片的光合(hé)作用受(shòu)到(dào)抑製(zhì)，並(bìng)且(qiě)含水(shuǐ)量降低，其(qí)在可見光(guāng)波(bō)段(duàn)的葉綠(lǜ)素(sù)反射區(qū)和(hé)O-H伸(shēn)縮振(zhèn)動(dòng)區與健康(kāng)葉片(piàn)之(zhī)間存(cún)在(zài)顯著差異。

在(zài)一些前(qián)期(qī)驗證實驗中(zhōng)，某科(kē)研(yán)團(tuán)隊(duì)采集了健(jiàn)康葉(yè)片(piàn)及不同病害(hài)程(chéng)度(dù)的柑(gān)橘(jú)葉(yè)片，使用可見-近(jìn)紅外光(guāng)譜波段進(jìn)行反射率(shuài)測量(liáng)，並重(zhòng)點(diǎn)關(guān)注450~800nm區(qū)間(jiān)。經(jīng)過有(yǒu)效(xiào)數據(jù)篩選，該(gāi)研究通(tōng)過最小二(èr)乘支(zhī)持向量(liáng)機(jī)（LS-SVM）和隨(suí)機森林（RF）算法建(jiàn)立了多種快速分(fēn)類(lèi)模(mó)型(xíng)，發現(xiàn)模型的(dí)分類(lèi)準(zhǔn)確(què)率分別(bié)在92.5%~95%，92.5%~97%。這(zhè)樣的高效(xiào)檢(jiǎn)測手段大大(dà)提高(gāo)了(liǎo)病(bìng)害的早(zǎo)期識別率(shuài)，為果(guǒ)農提供(gōng)了(liǎo)及時防治的依(yī)據(jù)。

When drones equipped with hyperspectral cameras ranging from 400 to 1000 nm fly over orchards, each leaf leaves behind a unique spectral "fingerprint." Infected leaves show significant differences in chlorophyll reflectance in the visible light range and O-H stretching vibration zones compared to healthy leaves due to suppressed photosynthesis and reduced moisture content.

In a series of preliminary validation experiments, a research team collected healthy leaves and leaves with varying levels of disease severity, using the visible-near-infrared spectral range to measure reflectance, focusing primarily on the 450-800 nm range. Following effective data filtering, the study established multiple rapid classification models through least squares support vector machine (LS-SVM) and random forest (RF) algorithms, achieving classification accuracies ranging from 92.5% to 95% and 92.5% to 97%. Such efficient detection methods significantly improved the early identification rate of the disease, providing timely preventive measures for farmers.

健(jiàn)康葉(yè)片(piàn)和(hé)患病(bìng)葉片（不同患(huàn)病程度）的(dí)光譜曲綫(xiàn)

Spectral curves of healthy leaves and infected leaves (with varying degrees of disease severity)

華南(nán)一個科研(yán)團隊使用(yòng)了無人機載(zǎi)高(gāo)光(guāng)譜成像(xiàng)係統收集高光譜圖像(xiàng)，該(gāi)高光(guāng)譜成像儀(yí)波長(cháng)範圍(wéi)是450~950nm，通道數為125。經過(guò)光譜(pǔ)預處(chǔ)理和特征工程(chéng)，應(yīng)用了連續投(tóu)影算法（SPA）來提(tí)取對柑(gān)橘(jú)患病(bìng)植株分(fēn)類影響最大的特征(zhēng)波長組合(hé)，從125個(gè)波(bō)段中鎖定了10個(gè)關(guān)鍵波段(duàn)。這些波段如同破解(jiě)黃龍(lóng)病(bìng)的“摩爾(ěr)斯電(diàn)碼(mǎ)"，高效地(dì)傳達了柑橘(jú)植株(zhū)病蟲害的信息。

在模(mó)型構(gòu)建方麵，研(yán)究(jiū)人員基(jī)於全(quán)波段(duàn)數據，應用了(liǎo)BP神經(jīng)網絡和(hé)XgBoost算法進行(háng)分(fēn)類(lèi)評估，同時基於(yú)特征(zhēng)波(bō)段使(shǐ)用邏(luó)輯回(huí)歸(guī)和支持(chí)向(xiàng)量機（SVM）算(suàn)法建立(lì)分類模(mó)型。

結果顯示，基於(yú)全(quán)波段(duàn)的BP神(shén)經網絡(luò)和XgBoost算法的分類模型分類準確率均超過95%。基(jī)於(yú)特征(zhēng)波段（698nm和(hé)762nm）的邏(luó)輯回歸和SVM建立(lì)的模型實現了93.00%和(hé)96.00%的患病(bìng)樣品分類準(zhǔn)確(què)率(shuài)。這證(zhèng)明(míng)了特(tè)征波長(cháng)組合的有(yǒu)效(xiào)性(xìng)，為柑(gān)橘種植園(yuán)的(dí)病蟲害監(jiān)測和精(jīng)準防治(zhì)提供了(liǎo)一定的數(shù)據(jù)和理(lǐ)論支(zhī)撐(chēng)。

A research team in South China utilized a drone-mounted hyperspectral imaging system to collect hyperspectral images, with the hyperspectral imager covering a wavelength range of 450-950 nm and comprising 125 channels. After spectral preprocessing and feature engineering, they applied a successive projection algorithm (SPA) to extract the most influential combinations of spectral wavelengths for classifying infected citrus plants, narrowing down to 10 key bands from 125. These bands resemble the "Morse code" for decoding HLB, efficiently conveying information about the disease and pests affecting citrus plants.

In model construction, researchers applied BP neural networks and XgBoost algorithms for classification assessment based on full-band data, while also using logistic regression and support vector machine (SVM) algorithms to establish classification models based on feature bands.

The results showed that classification models based on the full-band BP neural networks and XgBoost algorithms exceeded 95% classification accuracy. Models based on feature bands (698 nm and 762 nm), developed using logistic regression and SVM, achieved classification accuracies of 93.00% and 96.00% for infected samples. This confirms the effectiveness of the feature wavelength combinations, providing data and theoretical support for pest monitoring and precise prevention in citrus plantations.

華南科研(yán)團隊的試(shì)驗(yàn)區(qū)域(yù)及樣(yàng)本標(biāo)注
：粉，紅，藍，黃，白圓圈標記分(fēn)別代表不(bù)同(tóng)患病程度和患病未定(dìng)級的(dí)黃(huáng)龍病植株，三(sān)角形標記(jì)為缺(quē)素(sù)植(zhí)株；沒(méi)有標記(jì)的植株(zhū)為(wéi)健康(kāng)植(zhí)株

Experimental area and sample labeling by the research team in South China: The pink, red, blue, yellow, and white circular markers represent citrus plants with different degrees of Huanglongbing severity and those whose condition has not yet been classified; the triangular markers indicate nutrient-deficient plants; unmarked plants are healthy.

中(zhōng)美兩所高校(xiào)展開合(hé)作(zuò)，采用(yòng)無人機(jī)搭載(zǎi)高光(guāng)譜和(hé)多(duō)光(guāng)譜成像係統，獲(huò)得光(guāng)譜(pǔ)遙感(gǎn)數據(jù)，快(kuài)速(sù)識(shí)別感(gǎn)染(rǎn)黃(huáng)龍病的柑(gān)橘植株(zhū)。該(gāi)團(tuán)隊(duì)將(jiāng)航拍獲取(qǔ)的(dí)光(guāng)譜數(shù)據(jù)與農田(tián)和實驗室的(dí)地麵(miàn)驗證結(jié)果(guǒ)相結(jié)合(hé)，顯示出(chū)航拍的光譜數據(jù)能夠(gòu)有(yǒu)效(xiào)地區分(fēn)健康植(zhí)株與感(gǎn)染(rǎn)黃龍病的植株(zhū)，準(zhǔn)確(què)率最(zuì)高可達90%。

Two universities from China and the United States collaborated using drones equipped with hyperspectral and multispectral imaging systems to obtain spectral remote sensing data for rapid identification of citrus plants infected with HLB. This team combined aerial spectral data with ground-truth validation results from fields and laboratories, demonstrating that aerial spectral data effectively distinguish between healthy plants and those infected with HLB, achieving accuracies of up to 90%.

左圖
：美國(guó)佛羅裏達的(dí)黃(huáng)龍(lóng)病(bìng)感染區，右圖(tú)
：研究中使用的高光(guāng)譜與多光(guāng)譜(pǔ)傳感器

Left figure: Huanglongbing infection area in Florida, USA; Right figure: Hyperspectral and multispectral sensors used in the study.

從古詩(shī)詞(cí)中描繪(huì)的“柑橘正熟，金(jīn)果(guǒ)盈(yíng)枝(zhī)"的豐(fēng)收(shōu)畫(huà)麵，到(dào)今(jīn)天光譜(pǔ)儀(yí)中(zhōng)的圖譜(pǔ)曲(qū)綫(xiàn)，人(rén)類與作物(wù)的對話(huà)從未停(tíng)止(zhǐ)。那些舞動(dòng)的光譜曲綫，不僅是科技對抗(kàng)病(bìng)害的利劍，更承(chéng)載著我們(mén)對土地最深的敬畏。或許在不遠(yuǎn)的(dí)未(wèi)來，每顆(kē)柑橘都(dū)將(jiāng)擁(yōng)有自己的“光譜(pǔ)證件(jiàn)"——而這，正(zhèng)是科(kē)技(jì)賦予農業(yè)的詩意(yì)浪漫(màn)。

From ancient poetry depicting the bountiful harvest of “ripe citrus, golden fruits hanging from branches" to the spectral curves represented in spectrometers today, the dialogue between humans and crops has never ceased. Those dancing spectral curves are not only the sword of technology against diseases but also embody our deep respect for the land. Perhaps soon, each citrus fruit will have its own "spectral ID"—a poetic romance of agriculture bestowed by technology.

案例(lì)來(lái)源 / Source

1.Bai Ziqin, Zhou Changyong,  The Research Progress of Citrus Huanglongbing on Pathogen Diversity and Epidemiology, Chinese Agricultural Science Bulletin, 2012,28(1):133-137.

2.QIU Hong-lin, LIU Tian-yuan, KONG Li-li, YU Xin-na, WANG Xian-da, HUANG Mei-zhen. Rapid Detection of Citrus Huanglongbing Based on Extraction of Characteristic Wavelength of Visible Spectrum and Classification Algorithm[J]. Spectroscopy and Spectral Analysis, 2024,44(6): 1518-1525.

3.Li X, Lee WS, Li M, et al. Spectral difference analysis and airborne imaging classification for citrus greening infected trees Computers and Electronics in Agriculture.. 2012 Apr;83:32-46.

4.DENG Xiaoling, ZENG Guoliang, ZHU Zihao, et al. Classification and feature band extraction of diseased citrus plants based on UAV hyperspectral remote sensing[J]. Journal of South China Agricultural University, 2020, 41(6): 100-108.

5.Xiuhua Li, Won Suk Lee, Minzan Li, Reza Ehsani, Ashish Ratn Mishra, Chenghai Yang, Robert L. Mangan, Spectral difference analysis and airborne imaging classification for citrus greening infected trees, Computers and Electronics in Agriculture, Volume 83,2012, Pages 32-46.