基于随机森林法的棉花叶片叶绿素含量估算

doi:10.3724/SP.J.1006.2019.84058

Abstract

Abstract:

The main objective of this study is the estimation of the leaf chlorophyll content efficiently and harmlessly. SPAD values and spectral data were collected from field observation. Original spectra processed to continuum-removal transformation, cube-root transformation and reciprocal transformation. Based on the correlation between SPAD values and canopy spectral reflectance, we selected characteristic bands by random forest approach to establish two kinds of estimating models, including back propagation artificial neural network (BP ANN) model and partial least squares regression (PLSR) model. The reflectivity in the range of 605-690 nm was negatively correlated with the SPAD value at P < 0.01, with the correlation coefficient of -0.619. After transformations, the spectral reflectance exhibited different correlations with SPAD value, continuum-removal spectra improved the correlation in the range of 550-750 nm, and had a better correlation with SPAD value than cube-root and reciprocal transformations. Random forest approach effectively evaluated the characteristic bands with large influence on SPAD value, which can help improve the estimation accuracy of the model. R ² of the PLSR and BP neural network model based on continuum-removal spectra was 0.92 and 0.83 respectively, show the two models with good stability in estimation of cotton SPAD values. The RMSE of the two models was 0.88, 1.26, and RE was 1.30% and 1.89% respectively, which indicates that estimation accuracy of PLSR model is higher that of BP neural network model. From the validation of the model, PLSR model has certain advantages and reference value in estimating chlorophyll content of cotton.

Key words: SPAD value, cotton, random forest method, hyper-spectral estimation model

ABLET Ershat,SAWUT Mamat,MAIMAITIAILI Baidengsha,Shen-Qun AN,Chun-Yue MA. Estimation of leaf chlorophyll content in cotton based on the random forest approach[J].Acta Agronomica Sinica, 2019, 45(1): 81-90.

Figures/Tables 8

Fig. 1

Fig. 2

Fig. 3

Fig. 4

Table 1

Fig. 5

Table 2

Fig. 6

References 43

[1]	史典义, 刘忠香, 金危危 . 植物叶绿素合成、分解代谢及信号调控. 遗传, 2009,31:698-704. doi: 10.3724/SP.J.1005.2009.00698
	Shi D Y, Liu Z X, Jin W W . Biosynthesis, catabolism and related signal regulations of plant chlorophyll. Hereditas, 2009,31:698-704 (in Chinese with English abstract). doi: 10.3724/SP.J.1005.2009.00698
[2]	刘燕婕, 李建设, 高艳明 . 可见光波段不同氮处理生菜叶片光谱反射率与叶片全氮、叶绿素的相关性研究. 北方园艺, 2015,39(22):12-16. doi: 10.11937/bfyy.201522003
	Liu Y J, Li J S, Gao Y M . Correlation between lettuce leaf spectral reflectance in visible light area and leaf nitrogen content and leaf chlorophyll content under different levels of nitrogen. Nor Hortic, 2015,39(22):12-16 (in Chinese with English abstract). doi: 10.11937/bfyy.201522003
[3]	姜海玲, 杨杭, 陈小平, 王树东, 李雪轲, 刘凯 . 利用光谱指数反演植被叶绿素含量的精度及稳定性研究. 光谱学与光谱分析, 2015,35:975-981. doi: 10.3964/j.issn.1000-0593(2015)04-0975-07
	Jiang H L, Yang H, Chen X P, Wang S D, Li X K, Liu K . Research on accuracy and stability of inversing vegetation chlorophyll content by spectral index method. Spectrosc Spect Anal, 2015,35:975-981 (in Chinese with English abstract). doi: 10.3964/j.issn.1000-0593(2015)04-0975-07
[4]	Inoue Y, Guérif M, Baret F, Skidmore A, Gitelson A, Schlerf M . Simple and robust methods for remote sensing of canopy chlorophyll content: a comparative analysis of hyper-spectral data for different types of vegetation. Plant Cell Environ, 2016,39:2609-2623. doi: 10.1111/pce.12815 pmid: 27650474
[5]	Vane G, Goetz A . Terrestrial imaging spectrometry: Current status, future trends. Remote Sense Environ, 1993,44:117-126. doi: 10.1016/0034-4257(93)90011-L
[6]	Curran P J . Remote sensing of foliar chemistry. Remote Sense Environ, 1989,30:271-278. doi: 10.1016/0034-4257(89)90069-2
[7]	Jacquemoud S, Baret F . PROSPECT: a model of leaf optical properties spectra. Remote Sense Environ, 1990,34:75-91. doi: 10.1016/0034-4257(90)90100-Z
[8]	Li D, Cheng T, Zhou K, Zheng H, Yao X, Tian Y . WREP: a wavelet-based technique for extracting the red edge position from reflectance spectra for estimating leaf and canopy chlorophyll contents of cereal crops. ISPRS J Photogramm Remote Sense, 2017: 103-117. doi: 10.1016/j.isprsjprs.2017.04.024
[9]	毛博慧, 李民赞, 孙红, 刘豪杰, 张俊逸, Zhang Q . 冬小麦苗期叶绿素含量检测光谱学参数寻优. 农业工程学报, 2017,33(S1):164-169. doi: 10.11975/j.issn.1002-6819.2017.z1.025
	Mao B H, Li M Z, Sun H, Liu H J, Zhang J Y, Zhang Q . Optimization of spectroscopy parameters and prediction of chlorophyll content at seeding stage of winter wheat. Trans CSAE, 2017,33(S1):164-169 (in Chinese with English abstract). doi: 10.11975/j.issn.1002-6819.2017.z1.025
[10]	丁永军, 张晶晶, 孙红, 李修华 . 玻璃温室环境下番茄叶绿素含量敏感光谱波段提取及估测模型. 光谱学与光谱分析, 2017,37:194-199.
	Ding Y J, Zhang J J, Sun H, Li X H . Sensitive bands extraction and prediction model of tomato chlorophyll in glass green house. Spectrosc Spect Anal, 2017,37:194-199 (in Chinese with English abstract).
[11]	姚霞, 田永超, 刘小军, 曹卫星, 朱艳 . 不同算法红边位置监测小麦冠层氮素营养指标的比较. 中国农业科学, 2010,43:2661-2667. doi: 10.3864/j.issn.0578-1752.2010.13.005
	Yao X, Tian Y C, Liu X J, Cao W X, Zhu Y . Comparative study on monitoring canopy leaf nitrogen status on red edge position with different algorithms in wheat. Sci Agric Sin, 2010,43:2661-2667 (in Chinese with English abstract). doi: 10.3864/j.issn.0578-1752.2010.13.005
[12]	Yi Q X, Huang J F, Wang F M, Wang X Z . Evaluating the performance of PC-ANN for the estimation of rice nitrogen concentration from canopy hyperspectral reflectance. Int J Remote Sense, 2010,31:931-940. doi: 10.1080/01431160902912061
[13]	Curran P J, Dungan J L, Peterson D L . Estimating the foliar biochemical concentration of leaves with reflectance spectrometry: testing the Kokaly and Clark methodologies. Remote Sense Environ, 2001,76:349-359. doi: 10.1016/S0034-4257(01)00182-1
[14]	郭超凡, 郭逍宇 . 基于可见光波段包络线去除的湿地植物叶片叶绿素估算. 生态学报, 2016,36:6538-6546. doi: 10.5846/stxb201507091460
	Guo C F, Guo X Y . Estimation of wetland plant leaf chlorophyll content based on continuum removal on visible domain. Acta Ecol Sin, 2016,36:6538-6546 (in Chinese with English abstract). doi: 10.5846/stxb201507091460
[15]	Mielke C, Boesche N K, Rogass C, Kaufmann H, Gauert C . New geometric hull continuum removal algorithm for automatic absorption band detection from spectroscopic data. Remote Sense Lett, 2015,6:97-105. doi: 10.1080/2150704X.2015.1007246
[16]	Breiman L . Random forests. Mach Learn, 2001,45:5-32. doi: 10.1023/A:1010933404324
[17]	李振国, 杨德森 . 生活质量与临床医学. 中国社会医学, 1994, ( 3):34-35.
	Li Z G, Yang D S . Quality of life and clinical medicine. Chin J Soc Med, 1994, ( 3):34-35 (in Chinese).
[18]	Donnelly S, Walsh D . Quality of life assessment in advanced cancer. Palliat Med, 2000,2:338-342. doi: 10.1007/s11912-000-0027-7 pmid: 8931062
[19]	Grömping U . Variable importance assessment in regression: linear regression versus random forest. Am Stat, 2009,63:308-319. doi: 10.1198/tast.2009.08199
[20]	梁智, 孙国强, 卫志农, 臧海祥 . 基于变量选择与高斯过程回归的短期负荷预测. 电力建设, 2017,38(2):122-128. doi: 10.3969/j.issn.1000-7229.2017.01.017
	Liang Z, Sun G Q, Wei Z N, Zang H X , Short-term load forecasting based on variable selection and gaussian process regression. Electric Power Const, 2017,38(2):122-128 (in Chinese with English abstract). doi: 10.3969/j.issn.1000-7229.2017.01.017
[21]	尼加提·卡斯木, 师庆东, 王敬哲, 茹克亚·萨吾提, 依力亚斯江·努尔麦麦提, 古丽努尔·依沙克 . 基于高光谱特征和偏最小二乘法的春小麦叶绿素含量估算. 农业工程学报, 2017,33(22):208-216. doi: 10.11975/j.issn.1002-6819.2017.22.027
	Nijat K, Shi Q D, Wang J Z, Rukeya S, Ilyas N, Gulnur I . Estimation of spring wheat chlorophyll content based on hyper-spectral features and PLSR model. Trans CSAE, 2017,33(22):208-216 (in Chinese with English abstract). doi: 10.11975/j.issn.1002-6819.2017.22.027
[22]	翁永玲, 戚浩平, 方洪宾, 赵福岳, 路云阁 . 基于PLSR方法的青海茶卡-共和盆地土壤盐分高光谱遥感反演. 土壤学报, 2010,47:1255-1263. doi: 10.11766/trxb200907100306
	Weng Y L, Qi H P, Fang H B, Zhao F Y, Lu Y G . PLSR-Based hyper-spectral remote sensing retrieval of soil salinity of Chaka-gonghe basin in Qinghai province. Acta Pedol Sin, 2010,47:1255-1263(in Chinese with English abstract). doi: 10.11766/trxb200907100306
[23]	刘全明, 成秋明, 王学, 李相君 . 河套灌区土壤盐渍化微波雷达反演. 农业工程学报, 2016,32(16):109-114. doi: 10.11975/j.issn.1002-6819.2016.16.016
	Liu Q M, Cheng Q M, Wang X, Li X J . Soil salinity inversion in Hetao Irrigation district using microwave radar. Trans CSAE, 2016,32(16):109-114 (in Chinese with English abstract). doi: 10.11975/j.issn.1002-6819.2016.16.016
[24]	王静, 刘湘南, 黄方, 唐吉龙, 赵冷冰 . 基于ANN技术和高光谱遥感的盐渍土盐分预测. 农业工程学报, 2009,25(12):161-166. doi: 10.3969/j.issn.1002-6819.2009.12.029
	Wang J, Liu X N, Huang F, Tang J L, Zhao L B . Salinity forecasting of saline soil based on ANN and hyper-spectral remote sensing. Trans CSAE, 2009,25(12):161-166 (in Chinese with English abstract). doi: 10.3969/j.issn.1002-6819.2009.12.029
[25]	Johnson L F, Hlavka C A, Peterson D L . Multivariate analysis of AVIRIS data for canopy biochemical estimation along the oregon transect. Remote Sense Environ, 1994,47:216-230. doi: 10.1016/0034-4257(94)90157-0
[26]	Matson P, Johnson L, Billow C, Miller J, Pu R . Seasonal patterns and remote spectral estimation of canopy chemistry across the oregon transect. Ecol Appl, 1994,4:280-298. doi: 10.2307/1941934
[27]	Curran P J, Kupiec J A, Smith G M . Remote sensing the biochemical composition of a slash pine canopy. IEEE Trans Geosci Remote Sense, 1997,35:415-420. doi: 10.1109/36.563280
[28]	Peterson D L, Aber J D, Matson P A, Card D H, Swanberg N, Wessman C . Remote sensing of forest canopy and leaf biochemical contents. Remote Sense Environ, 1988,24:85-108. doi: 10.1016/0034-4257(88)90007-7
[29]	Yoder B J, Pettigrew-Crosby R E . Predicting nitrogen and chlorophyll content and concentrations from reflectance spectra (400-2500 nm) at leaf and canopy scales. Remote Sense Environ, 1995,53:199-211. doi: 10.1016/0034-4257(95)00135-N
[30]	Chen L, Huang J F, Wang F M . Comparison between back propagation neural network and regression models for the estimation of pigment content in rice leaves and panicles using hyper-spectral data. Int J Remote Sense, 2007,28:3457-3478. doi: 10.1080/01431160601024242
[31]	刘平, 马美湖 . 基于高光谱技术检测全蛋粉掺假的研究. 光谱学与光谱分析, 2018,38:246-252. doi: 10.3964/j.issn.1000-0593(2018)01-0246-07
	Liu P, Ma M F . Application of hyper-spectral technology for detecting adulterated whole egg powder. Spectrosc Spect Anal, 2018,38:246-252 (in Chinese with English abstract). doi: 10.3964/j.issn.1000-0593(2018)01-0246-07
[32]	贾学勤, 冯美臣, 杨武德, 王超, 肖璐洁, 孙慧, 武改红, 张松 . 基于多植被指数组合的冬小麦地上干生物量高光谱估测. 生态学杂志, 2018,37:424-429.
	Jia X Q, Feng M C, Yang W D, Wang C, Xiao L J, Sun H, Wu G H, Zhang S . Hyper-spectral estimation of aboveground dry biomass of winter wheat based on the combination of vegetation indices. Chin J Ecol, 2018,37:424-429 (in Chinese with English abstract).
[33]	孙红, 郑涛, 刘宁, 程萌, 李民赞, Zhang Q . 高光谱图像检测马铃薯植株叶绿素含量垂直分布. 农业工程学报, 2018,34(1):149-156.
	Sun H, Zheng T, Liu N, Cheng M, Li M Z, Zhang Q . Vertical distribution of chlorophyll in potato plants based on hyper-spectral imaging. Trans CSAE, 2018,34(1):149-156 (in Chinese with English abstract).
[34]	郭云开, 刘宁, 刘磊, 李丹娜, 朱善宽 . 土壤Cu含量高光谱反演的BP神经网络模型. 测绘科学, 2018,43(1):135-139.
	Guo Y K, Liu N, Liu L, Li D N, Zhu S K . Hyper-spectral inversion of soil Cu content based on BP neural network model. Sci Survey Map, 2018,43(1):135-139 (in Chinese with English abstract).
[35]	余蛟洋, 常庆瑞, 由明明, 张卓然, 罗丹 . 基于高光谱和BP神经网络模型苹果叶片SPAD值遥感估算. 西北林学院学报, 2018,33(2):156-165.
	Yu J Y, Chang Q R, You M M, Zhang Z R, Luo D . Estimation of apple leaf SPAD value based on hyperspectrum and BP Neural Network. J Northwest For Univ, 2018,33(2):156-165 (in Chinese with English abstract).
[36]	Zagolski F, Pinel V, Romier J, Alcayde D, Fontanari J, Gastellu-Etchegorry J P . Forest canopy chemistry with high spectral resolution remote sensing. Int J Remote Sense, 1996,17:1107-1128. doi: 10.1080/01431169608949073
[37]	Pal M . Random forest classifier for remote sensing classification. Int J Remote Sense, 2005,26:217-222. doi: 10.1080/01431160412331269698
[38]	Deschamps B, Mcnairn H, Shang J, Jiao X . Towards operational radar-only crop type classification: comparison of a traditional decision tree with a random forest classifier. Can J Remote Sense, 2012,38:60-68. doi: 10.5589/m12-012
[39]	黄健熙, 侯矞焯, 苏伟, 刘峻明, 朱德海 . 基于GF-1 WFV数据的玉米与大豆种植面积提取方法. 农业工程学报, 2017,33(7):164-170. doi: 10.11975/j.issn.1002-6819.2017.07.021
	Huang J X, Hou Y Z, Su W, Liu J M, Zhu D H . Mapping corn and soybean cropped area with GF-1 WFV data. Trans CSAE, 2017,33(7):164-170 (in Chinese with English abstract). doi: 10.11975/j.issn.1002-6819.2017.07.021
[40]	陈纪波, 胡慧, 陈克垚, 王桂芝 . 基于非线性PLSR模型的气候变化对粮食产量的影响分析. 中国农业气象, 2016,37:674-681. doi: 10.3969/j.issn.1000-6362.2016.06.007
	Chen J B, Hu H, Chen K Y, Wang G Z . Effects of climate change on the grain yield based on nonlinear PLSR model. Chin J Agrometeorol, 2016,37:674-681 (in Chinese with English abstract). doi: 10.3969/j.issn.1000-6362.2016.06.007
[41]	于雷, 洪永胜, 耿雷, 周勇, 朱强, 曹隽隽, 聂艳 . 基于偏最小二乘回归的土壤有机质含量高光谱估算, 农业工程学报, 2015,31(14):103-109. doi: 10.11975/j.issn.1002-6819.2015.14.015
	Yu L, Hong Y S, Geng L, Zhou Y, Zhu Q, Cao J J, Nie Y . Hyperspectral estimation of soil organic matter content based on partial least squares regression. Trans CSAE, 2015,31(14):103-109 (in Chinese with English abstract). doi: 10.11975/j.issn.1002-6819.2015.14.015
[42]	Gomez C, Lagacherie P, Coulouma G . Continuum removal versus PLSR method for clay and calcium carbonate content estimation from laboratory and airborne hyperspectral measurements. Geoderma, 2008,148:141-148. doi: 10.1016/j.geoderma.2008.09.016
[43]	刘晓莉, 杨灵娥, 宋春玲 . 提高多目标输出神经网络模型泛化能力和预测精度的方法. 佛山科学技术学院学报(自然科学版), 2008,26(1):31-33. doi: 10.3969/j.issn.1008-0171.2008.01.009
	Liu X L, Yang L E, Song C L . Improvement of the genera and the learn enlcienin BP network models. J Foshan Univ(Nat Sci Edn), 2008,26(1):31-33 (in Chinese with English abstract). doi: 10.3969/j.issn.1008-0171.2008.01.009

Related Articles 15

[1]	Peng Jia-Luo, Li Ying, Li Dan-Dan, Yang Jun-Ning, Guo Xue-Feng, Zhang Wen-Jiao, Yu Xiao-Xue, Zhou Ya-Rong, Wang Zhen-Yu, Wang Cai-Xiang, Ma Xiong-Feng, Su Jun-Ji. Identification of class I LBD family members in upland cotton and function and haplotype analyses of GhLBD6 in regulating flowering period [J]. Acta Agronomica Sinica, 2026, 52(6): 1682-1697.
[2]	Zhao Jia-Xue, Zhou Long-Hao, Guo Qi-Yuan, Shang Lun-Xiao, Wang Han, Liu Zhi-Tao, Chen Xi, Zhang Xiao-Pei, Song Xian-Liang, Ahmedov Miraziz Baltaevich, Mao Li-Li. Long-term stubble return and subsoiling enhance cotton yields in coastal saline-alkali soils by improving soil conditions and photosynthetic characteristics [J]. Acta Agronomica Sinica, 2026, 52(5): 1548-1560.
[3]	Zhang Xi, Wang Guang-En, Li Shao-Qi, Liu Yi, Li Jun-Lan, Qian Yu-Yuan. Transcriptome sequencing-based analysis on the formation mechanism of fiber micronaire differences between two sister lines derived from Gossypium hirsutum-G. barbadense hybrid [J]. Acta Agronomica Sinica, 2026, 52(5): 1442-1458.
[4]	Zhou Qi-Xiang, Zhu Yan, Wang Chu-Bo, Zhu Bo-Lin, Li Jun-Bo, Song Li-Bing. Modeling the effects of climate change on cotton phenology and potential yield in Xinjiang based on the DSSAT model [J]. Acta Agronomica Sinica, 2026, 52(2): 590-602.
[5]	LI Yi-Qian, XU Shou-Zhen, LIU Ping, MA Qi, XIE Bin, CHEN Hong. Genome-wide association study of yield components using a 40K SNP array and identification of a stable locus for boll weight in upland cotton (Gossypium hirsutum L.) [J]. Acta Agronomica Sinica, 2025, 51(8): 2128-2138.
[6]	GUO Dong-Cai, LYU Tao, CAI Yong-Sheng, MAI WU-LU-DA·AI He-Mai-Ti, CHEN Quan-Jia, QU Yan-Ying, ZHENG Kai. Meta-analysis of QTL and identification of candidate genes for fiber quality in cotton [J]. Acta Agronomica Sinica, 2025, 51(6): 1445-1466.
[7]	WANG Ya-Wen, QI Zheng-Yang, YOU Jia-Qi, NIE Xin-Hui, CAO Juan, YANG Xi-Yan, TU Li-Li, ZHANG Xian-Long, WANG Mao-Jun. Preparation of cotton 60K functional locus gene chip and its application to genetic research [J]. Acta Agronomica Sinica, 2025, 51(5): 1178-1188.
[8]	DING Jun-Feng, XU Ying-Fei, ZHANG Xiang, CHEN Yuan, CHEN De-Hua. Effects of the plant growth regulator IBA on the survival and growth of substrate- grown transplanted cotton seedlings [J]. Acta Agronomica Sinica, 2025, 51(12): 3331-3341.
[9]	HALIHASHI Yibati, ZHANG Yan, LI Qing-Jun, XU Xin-Peng, HE Ping. Study on smart fertilizer recommendation methods based on yield response and agronomic efficiency for cotton [J]. Acta Agronomica Sinica, 2025, 51(11): 3052-3064.
[10]	ZHAO Hai-Hong, LI Meng-Yuan, LIU Jin-Jing, WANG Yuan-Yuan, DU Lei, WANG Juan, DONG Cheng-Guang, LI Cheng-Qi. Detection of QTNs and QTN-by-environment interactions for plant height in upland cotton (G. hirsutum L.) using the 3VmrMLM method [J]. Acta Agronomica Sinica, 2025, 51(10): 2619-2631.
[11]	LI Ya-Wei, XU Ying-Ying, ZUO Chun-Yang, LIU Ruo-Nan, LIANG Ya-Jun, KONG Jie, ZHANG Xian-Long, MIN Ling. Construction of a meiotic progression identification system in cotton and analysis of its response to high-temperature stress [J]. Acta Agronomica Sinica, 2025, 51(10): 2570-2580.
[12]	CHEN Jia-Wei, LIN Yan, ZHANG Ming-Xing, ZHOU Shi-Jing, RAO Li-Qun, ZHOU Chi, LI Xin. Effects of Bacillus velezensis YCH92 on the rhizosphere microbial community and yield of cotton [J]. Acta Agronomica Sinica, 2025, 51(10): 2821-2835.
[13]	XIE Zhang-Shu, XIE Xue-Fang, TU Xiao-Ju, LIU Ai-Yu, DONG He-Zhong, ZHOU Zhong-Hua. Research progress in phytohormone regulation of square and boll shedding in cotton [J]. Acta Agronomica Sinica, 2025, 51(1): 1-29.
[14]	XIN Ming-Hua, MI Ya-Di, WANG Guo-Ping, LI Xiao-Fei, LI Ya-Bing, DONG He-Lin, HAN Ying-Chun, FENG Lu. Effect of row spacing configuration and density regulation on dry matter production and yield in cotton [J]. Acta Agronomica Sinica, 2025, 51(1): 221-232.
[15]	LI Chao, FU Xiao-Qiong. Comprehensive evaluation of regional trial varieties of medium mature hybrid cotton in the Yellow River Basin based on GYT biplot [J]. Acta Agronomica Sinica, 2025, 51(1): 30-43.

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed

Comments

Recommended 0

No Suggested Reading articles found!

原始光谱RR				包络线去除光谱R_cr
变量名Variable name	特征波段Characteristic band (nm)	相关系数Correlation coefficient	VIM值 VIM value	变量名Variable name	特征波段Characteristic band (nm)	相关系数Correlation coefficient	VIM值 VIM value
X₁	614	-0.498	0.03420	X'₁	407	-0.670	0.00729
X₂	616	-0.520	0.00652	X'₂	479	-0.681	0.00326
X₃	653	-0.603	0.01130	X'₃	488	-0.694	0.00326
X₄	670	-0.633	0.01031	X'₄	508	-0.699	0.00461
X₅	689	-0.628	0.00461	X'₅	577	-0.732	0.00326
X₆	697	-0.544	0.01458	X'₆	585	-0.750	0.00326
X₇	700	-0.482	0.00652	X'₇	612	-0.779	0
X₈	759	0.513	0.00565	X'₈	621	-0.799	0.00461
X₉	786	0.516	0.00461	X'₉	651	-0.793	0.00326
X₁₀	826	0.519	0.00799	X'₁₀	695	-0.792	0.00799
X₁₁	905	0.529	0.00799	X'₁₁	712	-0.760	0.00652
X₁₂	941	0.509	0.05238	X'₁₂	723	-0.697	0.00790

模型 Model	建模Calibration (RR)		建模集Calibration (R_cr)		验证集Validation (RR)			验证集Validation (R_cr)
模型 Model	R²	RMSE	R²	RMSE	R²	RMSE	RE (%)	R²	RMSE	RE (%)
偏最小二乘模型PLSR BP神经网络模型BP ANN	0.68 0.69	1.62 1.59	0.63 0.90	1.73 0.91	0.64 0.78	2.06 1.60	3.01 2.27	0.92 0.83	0.88 1.26	1.30 1.89

Estimation of leaf chlorophyll content in cotton based on the random forest approach

RichHTML341

PDF