基于光谱指数的琯溪蜜柚叶片钙素含量估测模型研究

doi:10.3864/j.issn.0578-1752.2025.07.006

摘要/Abstract

摘要：

【目的】构建基于光谱分析的蜜柚叶片钙（Ca）素含量估测模型，可为蜜柚叶片钙素含量的监测和快速无损诊断提供理论基础。【方法】分析提取蜜柚叶片原始光谱及一阶导数光谱特征波段和光谱特征指数（差值光谱指数（DSI）、比值光谱指数（RSI）和归一化光谱指数（NDSI）），构建蜜柚叶片钙素含量的单变量估测模型、偏最小二乘估测模型（PLS）、反向传播神经网络估测模型（BPNN）、随机森林估测模型（RF）和支持向量机估测模型（SVM），并评价和验证蜜柚叶片钙素含量的最优光谱估测模型。【结果】蜜柚叶片原始光谱和一阶导数光谱与钙素含量存在多波段显著相关，基于原始光谱和一阶导数光谱的相关系数，最大的波长分别为553、714 nm和528、699、602 nm。基于原始光谱和一阶导数光谱与钙素含量相关性较显著的光谱指数分别为DSI_790,1040、RSI_910,990、NDSI_900,990和NDSI′_350,580、DSI′_560,570、RSI′_350,580。以RSI_910,990、NDSI_900,990、NDSI′_350,580、DSI_790,1040、DSI′_560,570、RSI′_350,580、DSI′_528,602等光谱指数为自变量构建的多项式估测模型，决定系数R²较大（R²>0.60）。运用上述4种机器学习方法建立蜜柚叶片钙素含量高光谱估测模型，PLS、BPNN、RF和SVM 4种估测模型的R²分别为0.79、0.82、0.85和0.84，均方根误差（RMSE）分别为4.33、4.11、3.81和3.93，验证模型的R²分别为0.77、0.80、0.87和0.83，RMSE分别为4.50、4.28、3.67和3.90，估测模型的精确程度为RF>SVM>BPNN>PLS。【结论】蜜柚叶片钙素含量的4种模型进行精度对比分析表明，RF估测模型的预测性优于其他3种估测模型。该结果可为蜜柚叶片钙素含量快速诊断提供新方法以供参考。

关键词: 光谱指数, 估测模型, 高光谱, 蜜柚, 钙素

Abstract:

【Objective】By constructing the estimation model for calcium (Ca) content in honey pomelo leaves based on spectral analysis, it could provide a theoretical basis for monitoring and rapid non-destructive diagnosis of Ca content in honey pomelo leaves.【Method】The original spectral and first-order derivative spectral characteristic bands and spectral characteristic indices (difference spectral index (DSI), ratio spectral index (RSI), and normalized difference spectral index (NDSI)) were analyzed and extracted. Single variable estimation model, partial least squares estimation model (PLS), backpropagation neural network estimation model (BPNN), random forest estimation model (RF), and support vector machine estimation model (SVM) for honey pomelo leaf calcium content were established, and the optimal spectral estimation model for honey pomelo leaf calcium content was evaluated and verified. 【Result】There was a significant multi band correlation between the original spectrum and first-order derivative spectrum of pomelo leaves and calcium content. Based on the correlation coefficients of the original spectrum and first-order derivative spectrum, the maximum wavelengths were 553, 714 nm and 528, 699, 602 nm, respectively. The spectral indices with significant correlation between the original spectrum, first-order derivative of pomelo leaves and calcium content were DSI_790,1040, RSI_910,990, NDSI_900,990 and NDSI′_350,580, DSI′_560,570, RSI′_350,580. The polynomial estimation model constructed with spectral indices such as RSI_910,990, NDSI_900,990, NDSI′_350,580, DSI_790,1040, DSI′_560,570, RSI′_350,580, DSI′_528,602 as independent variables had relatively high determination coefficient R² (R²>0.60). A hyperspectral estimation model for calcium content in honey pomelo leaves was established using the above four machine learning methods. The R²of PLS, BPNN, RF and SVM estimation models were 0.79, 0.82, 0.85 and 0.84, respectively, and the root mean square errors (RMSE) were 4.33, 4.11, 3.81 and 3.93, respectively; the R² of the validation models were 0.77, 0.80, 0.87 and 0.83, respectively, and the RMSE were 4.50, 4.28, 3.67 and 3.90, respectively. The order of estimating the accuracy of the model was RF>SVM>BPNN>PLS.【Conclusion】The accuracy comparison analysis of four models for calcium content in honey pomelo leaves showed that the RF estimation model had better predictive performance than the other three estimation models. This result could provide a new method for rapid diagnosis of calcium content in honey pomelo leaves for reference.

Key words: spectral index, estimation model, hyperspectrum, honey pomelo, Calcium

栗方亮, 孔庆波, 张青. 基于光谱指数的琯溪蜜柚叶片钙素含量估测模型研究[J]. 中国农业科学, 2025, 58(7): 1321-1332.

LI FangLiang, KONG QingBo, ZHANG Qing. Research on the Estimation Model of Calcium Content in Guanxi Honey Pomelo Leaves Based on Spectral Index[J]. Scientia Agricultura Sinica, 2025, 58(7): 1321-1332.

0
/ / 推荐

导出引用管理器 EndNote|Reference Manager|ProCite|BibTeX|RefWorks

链接本文: https://www.chinaagrisci.com/CN/10.3864/j.issn.0578-1752.2025.07.006

https://www.chinaagrisci.com/CN/Y2025/V58/I7/1321

图/表 7

表1

图1

图2

图3

表2

表3

图4

参考文献 52

[1]	平和县统计局. 平和统计年鉴(2023). 2023: 40. http://www.pinghe.gov.cn/cms/html/phxrmzf/tjnj/index.html.
	PINGHE COUNTY STATISTICS BUREAU. Pinghe statistical yearbook(2023). 2023:40. http://www.pinghe.gov.cn/cms/html/phxrmzf/tjnj/index.html. (in Chinese)
[2]	栗方亮, 孔庆波, 张青. 基于高光谱的琯溪蜜柚叶片磷素含量估算模型研究. 中国农业科技导报, 2023, 25(1): 100-108. doi: 10.13304/j.nykjdb.2021.1002
	LI F L, KONG Q B, ZHANG Q. Estimation models of phosphorus contents in Guanxi honey pomelo leaves based on hyperspectral data. Journal of Agricultural Science and Technology, 2023, 25(1): 100-108. (in Chinese) doi: 10.13304/j.nykjdb.2021.1002
[3]	刘禹, 雷靖, 胡承孝, 谭启玲, 庄木来, 孙学成, 武松伟. 钙镁配施对琯溪蜜柚树体钙镁营养及果实产量和品质的影响. 中国南方果树, 2023, 52(3): 15-21.
	LIU Y, LEI J, HU C X, TAN Q L, ZHUANG M L, SUN X C, WU S W. Effects of combined application of calcium and magnesium on yield, quality and calcium and magnesium nutrients of ‘Guanxi’ pomelo. South China Fruits, 2023, 52(3): 15-21. (in Chinese)
[4]	陶晶霞, 王玉雯, 李晓娜, 张利军, 张建翔, 张华, 廖文强, 姜玉英, 吴良泉, 李延, 郭九信. 琯溪蜜柚地上部新生器官生物量和钙镁养分累积特征. 果树学报, 2024, 41(1): 101-112.
	TAO J X, WANG Y W, LI X N, ZHANG L J, ZHANG J X, ZHANG H, LIAO W Q, JIANG Y Y, WU L Q, LI Y, GUO J X. Accumulation dynamics of biomass, Ca and Mg nutrient in the aboveground newborn organs of Guanximiyou pomelo tree. Journal of Fruit Science, 2024, 41(1): 101-112. (in Chinese)
[5]	李清华, 王飞, 何春梅, 林诚, 钟少杰, 黄绿林. 平和琯溪蜜柚施肥现状调查分析. 南方农业学报, 2016, 47(12): 2059-2064.
	LI Q H, WANG F, HE C M, LIN C, ZHONG S J, HUANG L L. Investigation and analysis of fertilization status for Guanxi honey pomelo in Pinghe county. Journal of Southern Agriculture, 2016, 47(12): 2059-2064. (in Chinese)
[6]	陆芃希, 甘增光, 庄木来, 郭九信, 王平, 李延. 琯溪蜜柚园土壤钙素养分分析. 经济林研究, 2023, 41(1): 133-142, 195.
	LU P X, GAN Z G, ZHUANG M L, GUO J X, WANG P, LI Y. Analysis of soil calcium nutrition of Guanxi pomelo orchard. Non-wood Forest Research, 2023, 41(1): 133-142, 195. (in Chinese)
[7]	ALDON D, MBENGUE M, MAZARS C, GALAUD J P. Calcium signalling in plant biotic interactions. International Journal of Molecular Sciences, 2018, 19(3): 665.
[8]	LI J, CHEN J Z. Citrus fruit-cracking: causes and occurrence. Horticultural Plant Journal, 2017, 3(6): 255-260.
[9]	LU J S, YANG T C, SU X, QI H, YAO X, CHENG T, ZHU Y, CAO W X, TIAN Y C. Monitoring leaf potassium content using hyperspectral vegetation indices in rice leaves. Precision Agriculture, 2020, 21(2): 324-348.
[10]	GUO R. Simulation of soybean canopy nutrient contents by hyperspectral remote sensing. Applied Ecology and Environmental Research, 2017, 15(4): 1185-1198.
[11]	MAHAJAN G R, DAS B, MURGAOKAR D, HERRMANN I, BERGER K, SAHOO R N, PATEL K, DESAI A, MORAJKAR S, KULKARNI R M. Monitoring the foliar nutrients status of mango using spectroscopy-based spectral indices and PLSR-combined machine learning models. Remote Sensing, 2021, 13(4): 641.
[12]	李勋兰, 王武, 杨蕾, 韩国辉, 杨海健, 洪林. 基于高光谱的柑橘叶片钾含量快速诊断模型. 南方农业, 2019, 13(22): 37-40.
	LI X L, WANG W, YANG L, HAN G H, YANG H J, HONG L. Rapid diagnosis model of potassium content in Citrus leaves based on high spectrum. South China Agriculture, 2019, 13(22): 37-40. (in Chinese)
[13]	WANG M, ZHENG Q S, SHEN Q R, GUO S W. The critical role of potassium in plant stress response. International Journal of Molecular Sciences, 2013, 14(4): 7370-7390. doi: 10.3390/ijms14047370 pmid: 23549270
[14]	BRENNAN R F, BOLLAND M D A, RAMM R D. Changes in chemical properties of sandy duplex soils in 11 paddocks over 21 years in the low rainfall cropping zone of southwestern Australia. Communications in Soil Science and Plant Analysis, 2013, 44(12): 1885-1908.
[15]	ZÖRB C, SENBAYRAM M, PEITER E. Potassium in agriculture- status and perspectives. Journal of Plant Physiology, 2014, 171(9): 656-669.
[16]	OSCO L P, RAMOS A P M, FAITA PINHEIRO M M, MORIYA É A S, IMAI N N, ESTRABIS N, IANCZYK F, ARAÚJO F F, LIESENBERG V, D E CASTRO JORGE L A, et al. A machine learning framework to predict nutrient content in Valencia-orange leaf hyperspectral measurements. Remote Sensing, 2020, 12(6): 906.
[17]	邢东兴, 常庆瑞. 基于光谱分析的果树叶片微量元素含量估测研究: 以红富士苹果树为例. 西北农林科技大学学报(自然科学版), 2008, 36(11): 143-150.
	XING D X, CHANG Q R. Research on predicting the Fe, Mn, Cu, Zn contents in fruit trees' fresh leaves by spectral analysis: Red Fuji apple tree as an example. Journal of Northwest A&F University (Natural Science Edition), 2008, 36(11): 143-150. (in Chinese)
[18]	栗方亮, 孔庆波, 张青. 光谱技术在果树叶片营养诊断上的应用研究进展. 江西农业学报, 2024, 36(3): 22-26.
	LI F L, KONG Q B, ZHANG Q. Research progress in application of spectroscopic technology in nutritional diagnosis of fruit tree leaves. Acta Agriculturae Jiangxi, 2024, 36(3): 22-26. (in Chinese)
[19]	田旷达, 邱凯贤, 李祖红, 吕亚琼, 张秋菊, 熊艳梅, 闵顺耕. 近红外光谱法结合最小二乘支持向量机测定烟叶中钙、镁元素. 光谱学与光谱分析, 2014, 34(12): 3262-3266.
	TIAN K D, QIU K X, LI Z H, LÜ Y Q, ZHANG Q J, XIONG Y M, MIN S G. Determination of calcium and magnesium in tobacco by near-infrared spectroscopy and least squares--support vector machine. Spectroscopy and Spectral Analysis, 2014, 34(12): 3262-3266. (in Chinese)
[20]	MENESATTI P, ANTONUCCI F, PALLOTTINO F, ROCCUZZO G, ALLEGRA M, STAGNO F, INTRIGLIOLO F. Estimation of plant nutritional status by Vis-NIR spectrophotometric analysis on orange leaves [Citrus sinensis (L) Osbeck cv Tarocco]. Biosystems Engineering, 2010, 105(4): 448-454.
[21]	DIBI W G, BOSSON J, ZOBI I C, TIÉ B T, ZOUEU J T. Use of fluorescence and reflectance spectra for predicting okra (Abelmoschus esculentus) yield and macronutrient contents of leaves. Open Journal of Applied Sciences, 2017, 7(10): 537-558.
[22]	GALÜEZ-SOLA L, GARCÍA-SÁNCHEZ F, PÉREZ-PÉREZ J G, GIMENO V, NAVARRO J M, MORAL R, MARTÍNEZ-NICOLÁS J J, NIEVES M. Rapid estimation of nutritional elements on Citrus leaves by near infrared reflectance spectroscopy. Frontiers in Plant Science, 2015, 6: 571.
[23]	CUQ S, LEMETTER V, KLEIBER D, LEVASSEUR-GARCIA C. Assessing macro- (P, K, Ca, Mg) and micronutrient (Mn, Fe, Cu, Zn, B) concentration in vine leaves and grape berries of Vitis vinifera by using near-infrared spectroscopy and chemometrics. Computers and Electronics in Agriculture, 2020, 179: 105841.
[24]	CHEN S M, HU T T, LUO L H, HE Q, ZHANG S W, LI M Y, CUI X L, LI H X. Rapid estimation of leaf nitrogen content in apple-trees based on canopy hyperspectral reflectance using multivariate methods. Infrared Physics & Technology, 2020, 111: 103542.
[25]	WANG J, SHEN C W, LIU N, JIN X, FAN X S, DONG C X, XU Y C. Non-destructive evaluation of the leaf nitrogen concentration by in-field visible/near-infrared spectroscopy in pear orchards. Sensors, 2017, 17(3): 538.
[26]	OSCO L P, MARQUES RAMOS A P, SAITO MORIYA É A, DE SOUZA M, MARCATO J Jr, MATSUBARA E T, IMAI N N, CRESTE J E. Improvement of leaf nitrogen content inference in Valencia-orange trees applying spectral analysis algorithms in UAV mounted-sensor images. International Journal of Applied Earth Observation and Geoinformation, 2019, 83: 101907.
[27]	郭燕, 井宇航, 王来刚, 黄竞毅, 贺佳, 冯伟, 郑国清. 基于无人机影像特征的冬小麦植株氮含量预测及模型迁移能力分析. 中国农业科学, 2023, 56(5): 850-865. doi: 10.3864/j.issn.0578-1752.2023.05.004.
	GUO Y, JING Y H, WANG L G, HUANG J Y, HE J, FENG W, ZHENG G Q. UAV multispectral image-based nitrogen content prediction and the transferability analysis of the models in winter wheat plant. Scientia Agricultura Sinica, 2023, 56(5): 850-865. doi: 10.3864/j.issn.0578-1752.2023.05.004. (in Chinese)
[28]	栗方亮, 孔庆波, 张青. 基于光谱特征参数的琯溪蜜柚叶片叶绿素含量估算. 福建农业学报, 2021, 36(12): 1447-1456.
	LI F L, KONG Q B, ZHANG Q. Spectral measurements-based estimation for chlorophyll in Guanxi honey pomelo leaves. Fujian Journal of Agricultural Sciences, 2021, 36(12): 1447-1456. (in Chinese)
[29]	栗方亮, 孔庆波, 张青. 利用多种回归模型对比估算琯溪蜜柚叶片钾素含量. 热带作物学报, 2022, 43(6): 1191-1199. doi: 10.3969/j.issn.1000-2561.2022.06.012
	LI F L, KONG Q B, ZHANG Q. Comparative estimation of potassium contents in Guanxi honey pomelo leaves by multiple regression models. Chinese Journal of Tropical Crops, 2022, 43(6): 1191-1199. (in Chinese) doi: 10.3969/j.issn.1000-2561.2022.06.012
[30]	鲁如坤. 土壤农业化学分析方法. 北京: 中国农业科技出版社, 2000:318-320.
	LU R K. Methods for agricultural chemical analysis of soil. Beijing: China Agricultural Science and Technology Press, 2000:318-320. (in Chinese)
[31]	雷靖, 孙冠利, 庄木来, 朱东煌, 李潇彬, 谭启玲, 胡承孝. 琯溪蜜柚园土壤肥力和叶片营养随树龄的变化. 中国土壤与肥料, 2019(1): 166-172.
	LEI J, SUN G L, ZHUANG M L, ZHU D H, LI X B, TAN Q L, HU C X. The changes of soil fertility and leaf nutrition of Guanxi pomelo orchards with tree-age. Soil and Fertilizer Sciences in China, 2019(1): 166-172. (in Chinese)
[32]	朱白雪. ‘新新2号’核桃叶片营养元素含量光谱估算模型[D]. 乌鲁木齐: 新疆农业大学, 2016.
	ZHU B X. Spectral estimation model of nutrient element content in walnut leaves 'Xinxin No.2'. Urumqi: Xinjiang Agricultural University, 2016. (in Chinese)
[33]	KLANČNIK K, VOGEL-MIKUŠ K, KELEMEN M, VAVPETIČ P, PELICON P, KUMP P, JEZERŠEK D, GIANONCELLI A, GABERŠČIK A. Leaf optical properties are affected by the location and type of deposited biominerals. Journal of Photochemistry and Photobiology B: Biology, 2014, 140: 276-285.
[34]	李哲, 张飞, 陈丽华, 张海威. 光谱指数的植物叶片叶绿素含量估算模型. 光谱学与光谱分析, 2018, 38(5):1533-1539.
	LI Z, ZHANG F, CHEN L H, ZHANG H W. Research on spectrum variance of vegetation leaves and estimation model for leaf chlorophyll content based on the spectral index. Spectroscopy and Spectral Analysis, 2018, 38(5):1533-1539. (in Chinese).
[35]	YANG J, DU L, GONG W, SHI S, SUN J, CHEN B W. Analyzing the performance of the first-derivative fluorescence spectrum for estimating leaf nitrogen concentration. Optics Express, 2019, 27(4): 3978. doi: 10.1364/OE.27.003978 pmid: 30876021
[36]	YANG J, CHENG Y J, DU L, GONG W, SHI S, SUN J, CHEN B W. Selection of the optimal bands of first-derivative fluorescence characteristics for leaf nitrogen concentration estimation. Applied Optics, 2019, 58(21): 5720-5727.
[37]	ZHOU W H, ZHANG J J, ZOU M M, LIU X Q, DU X L, WANG Q, LIU Y Y, LIU Y, LI J L. Prediction of cadmium concentration in brown rice before harvest by hyperspectral remote sensing. Environmental Science and Pollution Research, 2019, 26(2): 1848-1856.
[38]	栗方亮, 孔庆波, 张青, 庄木来. 琯溪蜜柚叶片氮素含量多种高光谱估算模型对比研究. 果树学报, 2022, 39(5): 882-891.
	LI F L, KONG Q B, ZHANG Q, ZHUANG M L. Comparative study on several hyperspectral estimation models of nitrogen contents in Guanxi honey pomelo leaves. Journal of Fruit Science, 2022, 39(5): 882-891. (in Chinese)
[39]	SHI T Z, WANG J J, LIU H Z, WU G F. Estimating leaf nitrogen concentration in heterogeneous crop plants from hyperspectral reflectance. International Journal of Remote Sensing, 2015, 36(18): 4652-4667.
[40]	WANG J, CHEN J, JU W M, QIU F, ZHANG Q, FANG M H, CHEN F G. Limited effects of water absorption on reducing the accuracy of leaf nitrogen estimation. Remote Sensing, 2017, 9(3): 291.
[41]	SUN T, LI Z J, WANG Z K, LIU Y C, ZHU Z H, ZHAO Y Z, XIE W H, CUI S H, CHEN G F, YANG W L, ZHANG Z T, ZHANG F C. Monitoring of nitrogen concentration in soybean leaves at multiple spatial vertical scales based on spectral parameters. Plants, 2024, 13(1): 140.
[42]	PIMSTEIN A, KARNIELI A, BANSAL S K, BONFIL D J. Exploring remotely sensed technologies for monitoring wheat potassium and phosphorus using field spectroscopy. Field Crops Research, 2011, 121(1): 125-135.
[43]	冯海宽, 杨福芹, 杨贵军, 李振海, 裴浩杰, 邢会敏. 基于特征光谱参数的苹果叶片叶绿素含量估算. 农业工程学报, 2018, 34(6): 182-188.
	FENG H K, YANG F Q, YANG G J, LI Z H, PEI H J, XING H M. Estimation of chlorophyll content in apple leaves base on spectral feature parameters. Transactions of the Chinese Society of Agricultural Engineering, 2018, 34(6): 182-188. (in Chinese)
[44]	MA L, LIU Y, ZHANG X L, YE Y X, YIN G F, JOHNSON B A. Deep learning in remote sensing applications: A meta-analysis and review. ISPRS Journal of Photogrammetry and Remote Sensing, 2019, 152: 166-177. doi: 10.1016/j.isprsjprs.2019.04.015
[45]	张卓然, 常庆瑞, 张廷龙, 班松涛, 由明明. 基于支持向量机的棉花冠层叶片叶绿素含量高光谱遥感估算. 西北农林科技大学学报(自然科学版), 2018, 46(11): 39-45.
	ZHANG Z R, CHANG Q R, ZHANG T L, BAN S T, YOU M M. Hyperspectral estimation of chlorophyll content of cotton canopy leaves based on support vector machine. Journal of Northwest A & F University (Natural Science Edition), 2018, 46(11): 39-45. (in Chinese)
[46]	YAO X, HUANG Y, SHANG G Y, ZHOU C, CHENG T, TIAN Y C, CAO W X, ZHU Y. Evaluation of six algorithms to monitor wheat leaf nitrogen concentration. Remote Sensing, 2015, 7(11): 14939-14966.
[47]	王丽爱, 马昌, 周旭东, 訾妍, 朱新开, 郭文善. 基于随机森林回归算法的小麦叶片SPAD值遥感估算. 农业机械学报, 2015, 46(1): 259-265.
	WANG L A, MA C, ZHOU X D, ZI Y, ZHU X K, GUO W S. Estimation of wheat leaf SPAD value using RF algorithmic model and remote sensing data. Transactions of the Chinese Society for Agricultural Machinery, 2015, 46(1): 259-265. (in Chinese)
[48]	HE L, REN X X, WANG Y Y, LIU B C, ZHANG H Y, LIU W D, FENG W, GUO T C. Comparing methods for estimating leaf area index by multi-angular remote sensing in winter wheat. Scientific Reports, 2020, 10: 13943. doi: 10.1038/s41598-020-70951-w pmid: 32811882
[49]	YANG J, SUN J, DU L, CHEN B W, ZHANG Z B, SHI S, GONG W. Effect of fluorescence characteristics and different algorithms on the estimation of leaf nitrogen content based on laser-induced fluorescence lidar in paddy rice. Optics Express, 2017, 25(4): 3743-3755. doi: 10.1364/OE.25.003743 pmid: 28241586
[50]	孙小香, 王芳东, 赵小敏, 谢文, 郭熙. 基于冠层光谱和BP神经网络的水稻叶片氮素浓度估算模型. 中国农业资源与区划, 2019, 40(3): 35-44.
	SUN X X, WANG F D, ZHAO X M, XIE W, GUO X. The estimation models of rice leaf nitrogen concentration based on canopy spectrum and BP neural network. Chinese Journal of Agricultural Resources and Regional Planning, 2019, 40(3): 35-44. (in Chinese)
[51]	周智辉, 谷晓博, 程智楷, 常甜, 赵彤彤, 王玉明, 杜娅丹. 基于影像分割的覆膜玉米叶绿素含量反演. 中国农业科学, 2024, 57(6): 1066-1079. doi: 10.3864/j.issn.0578-1752.2024.06.004.
	ZHOU Z H, GU X B, CHENG Z K, CHANG T, ZHAO T T, WANG Y M, DU Y D. Inversion of chlorophyll content of film-mulched maize based on image segmentation. Scientia Agricultura Sinica, 2024, 57(6): 1066-1079. doi: 10.3864/j.issn.0578-1752.2024.06.004. (in Chinese)
[52]	MALMIR M, TAHMASBIAN I, XU Z H, FARRAR M B, BAI S H. Prediction of macronutrients in plant leaves using chemometric analysis and wavelength selection. Journal of Soils and Sediments, 2020, 20(1): 249-259.

组别 Group	样本数 Sample number	最小值 Minimum value (g·kg^-1)	最大值 Maximum value (g·kg^-1)	平均值 Average value (g·kg^-1)	标准偏差 Standard deviation
Ca1	30	6.45	23.05	13.48	4.93
Ca2	30	24.41	30.67	27.54	2.19
Ca3	30	30.97	40.92	34.37	3.27
YZ	30	6.46	40.90	25.23	9.58

光谱指数Spectral index	高光谱参数Hyperspectal parameter	估测模型Estimation model	R²
差值光谱指数 DSI	DSI_553,714	y=40.74+107.395x	0.366
	DSI_790,1040	y=0.04-0.003x+2.205e-05x²	0.707
	DSI′_528,699	y=41.956e^83.27^x	0.552
	DSI′_528,602	y=37.859e^-195.191^x	0.642
	DSI′_560,570	y=0.002-8.919e-05x+8.736e-07x²	0.704
	DSI′_699,602	y=40.994e^-59.127^x	0.586
比值光谱指数 RSI	RSI_553,714	y=85.817+0.042^x	0.358
	RSI_910,990	y=1.047-0.001x	0.745
	RSI′_350,580	y=10.276+0.055^x	0.663
	RSI′_528,699	y=20.744+235.55x-966.837x²	0.439
	RSI′_528,602	y=e3.121+0.001/x	0.119
	RSI′_699,702	y=e3.954+22.644/x	0.409
归一化光谱指数 NDSI	NDSI_553,714	y=e^4.311+0.469/^x	0.352
	NDSI_900,990	y=-0.025-90.001x	0.736
	NDSI′_350,580	y=0.826+0.007x-7.925e-05x²	0.724
	NDSI′_528,699	y=-319.242-934.362x-617.407x²	0.441
	NDSI′_528,602	y=110.479-105.326x+31.409x²	0.122
	NDSI′_699,602	y=-2922.251+5739.173x-2786x²	0.519

估测模型 Estimation model	估算模型R²Estimation model R²	估算模型RMSE Estimation model RMSE	估算模型RE（%） Estimation model RE (%)	验证模型R²Validation model R²	验证模型RMSE Validation model RMSE	验证模型RE（%）Validation model RE (%)
偏最小二乘法 PLS	0.79	4.33	17.13	0.77	4.50	18.04
BP神经网络 BPNN	0.82	4.11	15.56	0.80	4.28	16.92
随机森林法 RF	0.85	3.81	13.91	0.87	3.67	13.05
支持向量机 SVM	0.84	3.93	13.53	0.83	3.90	12.69