From Forests to Cities: How Does Hyperspectral Imaging Enable Tree Species Identification?

高光(guāng)譜(pǔ)成(chéng)像技術在樹(shù)種識別領域(yù)的(dí)應(yīng)用日(rì)益廣(guǎng)泛，它通(tōng)過(guò)捕捉樹木在多(duō)個(gè)窄波段(duàn)上的光譜(pǔ)信息，實現(xiàn)對樹(shù)種的精(jīng)確(què)分(fēn)類和識(shí)別(bié)，在(zài)森林資源(yuán)管理
，城市綠(lǜ)化規劃和生(shēng)態(tài)環境(jìng)保護等(děng)方(fāng)麵(miàn)具有重要意義(yì)，為相關(guān)工(gōng)作(zuò)提供(gōng)了(liǎo)關鍵技術(shù)支(zhī)撐。

下麵是高光譜(pǔ)成像技術在樹種識(shí)別的(dí)應(yīng)用場景(jǐng)。

Hyperspectral imaging technology is increasingly being applied in the field of tree species identification. By capturing spectral information from trees across multiple narrow bands, it enables accurate classification and identification of species. This technology plays a significant role in forest resource management, urban greening planning, and ecological environment protection, providing critical technical support for related tasks.

Below are the application scenarios of hyperspectral imaging technology in tree species identification.

1. 森(sēn)林(lín)資(zī)源(yuán)調查與監(jiān)測(cè) / Forest Resource Inventory and Monitoring

·樹種(zhǒng)分類與分布：高光(guāng)譜數據可以用(yòng)於識別和分(fēn)類森林中的不(bù)同樹種(zhǒng)，生成樹(shù)種分布圖，為(wéi)森林資(zī)源(yuán)管理提(tí)供基礎數(shù)據(jù)。

在巴西大西(xī)洋(yáng)森林的(dí)研(yán)究(jiū)中，研(yán)究(jiū)者結(jié)合無人(rén)機高光譜(pǔ)數據(jù)與激光雷達（LiDAR）數據(jù)，對8種(zhǒng)上(shàng)層樹冠(guān)樹種進行(háng)分(fēn)類，通過(guò)主(zhǔ)成分分析(xī)（PCA）處理所(suǒ)有(yǒu)特征後，分類總(zǒng)體(tǐ)精度(dù)達(dá)到(dào)76%，為該退化森(sēn)林的物種分布(bù)監測提供了有(yǒu)效數據(jù)支撐。

·Tree Species Classification and Distribution: Hyperspectral data can be used to identify and classify different tree species in forests, generating species distribution maps that serve as foundational data for forest resource management.

In a study of the Atlantic Forest in Brazil, researchers combined UAV-based hyperspectral data with LiDAR data to classify eight canopy tree species. After processing all features using Principal Component Analysis (PCA), an overall classification accuracy of 76% was achieved, providing effective data support for monitoring species distribution in this degraded forest.

各種(zhǒng)樹(shù)的平均光(guāng)譜 / Mean spectra for each tree species

·森林(lín)健(jiàn)康評估：通過分析(xī)樹(shù)木的光譜特征，可(kě)以評(píng)估樹(shù)木(mù)的生長狀(zhuàng)況和健康程(chéng)度(dù)，及時(shí)發現病蟲害和環境脅迫(pò)，為森林(lín)保(bǎo)護(hù)提(tí)供(gōng)預(yù)警信(xìn)息。

中國(guó)地質(zhì)調查局在湖(hú)北宜城(chéng)的研(yán)究中(zhōng)，采(cǎi)用無(wú)人機(jī)高(gāo)光(guāng)譜(pǔ)數據（400~1000nm，270個(gè)光譜波段），結(jié)合(hé)歸一化植被指數（NDVI）
，類胡蘿(luó)卜素反(fǎn)射指數（CRI）和(hé)水波段指數（WBI），構建(jiàn)“寬帶綠度(dù)指數(shù)-葉綠(lǜ)素指(zhǐ)數(shù)-冠(guān)層含(hán)水量/光合(hé)能(néng)力指(zhǐ)數"的(dí)綜(zōng)合評估(gū)體(tǐ)係(xì)，實(shí)現了(liǎo)森林(lín)樹(shù)木健康(kāng)狀況的定性與定(dìng)量評估，結果(guǒ)與實地(dì)觀(guān)測及(jí)假彩色(sè)合成圖(tú)像特征(zhēng)高度(dù)一致(zhì)。

·Forest Health Assessment: By analyzing the spectral characteristics of trees, their growth conditions and health status can be evaluated, enabling timely detection of pests, diseases, and environmental stressors, thereby offering early warning information for forest protection.

In a study conducted by the China Geological Survey in Yicheng, Hubei, UAV-based hyperspectral data (400-1000nm, 270 spectral bands) was used in combination with vegetation indices such as NDVI, CRI, and WBI to construct a comprehensive evaluation system based on "broadband greenness index–chlorophyll index–canopy water content/photosynthetic capacity index." This system achieved both qualitative and quantitative assessments of forest tree health, with results highly consistent with field observations and false-color composite imagery.

(a) 真彩色影(yǐng)像(xiàng)與樹種識別(bié)分類；(b) 假彩(cǎi)色影像(xiàng)與健(jiàn)康評估

(a) True color image and tree species recognition class; (b) False color image and health assessment

·生物多(duō)樣(yàng)性研究：高(gāo)光譜(pǔ)數據可(kě)以用於研究(jiū)森林生態係統的生物多樣(yàng)性，了(liǎo)解不(bù)同(tóng)樹種(zhǒng)的生(shēng)態(tài)功(gōng)能和(hé)相互(hù)關(guān)係，為(wéi)生(shēng)態保護提供科學依據(jù)。

·Biodiversity Research: Hyperspectral data can be applied to study biodiversity in forest ecosystems, helping to understand the ecological functions and interrelationships of different tree species, thereby providing a scientific basis for ecological conservation.

·林木(mù)生(shēng)長參(cān)數(shù)反演：利(lì)用高光(guāng)譜數(shù)據可(kě)以反演(yǎn)林(lín)木的(dí)葉(yè)麵(miàn)積(jī)指數
，生(shēng)物(wù)量(liáng)等(děng)生(shēng)長參數，為林(lín)木(mù)生長模型的建(jiàn)立和優化(huà)提供(gōng)數據支(zhī)持。

在東(dōng)北針闊混(hùn)交(jiāo)林研究(jiū)中，研究(jiū)者(zhě)通(tōng)過高光譜數(shù)據(jù)提(tí)取植被指(zhǐ)數，結合LiDAR獲取(qǔ)的樹(shù)高
，冠(guān)幅等結(jié)構參(cān)數(shù)，實現了林木葉(yè)麵(miàn)積指(zhǐ)數(shù)和(hé)生物(wù)量的精準(zhǔn)反(fǎn)演，為(wéi)該區(qū)域(yù)精準林業中林木(mù)生(shēng)長模(mó)型優(yōu)化提(tí)供了關鍵(jiàn)數據。值得注(zhù)意(yì)的是(shì)，在這項研究(jiū)中(zhōng)，高光(guāng)譜成像儀和(hé)LiDAR是(shì)分(fēn)別(bié)掛載在不同(tóng)的(dí)無人(rén)機上的。

·Inversion of Tree Growth Parameters: Hyperspectral data can be used to invert growth parameters such as leaf area index and biomass, supporting the establishment and optimization of tree growth models.

In a study on mixed coniferous-broadleaf forests in Northeast China, researchers extracted vegetation indices from hyperspectral data and combined them with structural parameters (e.g., tree height and crown width) obtained from LiDAR to achieve accurate inversion of leaf area index and biomass. This provided key data for optimizing tree growth models in precision forestry in the region. It is worth noting that in this study, the hyperspectral imager and LiDAR were mounted on different UAVs.

樹種專題(tí)圖(tú) / Thematic map of tree species

2. 城(chéng)市綠(lǜ)化規(guī)劃(huá)與(yǔ)管理 / Urban Greening Planning and Management

·城市樹(shù)種識別(bié)與分布：高光譜圖像可以用於識(shí)別(bié)城(chéng)市(shì)中的(dí)樹種(zhǒng)，了解城市(shì)綠(lǜ)化的(dí)樹(shù)種(zhǒng)構(gòu)成(chéng)和分布(bù)情況(kuàng)，為城市綠化規(guī)劃提(tí)供參(cān)考。

·城(chéng)市(shì)樹(shù)木健(jiàn)康監測(cè)：通過(guò)分(fēn)析(xī)城市樹(shù)木(mù)的(dí)光譜(pǔ)特征(zhēng)，可以(yǐ)評估城市(shì)樹木的生(shēng)長狀況和健(jiàn)康(kāng)程(chéng)度，及時(shí)發現病蟲害和環(huán)境脅(xié)迫，為城市樹木的養護管理提供指導(dǎo)。

香港(gǎng)理工大學一(yī)團隊(duì)利用高光譜(pǔ)圖(tú)像對城市樹(shù)種(zhǒng)進行了(liǎo)識(shí)別分類，2018年(nián)11月至2019年10月期間，在(zài)不(bù)同(tóng)季(jì)節對19個樹(shù)種的75棵城市樹木進(jìn)行(háng)了圖(tú)像采(cǎi)集，深度神(shén)經(jīng)網絡(luò)方(fāng)法在(zài)物(wù)種識(shí)別中達到了85%~96%的準(zhǔn)確(què)率(shuài)。不同物種(zhǒng)對健(jiàn)康狀況表(biǎo)現(xiàn)出不(bù)同(tóng)的(dí)光譜響應。

·Urban Tree Species Identification and Distribution: Hyperspectral imagery can be used to identify tree species in urban areas, helping to understand the composition and distribution of species in urban greening, thus providing references for urban greening planning.

·Urban Tree Health Monitoring: By analyzing the spectral characteristics of urban trees, their growth conditions and health status can be assessed, enabling timely detection of pests, diseases, and environmental stressors, thereby guiding maintenance and management efforts.

A team at The Hong Kong Polytechnic University used hyperspectral imagery to identify and classify urban tree species. From November 2018 to October 2019, images of 75 urban trees from 19 species were collected across different seasons. Deep neural network methods achieved an accuracy of 85%–96% in species identification. Different species exhibited distinct spectral responses to health conditions.

(a-d)為原(yuán)始(shǐ)圖像；(e-h)為(wéi)對應的掩(yǎn)蔽後圖像

Typified examples of masking canopies and homogenous regions: (a-d) are original images; (e-h) are corresponding masked images.

各輪實(shí)地數(shù)據(jù)采(cǎi)集中(zhōng)的(dí)不(bù)同(tóng)樹種平均冠(guān)層光(guāng)譜特征(zhēng)，樹(shù)種分別(bié)為(wéi)：(a) 相(xiāng)思(sī)樹(shù)（樣本(běn)量(liáng)N=6）；(b) 大(dà)葉合(hé)歡（N=3）；(c) 白(bái)楸（N=5）；(d) 榕樹(shù)（N=3）

Mean canopy spectral signature of different species in each round of in-situ data acquisition, the species are: (a) Acacia confuse (N = 6); (b) Albizia lebbeck (N = 3); (c) Mallotus paniculatus; (N = 5); (d) Ficus macrocarpa (N = 3). N indicates the number of tree samples for the corresponding species;

高(gāo)光(guāng)譜成(chéng)像技術為(wéi)樹(shù)種(zhǒng)識別提供了(liǎo)高(gāo)效
，精(jīng)確(què)的(dí)技術(shù)方案，它可以(yǐ)減(jiǎn)少人(rén)工調查的(dí)工作(zuò)量(liáng)
，獲(huò)取(qǔ)精細信(xìn)息
，為森林資源(yuán)管理(lǐ)
，城市(shì)綠化(huà)規(guī)劃和生態(tài)環(huán)境保護提(tí)供(gōng)科學(xué)依據和(hé)決(jué)策(cè)支持，應(yīng)用前景廣闊。

隨(suí)著技(jì)術發(fā)展，它(tā)將進(jìn)一(yī)步助(zhù)力林業(yè)與(yǔ)生(shēng)態(tài)領域(yù)的可持續發展，持(chí)續發揮核心支撐作(zuò)用。

作(zuò)為(wéi)高光譜的(dí)供(gōng)應商，愛博能提(tí)供(gōng)全麵(miàn)的產品(pǐn)綫(xiàn)，包(bāo)括全(quán)波(bō)段(duàn)的高光(guāng)譜相機
，無人機載高光譜(pǔ)成(chéng)像係統
，便攜式
，高(gāo)光譜(pǔ)實(shí)驗(yàn)室和(hé)顯微高(gāo)光(guāng)譜。歡迎(yíng)垂詢
！

Hyperspectral imaging technology provides an efficient and accurate technical solution for tree species identification. It reduces the workload of manual surveys, captures detailed information, and offers scientific basis and decision-making support for forest resource management, urban greening planning, and ecological environment protection. Its application prospects are broad.

With technological advancements, it will further contribute to the sustainable development of forestry and ecology, continuing to play a core supporting role.

As a supplier of hyperspectral solutions, ExponentSci provides a comprehensive product line, including full-band hyperspectral cameras, UAV-mounted hyperspectral imaging systems, portable systems, hyperspectral laboratories, and micro-hyperspectral imagers. Welcome to inquire!

案(àn)例來(lái)源(yuán) / Sources：

1. Zhong, H., Lin, W., Liu, H., Ma, N., Liu, K., Cao, R., Wang, T., & Ren, Z. (2022). Identification of tree species based on the fusion of UAV hyperspectral image and LiDAR data in a coniferous and broad-leaved mixed forest in Northeast China. Frontiers in Plant Science, 13, 964769.

2. Martins-Neto, R. P., Tommaselli, A., Imai, N., Honkavaara, E., Miltiadou, M., Moriya, E., & David, H. (2023). Tree species classification in a complex Brazilian tropical forest using hyperspectral and LiDAR data. Forests, 14(5), 945.

3. Zeng, G., Xu, J., Zhang, W., & Wang, B. (2023). Tree species identification and health assessment of forest sample plots based on UAV hyperspectral remote sensing technology. Journal of Physics: Conference Series, 2621(1), 012001.

4. Abbas, S., Peng, Q., Wong, M. S., Li, Z., Wang, J., Ng, K. T. K., Kwok, C. Y. T., & Hui, K. K. W. (2021). Characterizing and classifying urban tree species using bi-monthly terrestrial hyperspectral images in Hong Kong. ISPRS Journal of Photogrammetry and Remote Sensing, 177, 204–216.