基于VSURF-CA的小麦条锈病高光谱病情指数估测模型

doi:10.3864/j.issn.0578-1752.2024.03.005

摘要/Abstract

摘要：

【目的】条锈病对小麦生长和产量造成严重威胁，为确保有效防控，精准监测尤为关键。利用遥感技术构建小麦条锈病估测模型，能快速、准确地估测病情指数（DI），为精准防控提供技术支持。【方法】利用ASD光谱仪获取小麦不同生育期（抽穗期、灌浆期和成熟期）高光谱数据，采用随机森林变量选择（VSURF）方法结合相关性分析（CA）对原始光谱（OR）和一阶微分光谱（FD）进行特征波段筛选。使用随机森林（RF）对比不同数据集的特征波段建模结果，确定模型效果最佳的特征集。随后借助偏最小二乘回归（PLSR）、极致梯度提升（XGBoost）以及反向传播神经网络（BPNN），对比特征集在不同算法中的建模效果。通过对比建模效果，确定针对全生育期小麦条锈病病情指数的最佳估测模型。为了验证特征集在不同生育期中的效果，利用特征集在3个生育期重新构建模型，并对比模型效果。【结果】对不同数据集进行特征筛选，并使用RF构建条锈病DI估测模型，通过比较模型效果，确定VSURF-CA-FD特征集（绿光范围的537 nm以及近红外范围的821和846 nm）在RF模型中的估测效果最好。采用RF算法构建的模型表现出优异的精度，R²为0.89，RMSE为12.34。这些特征波段在其他算法构建的模型中也展现出良好的精度：XGBoost模型的R²为0.87，RMSE为13.15；BPNN模型的R²为0.84，RMSE为15.19；PLSR模型的R²为0.69，RMSE为20.92。使用不同生育期的冠层微分高光谱数据进行验证，利用VSURF-CA-FD特征集构建RF模型，对比模型发现在小麦生长的早期（抽穗期）R²为0.54，RMSE为1.29，NRMSE为0.21，能满足估测病害的要求；小麦生长的中期（灌浆期），模型的R²表现较好，R²为0.66，RMSE为12.24，NRMSE为0.21；小麦生长晚期（成熟期），模型效果好于前两个时期，R²为0.75，RMSE为10.77，NRMSE为0.15。【结论】使用VSURF-CA方法筛选出的特征波段，能构建出对小麦条锈病病情指数具有出色估测效果的RF模型。研究结果可为预测早期和中期条锈病病情指数提供有价值的思路和方法。

关键词: 高光谱估测模型, 小麦条锈病, 病情指数, VSURF, 特征选择

Abstract:

【Objective】Stripe rust is a serious threat to the growth and yield of wheat. Accurate monitoring and diagnostic assessment are fundamental prerequisites for effective prevention and control of stripe rust. The objective of this study is to construct a wheat stripe rust estimation model using remote sensing technology, enable the rapid and precise estimation of the disease index (DI), and to provide technical support for precise prevention and control.【Method】The hyperspectral data of wheat at different growth stages (heading period, grain-filling period, and maturity period) were acquired through the ASD spectrometer. Initially, the variable selection using random forests (VSURF) method, combined with correlation analysis (CA), was applied to select characteristic bands from the original spectrum (OR) and the first-order differential spectrum (FD). Subsequently, the random forest (RF) algorithm was utilized to compare modeling results of characteristic bands from different datasets, identifying the feature set with the most effective model. Further, models such as partial least squares regression (PLSR), extreme gradient boosting (XGBoost), and back-propagation neural network (BPNN) were employed to compare the modeling effects of different feature sets within various algorithms. This comprehensive analysis aimed to determine the optimal estimation model for wheat stripe rust DI across the entire growth period. Simultaneously, to validate the effectiveness of the feature set across different growth stages, the feature set was used to rebuild models during each of the three distinct growth periods.【Result】The comparative analysis of model effects revealed that the VSURF-CA-FD feature set (537 nm in the green range and 821, 846 nm in the near-infrared range) demonstrated the most effective estimation within the RF model, achieving an R² value of 0.89 and an RMSE of 12.34. These feature bands also exhibited precision in models constructed with other algorithms, including XGBoost (R²: 0.87, RMSE: 13.15), BPNN (R²: 0.84, RMSE: 15.19), and PLSR (R²: 0.69, RMSE: 20.92). For models constructed during different growth stages, the early growth stage (heading period) exhibited an R² value of 0.54, RMSE of 1.29, and NRMSE of 0.21, meeting the requirements for disease estimation. In the middle growth stage (grain-filling period), the model performed well with an R² of 0.66, RMSE of 12.24, and NRMSE of 0.21. In the late growth stage (maturity period), the model’s effectiveness surpassed that of the previous two stages, with an R² of 0.75, RMSE of 10.77, and NRMSE of 0.15.【Conclusion】Utilizing characteristic bands selected through the VSURF-CA method, an RF model with excellent estimation accuracy for wheat stripe rust DI can be established. The research outcomes will provide valuable insights and methodologies for predicting early and mid-stage stripe rust DI.

Key words: hyperspectral estimation model, wheat stripe rust, disease index (DI), VSURF, feature selection

梅广源, 李荣, 梅新, 陈日强, 樊意广, 程金鹏, 冯子恒, 陶婷, 赵倩, 赵培钦, 杨小冬. 基于VSURF-CA的小麦条锈病高光谱病情指数估测模型[J]. 中国农业科学, 2024, 57(3): 484-499.

MEI GuangYuan, LI Rong, MEI Xin, CHEN RiQiang, FAN YiGuang, CHENG JinPeng, FENG ZiHeng, TAO Ting, ZHAO Qian, ZHAO PeiQin, YANG XiaoDong. A VSURF-CA Based Hyperspectral Disease Index Estimation Model of Wheat Stripe Rust[J]. Scientia Agricultura Sinica, 2024, 57(3): 484-499.

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.0578-1752.2024.03.005

https://www.chinaagrisci.com/CN/Y2024/V57/I3/484

图/表 13

图1

图2

图3

图4

图5

图6

图7

图8

表1

图9

表2

图10

图11

参考文献 63

[1]	冷伟锋. 小麦条锈病遥感监测及网络信息平台构建[D]. 北京: 中国农业大学, 2015.
	LENG W F. Remote sensing monitoring of wheat yellow rust and development of network platform for the disease information[D]. Beijing: China Agricultural University, 2015. (in Chinese)
[2]	陈万权, 康振生, 马占鸿, 徐世昌, 金社林, 姜玉英. 中国小麦条锈病综合治理理论与实践. 中国农业科学, 2013, 46(20): 4254-4262. doi: 10.3864/j.issn.0578-1752.2013.20.008.
	CHEN W Q, KANG Z S, MA Z H, XU S C, JIN S L, JIANG Y Y. Integrated management of wheat stripe rust caused by Puccinia striiformis f. sp. tritici in China. Scientia Agricultura Sinica, 2013, 46(20): 4254-4262. doi: 10.3864/j.issn.0578-1752.2013.20.008. (in Chinese)
[3]	万安民, 赵中华, 吴立人. 2002年我国小麦条锈病发生回顾. 植物保护, 2003, 29(2): 5-8.
	WAN A M, ZHAO Z H, WU L R. Reviews of occurrence of wheat stripe rust disease in 2002 in China. Plant Protection, 2003, 29(2): 5-8. (in Chinese)
[4]	万安民. 小麦条锈病的发生状况和研究现状. 世界农业, 2000(5): 39-40.
	WAN A M. Occurrence and research status of wheat stripe rust. World Agriculture, 2000(5): 39-40. (in Chinese)
[5]	孙瑞琳, 孙全, 孙成明, 刘涛, 李冬双, 吴峰峰. 基于不同平台的小麦病虫害遥感监测研究进展. 中国农机化学报, 2021, 42(3): 142-150. doi: 10.13733/j.jcam.issn.2095-5553.2021.03.020
	SUN R L, SUN Q, SUN C M, LIU T, LI D S, WU F F. Recent advances in remote sensing monitoring on wheat pests and diseases based on different platforms. Journal of Chinese Agricultural Mechanization, 2021, 42(3): 142-150. (in Chinese)
[6]	江静. 基于冠层和区域尺度的小麦条锈病遥感监测[D]. 合肥: 安徽大学, 2020.
	JIANG J. Remote sensing monitoring of wheat yellow rust based on canopy and regional scale[D]. Hefei: Anhui University, 2020. (in Chinese)
[7]	郭安廷. 基于成像遥感的小麦条锈病监测方法研究[D]. 北京: 中国科学院大学(中国科学院空天信息创新研究院), 2021.
	GUO A T. Research on the methods of wheat yellow rust monitoring based on imaging remote sensing[D]. Beijing: University of Chinese Academy of Sciences (Aerospace Information Research Institute, Chinese Academy of Sciences), 2021. (in Chinese)
[8]	DUBEY S R, JALAL A S. Apple disease classification using color, texture and shape features from images. Signal, Image and Video Processing, 2016, 10: 819-826. doi: 10.1007/s11760-015-0821-1
[9]	ABDU A M, MOKJI M M, SHEIKH U U. Deep learning for plant disease identification from disease region images//Intelligent Robotics and Applications:13th International Conference, ICIRA 2020. Kuala Lumpur, Malaysia, 2020: 65-75.
[10]	FERENTINOS K P. Deep learning models for plant disease detection and diagnosis. Computers and Electronics in Agriculture, 2018, 145: 311-318. doi: 10.1016/j.compag.2018.01.009
[11]	孙刚, 黄文江, 陈鹏飞, 高帅, 王秀. 轻小型无人机多光谱遥感技术应用进展. 农业机械学报, 2018, 49(3): 1-17.
	SUN G, HUANG W J, CHEN P F, GAO S, WANG X. Advances in UAV-based multispectral remote sensing applications. Transactions of the Chinese Society for Agricultural Machinery, 2018, 49(3): 1-17. (in Chinese)
[12]	NEBIKER S, LACK N, ABÄCHERLI M, LÄDERACH S. Light-weight multispectral UAV sensors and their capabilities for predicting grain yield and detecting plant diseases. The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, 2016, 41: 963-970.
[13]	XIAO D Q, PAN Y Q, FENG J Z, YIN J J, LIU Y F, HE L. Remote sensing detection algorithm for apple fire blight based on UAV multispectral image. Computers and Electronics in Agriculture, 2022, 199: 107137. doi: 10.1016/j.compag.2022.107137
[14]	SU J Y, LIU C J, HU X P, XU X M, GUO L, CHEN W H. Spatio-temporal monitoring of wheat yellow rust using UAV multispectral imagery. Computers and Electronics in Agriculture, 2019, 167: 105035. doi: 10.1016/j.compag.2019.105035
[15]	张竞成, 袁琳, 王纪华, 罗菊花, 杜世州, 黄文江. 作物病虫害遥感监测研究进展. 农业工程学报, 2012, 28(20): 1-11.
	ZHANG J C, YUAN L, WANG J H, LUO J H, DU S Z, HUANG W J. Research progress of crop diseases and pests monitoring based on remote sensing. Transactions of the Chinese Society of Agricultural Engineering, 2012, 28(20): 1-11. (in Chinese)
[16]	刘良云, 黄木易, 黄文江, 王纪华, 赵春江, 郑兰芬, 童庆禧. 利用多时相的高光谱航空图像监测冬小麦条锈病. 遥感学报, 2004, 8(3): 275-281.
	LIU L Y, HUANG M Y, HUANG W J, WANG J H, ZHAO C J, ZHENG L F, TONG Q X. Monitoring stripe rust disease of winter wheat using multi-temporal hyperspectral airborne data. Journal of Remote Sensing, 2004, 8(3): 275-281. (in Chinese)
[17]	蒋金豹, 陈云浩, 黄文江. 用高光谱微分指数监测冬小麦病害的研究. 光谱学与光谱分析, 2007, 27(12): 2475-2479.
	JIANG J B, CHEN Y H, HUANG W J. Using hyperspectral derivative index to monitor winter wheat disease. Spectroscopy and Spectral Analysis, 2007, 27(12): 2475-2479. (in Chinese)
[18]	蔡成静, 王海光, 安虎, 史延春, 黄文江, 马占鸿. 小麦条锈病高光谱遥感监测技术研究. 西北农林科技大学学报(自然科学版), 2005, 33(S1): 31-36.
	CAI C J, WANG H G, AN H, SHI Y C, HUANG W J, MA Z H. Remote sensing research on monitoring technology of wheat stripe rust. Journal of Northwest A & F University (Natural Science Edition), 2005, 33(S1): 31-36. (in Chinese)
[19]	蒋金豹, 陈云浩, 黄文江, 李京. 冬小麦条锈病严重度高光谱遥感反演模型研究. 南京农业大学学报, 2007, 30(3): 63-67.
	JIANG J B, CHEN Y H, HUANG W J, LI J. Study on hyperspectral remote sensing retriveral models about winter wheat stripe rust severity. Journal of Nanjing Agricultural University, 2007, 30(3): 63-67. (in Chinese)
[20]	刘佳, 王利民, 杨福刚, 杨玲波. 基于高光谱微分指数监测春玉米大斑病的研究. 中国农学通报, 2019, 35(6): 143-150. doi: 10.11924/j.issn.1000-6850.casb18090024
	LIU J, WANG L M, YANG F G, YANG L B. Spring corn leaf blight monitoring based on hyperspectral derivative index. Chinese Agricultural Science Bulletin, 2019, 35(6): 143-150. (in Chinese) doi: 10.11924/j.issn.1000-6850.casb18090024
[21]	REN Y, HUANG W J, YE H C, ZHOU X F, MA H Q, DONG Y Y, SHI Y, GENG Y, HUANG Y R, JIAO Q J, XIE Q Y. Quantitative identification of yellow rust in winter wheat with a new spectral index: Development and validation using simulated and experimental data. International Journal of Applied Earth Observation and Geoinformation, 2021, 102: 102384. doi: 10.1016/j.jag.2021.102384
[22]	HUANG W J, LAMB D W, NIU Z, ZHANG Y J, LIU L Y, WANG J H. Identification of yellow rust in wheat using in-situ spectral reflectance measurements and airborne hyperspectral imaging. Precision Agriculture, 2007, 8: 187-197. doi: 10.1007/s11119-007-9038-9
[23]	CAO C L, WANG T L, GAO M F, LI Y, LI D D, ZHANG H J. Hyperspectral inversion of nitrogen content in maize leaves based on different dimensionality reduction algorithms. Computers and Electronics in Agriculture, 2021, 190: 106461. doi: 10.1016/j.compag.2021.106461
[24]	ZHANG J C, LIN Y, WANG J H, HUANG W J, CHEN L P, ZHANG D Y. Spectroscopic leaf level detection of powdery mildew for winter wheat using continuous wavelet analysis. Journal of Integrative Agriculture, 2012, 11(9): 1474-1484. doi: 10.1016/S2095-3119(12)60147-6
[25]	ZHANG J, JING X, SONG X Y, ZHANG T, DUAN W N, SU J. Hyperspectral estimation of wheat stripe rust using fractional order differential equations and Gaussian process methods. Computers and Electronics in Agriculture, 2023, 206: 107671. doi: 10.1016/j.compag.2023.107671
[26]	TIAN L, XUE B W, WANG Z Y, LI D, YAO X, CAO Q, ZHU Y, CAO W X, CHENG T. Spectroscopic detection of rice leaf blast infection from asymptomatic to mild stages with integrated machine learning and feature selection. Remote Sensing of Environment, 2021, 257: 112350. doi: 10.1016/j.rse.2021.112350
[27]	ZHANG J C, WANG N, YUAN L, CHEN F N, WU K H. Discrimination of winter wheat disease and insect stresses using continuous wavelet features extracted from foliar spectral measurements. Biosystems Engineering, 2017, 162: 20-29. doi: 10.1016/j.biosystemseng.2017.07.003
[28]	高媛, 竞霞, 刘良云, 白宗璠. 基于多核支持向量机的小麦条锈病遥感监测研究. 麦类作物学报, 2020, 40(1): 118-126.
	GAO Y, JING X, LIU L Y, BAI Z F. Remote sensing monitoring of wheat stripe rust based on multiple kernel SVM. Journal of Triticeae Crops, 2020, 40(1): 118-126. (in Chinese)
[29]	MUSTAFA G, ZHENG H, LI W, YIN Y, WANG Y, ZHOU M, LIU P, BILAL M, JIA H, LI G, et al. Fusarium head blight monitoring in wheat ears using machine learning and multimodal data from asymptomatic to symptomatic periods. Frontiers in Plant Science, 2023, 13: 1102341. doi: 10.3389/fpls.2022.1102341
[30]	HUANG L S, LIU Y, HUANG W J, DONG Y Y, MA H Q, WU K, GUO A T. Combining random forest and XGBoost methods in detecting early and mid-term winter wheat stripe rust using canopy level hyperspectral measurements. Agriculture, 2022, 12(1): 74. doi: 10.3390/agriculture12010074
[31]	黄木易, 王纪华, 黄文江, 黄义德, 赵春江, 万安民. 冬小麦条锈病的光谱特征及遥感监测. 农业工程学报, 2003, 19(6): 154-158.
	HUANG M Y, WANG J H, HUANG W J, HUANG Y D, ZHAO C J, WAN A M. Hyperspectral character of stripe rust on winter wheat and monitoring by remote sensing. Transactions of the Chinese Society of Agricultural Engineering, 2003, 19(6): 154-158. (in Chinese)
[32]	ZHENG H B, CHENG T, ZHOU M, LI D, YAO X, TIAN Y C, CAO W X, ZHU Y. Improved estimation of rice aboveground biomass combining textural and spectral analysis of UAV imagery. Precision Agriculture, 2019, 20: 611-629. doi: 10.1007/s11119-018-9600-7
[33]	SPEISER J L, MILLER M E, TOOZE J, IP E. A comparison of random forest variable selection methods for classification prediction modeling. Expert Systems with Applications, 2019, 134: 93-101. doi: 10.1016/j.eswa.2019.05.028 pmid: 32968335
[34]	GENUER R, POGGI J M, TULEAU-MALOT C. Variable selection using random forests. Pattern Recognition Letters, 2010, 31(14): 2225-2236. doi: 10.1016/j.patrec.2010.03.014
[35]	HUANG W L, MIN W K, DING J Q, LIU Y C, HU Y, NI W J, SHEN H F. Forest height mapping using inventory and multi-source satellite data over Hunan Province in southern China. Forest Ecosystems, 2022, 9: 100006. doi: 10.1016/j.fecs.2022.100006
[36]	EZENARRO J, SCHORN-GARCÍA D, ACEÑA L, MESTRES M, BUSTO O, BOQUÉ R. J-Score: A new joint parameter for PLSR model performance evaluation of spectroscopic data. Chemometrics and Intelligent Laboratory Systems, 2023: 104883.
[37]	SMIGAJ M, GAULTON R, SUÁREZ J C, BARR S L. Canopy temperature from an unmanned aerial vehicle as an indicator of tree stress associated with red band needle blight severity. Forest Ecology and Management, 2019, 433: 699-708. doi: 10.1016/j.foreco.2018.11.032
[38]	DOS SANTOS F R, DE OLIVEIRA J F, BONA E, DOS SANTOS J V F, BARBOZA G M, MELQUIADES F L. EDXRF spectral data combined with PLSR to determine some soil fertility indicators. Microchemical Journal, 2020, 152: 104275. doi: 10.1016/j.microc.2019.104275
[39]	YUAN L, HUANG Y B, LORAAMM R W, NIE C W, WANG J H, ZHANG J C. Spectral analysis of winter wheat leaves for detection and differentiation of diseases and insects. Field Crops Research, 2014, 156: 199-207. doi: 10.1016/j.fcr.2013.11.012
[40]	GUO A T, HUANG W J, DONG Y Y, YE H C, MA H Q, LIU B, WU W B, REN Y, RUAN C, GENG Y. Wheat yellow rust detection using UAV-based hyperspectral technology. Remote Sensing, 2021, 13(1): 123. doi: 10.3390/rs13010123
[41]	AZADBAKHT M, ASHOURLOO D, AGHIGHI H, RADIOM S, ALIMOHAMMADI A. Wheat leaf rust detection at canopy scale under different LAI levels using machine learning techniques. Computers and Electronics in Agriculture, 2019, 156: 119-128. doi: 10.1016/j.compag.2018.11.016
[42]	RUAN C, DONG Y Y, HUANG W J, HUANG L S, YE H C, MA H Q, GUO A T, SUN R Q. Integrating remote sensing and meteorological data to predict wheat stripe rust. Remote Sensing, 2022, 14(5): 1221. doi: 10.3390/rs14051221
[43]	JING X, ZOU Q, YAN J M, DONG Y Y, LI B Y. Remote sensing monitoring of winter wheat stripe rust based on mRMR-XGBoost algorithm. Remote Sensing, 2022, 14(3): 756. doi: 10.3390/rs14030756
[44]	SHAFI U, MUMTAZ R, HAQ I U, HAFEEZ M, IQBAL N, SHAUKAT A, ZAIDI S M H, MAHMOOD Z. Wheat yellow rust disease infection type classification using texture features. Sensors, 2021, 22(1): 146. doi: 10.3390/s22010146
[45]	YAO Z F, LEI Y, HE D J. Early visual detection of wheat stripe rust using visible/near-infrared hyperspectral imaging. Sensors, 2019, 19(4): 952. doi: 10.3390/s19040952
[46]	RUAN C, DONG Y Y, HUANG W J, HUANG L S, YE H C, MA H Q, GUO A T, REN Y. Prediction of wheat stripe rust occurrence with time series sentinel-2 images. Agriculture, 2021, 11(11): 1079. doi: 10.3390/agriculture11111079
[47]	JU C X, CHEN C, LI R, ZHAO Y Y, ZHONG X C, SUN R L, LIU T, SUN C M. Remote sensing monitoring of wheat leaf rust based on UAV multispectral imagery and the BPNN method. Food and Energy Security, 2023: e477.
[48]	FUSHIKI T. Estimation of prediction error by using K-fold cross-validation. Statistics and Computing, 2011, 21: 137-146.
[49]	竞霞, 白宗璠, 高媛, 刘良云. 利用随机森林法协同SIF和反射率光谱监测小麦条锈病. 农业工程学报, 2019, 35(13): 154-161.
	JING X, BAI Z F, GAO Y, LIU L Y. Wheat stripe rust monitoring by random forest algorithm combined with SIF and reflectance spectrum. Transactions of the Chinese Society of Agricultural Engineering, 2019, 35(13): 154-161. (in Chinese)
[50]	PALLATHADKA H, RAVIPATI P, SAJJA G S, PHASINAM K, KASSANUK T, SANCHEZ D T, PRABHU P. Application of machine learning techniques in rice leaf disease detection. Materials Today: Proceedings, 2022, 51: 2277-2280.
[51]	JACKULIN C, MURUGAVALLI S. A comprehensive review on detection of plant disease using machine learning and deep learning approaches. Measurement: Sensors, 2022, 24: 100441. doi: 10.1016/j.measen.2022.100441
[52]	SARKAR C, GUPTA D, GUPTA U, HAZARIKA B B. Leaf disease detection using machine learning and deep learning: Review and challenges. Applied Soft Computing, 2023, 145: 110534. doi: 10.1016/j.asoc.2023.110534
[53]	竞霞, 张腾, 邹琴, 闫菊梅, 董莹莹. 基于分数阶微分光谱指数的小麦条锈病遥感监测模型构建. 农业工程学报, 2021, 37(17): 142-151.
	JING X, ZHANG T, ZOU Q, YAN J M, DONG Y Y. Construction of remote sensing monitoring model of wheat stripe rust based on fractional-order differential spectral index. Transactions of the Chinese Society of Agricultural Engineering, 2021, 37(17): 142-151. (in Chinese)
[54]	蒋金豹, 陈云浩, 黄文江. 利用高光谱红边与黄边位置距离识别小麦条锈病. 光谱学与光谱分析, 2010, 30(6): 1614-1618.
	JIANG J B, CHEN Y H, HUANG W J. Using the distance between hyperspectral red edge position and yellow edge position to identify wheat yellow rust disease. Spectroscopy and Spectral Analysis, 2010, 30(6): 1614-1618. (in Chinese)
[55]	竞霞, 闫菊梅, 邹琴, 李冰玉, 杜凯奇. 基于CC-MPA特征优选算法的小麦条锈病遥感监测. 农业机械学报, 2022, 53(9): 217-225, 304.
	JING X, YAN J M, ZOU Q, LI B Y, DU K Q. Remote sensing monitoring of wheat stripe rust based on CC-MPA feature optimization algorithm. Transactions of the Chinese Society for Agricultural Machinery, 2022, 53(9): 217-225, 304. (in Chinese)
[56]	BREIMAN L. Random forests. Machine Learning, 2001, 45: 5-32. doi: 10.1023/A:1010933404324
[57]	张春兰, 杨贵军, 李贺丽, 汤伏全, 刘畅, 张丽妍. 基于随机森林算法的冬小麦叶面积指数遥感反演研究. 中国农业科学, 2018, 51(5): 855-867. doi: 10.3864/j.issn.0578-1752.2018.05.005.
	ZHANG C L, YANG G J, LI H L, TANG F Q, LIU C, ZHANG L Y. Remote sensing inversion of leaf area index of winter wheat based on random forest algorithm. Scientia Agricultura Sinica, 2018, 51(5): 855-867. doi: 10.3864/j.issn.0578-1752.2018.05.005. (in Chinese)
[58]	王丽爱, 周旭东, 朱新开, 郭文善. 基于HJ-CCD数据和随机森林算法的小麦叶面积指数反演. 农业工程学报, 2016, 32(3): 149-154.
	WANG L A, ZHOU X D, ZHU X K, GUO W S. Inverting wheat leaf area index based on HJ-CCD remote sensing data and random forest algorithm. Transactions of the Chinese Society of Agricultural Engineering, 2016, 32(3): 149-154. (in Chinese)
[59]	樊意广, 冯海宽, 刘杨, 边明博, 孟炀, 杨贵军. 基于冠层光谱特征和株高的马铃薯植株氮含量估算. 农业机械学报, 2022, 53(6): 202-208, 294.
	FAN Y G, FENG H K, LIU Y, BIAN M B, MENG Y, YANG G J. Estimation of potato plant nitrogen content based on canopy spectral characteristics and plant height. Transactions of the Chinese Society for Agricultural Machinery, 2022, 53(6): 202-208, 294. (in Chinese)
[60]	夏天, 吴文斌, 周清波, 周勇. 冬小麦叶面积指数高光谱遥感反演方法对比. 农业工程学报, 2013, 29(3): 139-147.
	XIA T, WU W B, ZHOU Q B, ZHOU Y. Comparison of two inversion methods for winter wheat leaf area index based on hyperspectral remote sensing. Transactions of the Chinese Society of Agricultural Engineering, 2013, 29(3): 139-147. (in Chinese)
[61]	王圆圆, 李贵才, 张立军, 范锦龙. 利用偏最小二乘回归从冬小麦冠层光谱提取叶片含水量. 光谱学与光谱分析, 2010, 30(4): 1070-1074.
	WANG Y Y, LI G C, ZHANG L J, FAN J L. Retrieva of leaf water content of winter wheat from canopy hyperspectral data using partial least square regression. Spectroscopy and Spectral Analysis, 2010, 30(4): 1070-1074. (in Chinese)
[62]	蒋小敏. 小麦条锈病严重度近地面遥感估算方法研究[D]. 淮南: 安徽理工大学, 2021.
	JIANG X M. Study on the estimation method of the severity of wheat stripe rust by near-ground remote sensing[D]. Huainan: Anhui University of Science and Technology, 2021. (in Chinese)
[63]	冯子恒, 宋莉, 张少华, 井宇航, 段剑钊, 贺利, 尹飞, 冯伟. 基于无人机多光谱和热红外影像信息融合的小麦白粉病监测. 中国农业科学, 2022, 55(5): 890-906. doi: 10.3864/j.issn.0578-1752.2022.05.005.
	FENG Z H, SONG L, ZHANG S H, JING Y H, DUAN J Z, HE L, YIN F, FENG W. Wheat powdery mildew monitoring based on information fusion of multi-spectral and thermal infrared images acquired with an unmanned aerial vehicle. Scientia Agricultura Sinica, 2022, 55(5): 890-906. doi: 10.3864/j.issn.0578-1752.2022.05.005. (in Chinese)

数据集 Dataset	预测变量个数 The number of prediction variables	运行时间 Time (min)
VSURF-OR	9	30.5
VSURF-FD	17	15.3
VSURF-CA-OR	7	13.4
VSURF-CA-FD	6	8.1