基于全局敏感性分析与机器学习的冬小麦叶面积指数估算

doi:10.3969/j.issn.1004-1524.2022.09.21

浙江农业学报 ›› 2022, Vol. 34 ›› Issue (9): 2020-2031.DOI: 10.3969/j.issn.1004-1524.2022.09.21

基于全局敏感性分析与机器学习的冬小麦叶面积指数估算

郭晗¹^,²(), 陆洲²^,^*(), 徐飞飞², 罗明², 张序¹^,^*()

1.苏州科技大学环境科学与工程学院,江苏苏州 215009
2.中国科学院地理科学与资源研究所,北京 100101

收稿日期:2021-04-14 出版日期:2022-09-25 发布日期:2022-09-30
作者简介:张序,E-mail: xu1960zhang@sina.com
*陆洲,E-mail: luz@lreis.ac.cn;
郭晗(1994—),女,江苏徐州人,硕士研究生,主要从事农业高光谱遥感估算研究。E-mail: 15501699250@163.com
通讯作者: 陆洲,张序
基金资助:
国家重点研发计划(2016YFD0300201);苏州市科技计划(SNG2018100)

Leaf area index estimation of winter wheat based on global sensitivity analysis and machine learning

GUO Han¹^,²(), LU Zhou²^,^*(), XU Feifei², LUO Ming², ZHANG Xu¹^,^*()

1. School of Environmental Science and Engineering, Suzhou University of Science and Technology, Suzhou 215009, Jiangsu, China
2. Institute of Geographic Sciences and Natural Resources Research, Chines Academy of Sciences, Beijing 100101, China

Received:2021-04-14 Online:2022-09-25 Published:2022-09-30
Contact: LU Zhou,ZHANG Xu

摘要/Abstract

摘要：

在小麦叶面积指数(leaf area index,LAI)的估算过程中,光谱变量与机器学习算法(MLs)相结合的方法具有较好的性能,但由于输入参数过多会导致数据冗余,使得计算效率降低。为了提高LAI估算的精度和MLs的计算效率,本研究提出了全局敏感性分析(global sensitivity analysis,GSA)与MLs相结合的方法(简称GSA-MLs)。首先,基于PROSAIL模拟数据集,利用GSA量化植被生长参数对Sentinel-2光谱变量的影响;此外利用4种变量筛选策略对所有光谱变量进行排序,并选择最优变量作为MLs的输入参数。然后,通过偏最小二乘回归(partial least square regression,PLSR)、支持向量机(support vector machine,SVM)和随机森林(random forest,RF)3种MLs对小麦叶面积指数(LAI)进行估算。结果表明:红边植被指数主要受叶绿素含量的影响,而短波红外相关的植被指数主要受等效水厚度的影响,所有光谱变量均会受到参数之间的交互作用。SLAI-SInteraction筛选得到的30个光谱变量在估算小麦LAI表现最佳(R²=0.94,RMSE=0.38)。并且在模型反演过程中运行时间缩短了54.13%。本研究提出了全局敏感性分析与机器学习相结合的方法,该方法提高了机器学习法估算LAI精度以及应用过程中的计算效率和机理性,该方法有较好的适用性。

关键词: 全局敏感性分析, 机器学习, 小麦, 叶面积指数

Abstract:

In the estimation process of wheat leaf area index (LAI), the method combining spectral variables with machine learning algorithm (MLs) has better performance. However, too many input parameters will lead to data redundancy and reduce the computing efficiency. In order to improve the accuracy of LAI estimation and the efficiency of MLs calculation, a method combining global sensitivity analysis (GSA) and MLs(GSA-MLs) was proposed in this study. Firstly, based on the PROSAIL simulation dataset, GSA was used to quantify the effects of vegetation growth parameters on Sentinel-2 spectral variables. In addition, four variable screening strategies were used to sort all spectral variables, and the optimal variable was selected as the input parameter of MLs. And then, partial least square regression (PLSR), support vector machine (SVM) and random forest (RF), three MLs were used to estimate wheat leaf area index (LAI). The results showed that the red edge vegetation index was mainly affected by chlorophyll content, while the short-wave infrared vegetation index was mainly affected by equivalent water thickness. All spectral variables were subject to interaction between parameters. The 30 spectral variables screened by SLAI-SInteraction performed best in estimating wheat LAI (R²=0.94, RMSE=0.38). Moreover, the running time of model inversion was shortened by 54.13%. This study proposed a combination of global sensitivity analysis and machine learning. In addition to improving the accuracy of LAI estimation by machine learning method and the calculation efficiency in the application process, the machine theory in the application process of machine learning was improved and had good applicability.

Key words: global sensitivity analysis, machine learning, wheat, leaf area index

中图分类号:

S512.1
S330

郭晗, 陆洲, 徐飞飞, 罗明, 张序. 基于全局敏感性分析与机器学习的冬小麦叶面积指数估算[J]. 浙江农业学报, 2022, 34(9): 2020-2031.

GUO Han, LU Zhou, XU Feifei, LUO Ming, ZHANG Xu. Leaf area index estimation of winter wheat based on global sensitivity analysis and machine learning[J]. Acta Agriculturae Zhejiangensis, 2022, 34(9): 2020-2031.

图/表 12

图1 研究区及地面调查样点分布

Fig.1 Location of study area and the distribution of ground samples

表1 Sentinel-2波段信息

Table 1 Sentinel-2 band information

波段 Bands	中心波长 Central wavelength/nm	空间分辨率 Space resolution/m
B1-Coastal aerosol	443	60
B2-Blue	490	10
B3-Green	560	10
B4-Red	665	10
B5-red edge (RE-1)	705	20
B6-red edge (RE-2)	740	20
B7-red edge (RE-3)	783	20
B8-NIR	842	10
B8a-Narrow NIR (NNIR)	865	20
B9-water vapour	945	60
B10-SWIR-Cirrus	1 380	60
B11-SWIR-1	1 610	20
B12-SWIR-2	2 190	20

图2 利用GSA-ML估算小麦LAI的方法

Fig.2 Wheat LAI estimation by using GSA-MLs

表2 PROSAIL模型的参数设置

Table 2 Parameter settings of PROSAIL model

参数Parameter	范围Range	$X -$ ±s±σ
结构系数Structure coefficient (N)	1.3~1.7	1.5±0.1
叶绿素含量Chlorophyll content (Cab)/(μg·cm^-2)	20~70	45±14
类胡萝卜素含量Carotenoid content (Car)/(μg·cm^-2)	5.0~17.5	—
等效水厚度Equivalent water thickness (Cw)/cm	0.001~0.1	0.050 5±0.028 6
叶片含水量Leaf water content (Cm)/(g·cm^-2)	0.003~0.011	0.007±0.002
褐色素含量Brown pigment content (Cbp)	0.05	—
平均叶倾角Average leaf angle (Lidfa)/(°)	35~70	52.5±10.1
叶面积指数Leaf area index (LAI)	0.1~9.0	4.550 1±2.569 1
热点Hot spot (hspot)	0.05~0.5	0.275±0.130
土壤亮度系数Soil brightness parameter (Psoil)	0~1	0.5±0.3
太阳天顶角Solar zenith angle (tts)/(°)	25	—
观察者天顶角Observer zenith angle (tto)/(°)	30	—
方位Azimuth (psi)/(°)	45	—

表2 PROSAIL模型的参数设置

Table 2 Parameter settings of PROSAIL model

参数Parameter	范围Range	$X -$ ±s±σ
结构系数Structure coefficient (N)	1.3~1.7	1.5±0.1
叶绿素含量Chlorophyll content (Cab)/(μg·cm^-2)	20~70	45±14
类胡萝卜素含量Carotenoid content (Car)/(μg·cm^-2)	5.0~17.5	—
等效水厚度Equivalent water thickness (Cw)/cm	0.001~0.1	0.050 5±0.028 6
叶片含水量Leaf water content (Cm)/(g·cm^-2)	0.003~0.011	0.007±0.002
褐色素含量Brown pigment content (Cbp)	0.05	—
平均叶倾角Average leaf angle (Lidfa)/(°)	35~70	52.5±10.1
叶面积指数Leaf area index (LAI)	0.1~9.0	4.550 1±2.569 1
热点Hot spot (hspot)	0.05~0.5	0.275±0.130
土壤亮度系数Soil brightness parameter (Psoil)	0~1	0.5±0.3
太阳天顶角Solar zenith angle (tts)/(°)	25	—
观察者天顶角Observer zenith angle (tto)/(°)	30	—
方位Azimuth (psi)/(°)	45	—

表3 用于估算小麦LAI的植被指数

Table 3 Vegetation index for estimation of wheat LAI

植被指数 Vegetation index	计算公式 Calculation formula	参考文献 Reference
归一化植被指数Normalized difference vegetation index (NDVI)	(NIR-R))/(NIR+R)	[19]
标准化差异红边指数Normalized difference red-edge index (NDRE)	(NIR-RE)/(NIR+RE)	[20]
比值植被指数Ratio vegetation index (RVI)	NIR/R	[21]
红边比值植被指数Red-edge ratio vegetation index (RERVI)	NIR/RE	[22]
植被指数Difference vegetation index (DVI)	NIR-R	[23]
红边差植被指数Red-edge difference vegetation index (REDVI)	NIR-RE	[19]
绿色植被指数Green difference vegetation index(GDVI)	NIR-G	[19]
红边绿差植被指数Red edge green difference vegetation index (REGDVI)	RE-G	[19]
绿化率植被指数Green ratio vegetation index(GRVI)	NIR/G	[24]
红边绿比植被指数Red edge green ration vegetation index (REGRVI)	RE/G	[1]
绿色归一化植被指数Green normalized difference vegetation index (GNDVI)	(NIR-G)/(NIR+G)	[21]
红边绿归一化差值植被指数	(RE-G)/(RE+G)	[25]
Red edge green normalized difference vegetation index (REGNDVI)
增强型植被指数Enhanced vegetation index (EVI)	2.5×(NIR-R)/(NIR+6·R-7.5·G+1))	[26]
改良增强植被指数Modified enhanced vegetation index (MEVI)	2.5×(NIR-RE)/(NIR+6·RE-7.5·G+1)	[27]
土壤矫正植被指数Soil-adjusted vegetation index (SAVI)	(NIR-R)/(NIR+R+0.25)+0.25	[28]
土壤矫正红边指数Soil-adjusted red-edge index (SARE)	(NIR-RE)/(NIR+R+0.25)+0.25	[29]
绿色叶绿素指数Green chlorophyll index (CIg)	(NIR-G)/G	[30]
叶绿素指数Chlorophyll index (CIre)	(NIR-RE)/RE	[30]
归一化水体指数Normalized difference water index (NDWI)	(NIR-SWIR)/(NIR+SWIR)	[31]
水分胁迫指数Moisture stress index (MSI)	SWIR/NIR	[32]

表4 单波段反射率及植被指数与LAI相关性

Table 4 Performance of Sentinel-2 spectral variables in LAI estimation

变量 Variable	精度 R²	均方根误差 RMSE	变量 Variable	精度 R²	均方根误差 RMSE	变量 Variable	精度 R²	均方根误差 RMSE
B	0.251	1.124	GRVI	0.560	1.214	REGNDVI3	0.343	1.130
G	0.177	1.274	GNDVI	0.547	1.172	REGRVI2	0.298	1.191
R	0.373	1.207	SAVI	0.512	1.063	REDVI3	0.286	1.039
RE1	0.083	1.130	RVI	0.511	1.187	REGDVI3	0.279	1.003
RE2	0.136	1.000	MTVI2	0.504	1.079	REGNDVI2	0.271	1.151
RE3	0.255	0.982	EVI	0.496	1.010	SARE3	0.181	1.080
NIR	0.463	0.979	NDVI	0.492	1.132	REGDVI2	0.180	1.023
NNIR	0.286	0.958	GDVI	0.491	1.003	NDRE3	0.155	1.086
SWIR1	0.115	1.333	DVI	0.486	1.002	CIre3	0.153	1.082
SWIR2	0.303	1.548	REDVI1	0.484	1.003	RERVI3	0.153	1.082
SARE2	0.707	0.907	SARE1	0.483	1.067	MEVI2	0.087	1.105
NDRE2	0.681	0.954	MEVI1	0.483	1.018	MEVI3	0.062	1.084
REDVI2	0.678	0.896	NDRE1	0.441	1.131	REGDVI1	0.009	1.049
CIre2	0.667	0.950	CIre1	0.439	1.108	REGRVI1	0.003	1.067
RERVI2	0.667	0.950	RERVI1	0.439	1.108	REGNDVI1	0.003	1.066
Cig	0.560	1.214	REGRVI3	0.365	1.172

图3 不同光谱变量全局敏感性分析结果

Fig.3 Sensitivity of different vegetation growth parameters to different spectral variables

表5 不同策略光谱变量排序结果

Table 5 Different strategies for sorting spectral variables

序号 No.	策略1 Strategy 1(S_LAI)	策略2 Strategy 2(S_LAI+S_Cab)	策略3 Strategy 3(S_LAI-S_Interaction)	策略4 Strategy 4(S_LAI+S_Cab-S_Interaction)
1	MTVI2	SARE1	MTVI2	MTVI2
2	SAVI	NDRE1	SAVI	SARE1
3	NDVI	MTVI2	NDVI	NDRE1
4	RVI	GNDVI	RVI	SAVI
5	NDRE3	REGNDVI3	DVI	RVI
6	CIRE3	REGNDVI2	REDVI1	SARE2
7	RERVI3	SAVI	REGDVI3	GNDVI
8	DVI	RVI	SARE1	REGNDVI3
9	SARE3	REGRVI2	GDVI	REGNDVI2
10	REDVI1	CIRE1	NDWI2	REGRVI2
11	REGDVI3	RERVI1	SARE3	NDRE2
12	MSI2	REGRVI3	NDRE3	CIRE1
13	SARE1	NDVI	REGDVI2	RERVI1
14	NDWI2	CIg	CIRE3	CIRE2
15	GDVI	GRVI	RERVI3	RERVI2
16	REGDVI2	SARE2	MSI2	REGRVI3
17	REGNDVI2	REGRVI1	EVI	CIg
18	REGNDVI3	REGNDVI1	REGNDVI2	GRVI
19	EVI	NDRE2	REGNDVI3	REDVI1
20	GNDVI	CIRE2	GNDVI	REGRVI1
21	MEVI1	RERVI2	NDRE1	REDVI2
22	R	REDVI2	MEVI1	REGNDVI1
23	NDRE1	REDVI1	RE-3	NDVI
24	RE-3	NDRE3	NIR	REGDVI3
25	NIR	CIRE3	NNIR	DVI
26	NNIR	RERVI3	REDVI2	GDVI
27	MSI1	REGDVI3	MSI1	EVI
28	REGNDVI1	EVI	REGNDVI1	NDWI2
29	REGRVI1	DVI	NDWI1	SARE3
30	REDVI2	GDVI	REGRVI1	REGDVI2

表6 冬小麦LAI估算模型对比

Table 6 Comparison of wheat LAI estimation by GSA-MLs

变量数量 Number of variables	策略Strategy	S_LAI		S_LAI+S_Cab		S_LAI-S_Interaction		S_LAI+S_Cab-S_Interaction
变量数量 Number of variables	模型Modeling	R²	RMSE	R²	RMSE	R²	RMSE	R²	RMSE
10	GSA-PLSR	0.69	0.84	0.69	0.84	0.69	0.84	0.70	0.82
	GSA-SVM	0.40	1.17	0.41	1.16	0.40	1.17	0.41	1.16
	GSA-RF	0.91	0.45	0.90	0.48	0.91	0.46	0.92	0.42
20	GSA-PLSR	0.76	0.73	0.75	0.75	0.76	0.73	0.79	0.69
	GSA-SVM	0.40	1.17	0.44	1.13	0.40	1.17	0.44	1.13
	GSA-RF	0.92	0.44	0.92	0.42	0.92	0.44	0.92	0.42
30	GSA-PLSR	0.87	0.55	0.93	0.40	0.88	0.53	0.92	0.44
	GSA-SVM	0.40	1.17	0.44	1.12	0.40	1.16	0.44	1.12
	GSA-RF	0.93	0.40	0.93	0.40	0.94	0.38	0.94	0.38

表7 MLs法估算小麦LAI的比较

Table 7 Comparison of wheat LAI estimation by MLs

机器学习法MLs	R²	RMSE
PLSR	0.81	0.31
SVM	0.41	1.06
RF	0.92	0.40

表8 不同估算模型应用过程中的计算机运行时间

Table 8 Computer running time in the application process of different estimation models s

建模方法 Modeling methods	机器学习 MLs	全局敏感性机器学习 GSA-MLs
PLSR	487.772	226.270
SVM	495.957	227.190
RF	569.327	261.130

图4 由GSA-RF反演的叶面积指数分布图

Fig.4 LAI map generated by GSA-RF

参考文献 39

[1]	ZHUO W, HUANG J X, GAO X R, et al. Prediction of winter wheat maturity dates through assimilating remotely sensed leaf area index into crop growth model[J]. Remote Sensing, 2020, 12(18): 2896. DOI URL
[2]	LI H, CHEN Z X, JIANG Z W, et al. Comparative analysis of GF-1, HJ-1, and Landsat-8 data for estimating the leaf area index of winter wheat[J]. Journal of Integrative Agriculture, 2017, 16(2): 266-285. DOI URL
[3]	DONG T F, LIU J G, SHANG J L, et al. Assessment of red-edge vegetation indices for crop leaf area index estimation[J]. Remote Sensing of Environment, 2019, 222: 133-143. DOI URL
[4]	HOJAS GASCÓN L, CECCHERINI G, GARCÍA HARO F, et al. The potential of high resolution (5 m) RapidEye optical data to estimate above ground biomass at the national level over Tanzania[J]. Forests, 2019, 10(2): 107. DOI URL
[5]	AZADBAKHT M, ASHOURLOO D, AGHIGHI H, et al. Wheat leaf rust detection at canopy scale under different LAI levels using machine learning techniques[J]. Computers and Electronics in Agriculture, 2019, 156: 119-128. DOI URL
[6]	PADALIA H, SINHA S K, BHAVE V, et al. Estimating canopy LAI and chlorophyll of tropical forest plantation (North India) using Sentinel-2 data[J]. Advances in Space Research, 2020, 65(1): 458-469. DOI URL
[7]	CUI B, ZHAO Q J, HUANG W J, et al. Leaf chlorophyll content retrieval of wheat by simulated RapidEye, Sentinel-2 and EnMAP data[J]. Journal of Integrative Agriculture, 2019, 18(6): 1230-1245. DOI
[8]	ESTÉVEZ J, VICENT J, RIVERA-CAICEDO J P, et al. Gaussian processes retrieval of LAI from Sentinel-2 top-of-atmosphere radiance data[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2020, 167: 289-304. DOI URL
[9]	王丽爱, 周旭东, 朱新开, 等. 基于HJ-CCD数据和随机森林算法的小麦叶面积指数反演[J]. 农业工程学报, 2016, 32(3): 149-154.
	WANG L A, ZHOU X D, ZHU X K, et al. Inverting wheat leaf area index based on HJ-CCD remote sensing data and random forest algorithm[J]. Transactions of the Chinese Society of Agricultural Engineering, 2016, 32(3): 149-154. (in Chinese with English abstract)
[10]	LI X C, ZHANG Y J, LUO J H, et al. Quantification winter wheat LAI with HJ-1CCD image features over multiple growing seasons[J]. International Journal of Applied Earth Observation and Geoinformation, 2016, 44: 104-112. DOI URL
[11]	WANG L, CHANG Q R, LI F L, et al. Effects of growth stage development on paddy rice leaf area index prediction models[J]. Remote Sensing, 2019, 11(3): 361. DOI URL
[12]	ABDEL-RAHMAN E M, AHMED F B, ISMAIL R. Random forest regression and spectral band selection for estimating sugarcane leaf nitrogen concentration using EO-1 Hyperion hyperspectral data[J]. International Journal of Remote Sensing, 2013, 34(2): 712-728. DOI URL
[13]	FANG H L, BARET F, PLUMMER S, et al. An overview of global leaf area index (LAI): methods, products, validation, and applications[J]. Reviews of Geophysics, 2019, 57(3): 739-799. DOI URL
[14]	DE LOS CAMPOS G, GIANOLA D, ROSA G J M. Reproducing kernel Hilbert spaces regression: a general framework for genetic evaluation[J]. Journal of Animal Science, 2009, 87(6): 1883-1887. DOI PMID
[15]	SOBOL I. On sensitivity estimation for nonlinear mathematical models[J]. Matem Modelirovanie, 1990, 2(1): 112-118.
[16]	SALTELLI A. Sensitivity analysis: Could better methods be used?[J]. Journal of Geophysical Research: Atmospheres, 1999, 104(D3): 3789-3793. DOI URL
[17]	SUN Y H, QIN Q M, REN H Z, et al. Red-edge band vegetation indices for leaf area index estimation from sentinel-2/MSI imagery[J]. IEEE Transactions on Geoscience and Remote Sensing, 2020, 58(2): 826-840. DOI URL
[18]	CHEN H Y, HUANG W J, LI W, et al. Estimation of LAI in winter wheat from multi-angular hyperspectral VNIR data: effects of view angles and plant architecture[J]. Remote Sensing, 2018, 10(10): 1630. DOI URL
[19]	TUCKER C J. Red and photographic infrared linear combinations for monitoring vegetation[J]. Remote Sensing of Environment, 1979, 8(2): 127-150. DOI URL
[20]	SIMS D A, GAMON J A. Relationships between leaf pigment content and spectral reflectance across a wide range of species, leaf structures and developmental stages[J]. Remote Sensing of Environment, 2002, 81(2/3): 337-354. DOI URL
[21]	BASSO M, STOCCHERO D, VENTURA BAYAN HENRIQUES R, et al. Proposal for an embedded system architecture using a GNDVI algorithm to support UAV-based agrochemical spraying[J]. Sensors, 2019, 19(24): 5397. DOI URL
[22]	VINCINI M, FRAZZI E. Active sensing of the N status of wheat using optimized wavelength combination: impact of seed rate, variety and growth stage[J]. Precision Agriculture, 2009.
[23]	JORDAN C F. Derivation of leaf-area index from quality of light on the forest floor[J]. Ecology, 1969, 50(4): 663-666. DOI URL
[24]	BUSCHMANN C, NAGEL E. In vivo spectroscopy and internal optics of leaves as basis for remote sensing of vegetation[J]. International Journal of Remote Sensing, 1993, 14(4): 711-722. DOI URL
[25]	ZHANG H X, LI Q Z, LIU J G, et al. Corrections to “image classification using RapidEye data: integration of spectral and textual features in a random forest classifier” [DEC 17 5334-5349][J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2018, 11(7): 2571. DOI URL
[26]	JIANG Z Y, HUETE A R, DIDAN K, et al. Development of a two-band enhanced vegetation index without a blue band[J]. Remote Sensing of Environment, 2008, 112(10): 3833-3845. DOI URL
[27]	JUSTICE C O, VERMOTE E, TOWNSHEND J R G, et al. The Moderate Resolution Imaging Spectroradiometer (MODIS): land remote sensing for global change research[J]. IEEE Transactions on Geoscience and Remote Sensing, 1998, 36(4): 1228-1249. DOI URL
[28]	HUETE A R. A soil-adjusted vegetation index (SAVI)[J]. Remote Sensing of Environment, 1988, 25(3): 295-309. DOI URL
[29]	ALI M, MONTZKA C, STADLER A, et al. Estimation and validation of RapidEye-based time-series of leaf area index for winter wheat in the rur catchment (Germany)[J]. Remote Sensing, 2015, 7(3): 2808-2831. DOI URL
[30]	CLEVERS J, KOOISTRA L, VAN DEN BRANDE M. Using sentinel-2 data for retrieving LAI and leaf and canopy chlorophyll content of a potato crop[J]. Remote Sensing, 2017, 9(5): 405. DOI URL
[31]	GAO B C. NDWI: a normalized difference water index for remote sensing of vegetation liquid water from space[J]. Remote Sensing of Environment, 1996, 58(3): 257-266. DOI URL
[32]	DORAISWAMY P C, THOMPSON D R. A crop moisture stress index for large areas and its application in the prediction of spring wheat phenology[J]. Agricultural Meteorology, 1982, 27(1/2): 1-15. DOI URL
[33]	NANNI M R, CEZAR E, SILVA JUNIOR C A D, et al. Partial least squares regression (PLSR) associated with spectral response to predict soil attributes in transitional lithologies[J]. Archives of Agronomy and Soil Science, 2018, 64(5): 682-695. DOI URL
[34]	翁永玲, 戚浩平, 方洪宾, 等. 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[J]. 土壤学报, 2010, 47(6): 1255-1263.
	WENG Y L, QI H P, FANG H B, et al. PLSR-based hyperspectral remote sensing retrieval of soil salinity of Chaka-Gonghe basin in Qinghai Province[J]. Acta Pedologica Sinica, 2010, 47(6): 1255-1263. (in Chinese with English abstract)
[35]	VAPNIK V N. The nature of statistical learning theory[M]. New York: Springer, 1999.
[36]	BUHMANN M D. Radial basis functions[M]. Cambridge: Cambridge University Press, 2003.
[37]	LIANG L, QIN Z H, ZHAO S H, et al. Estimating crop chlorophyll content with hyperspectral vegetation indices and the hybrid inversion method[J]. International Journal of Remote Sensing, 2016, 37(13): 2923-2949. DOI URL
[38]	MENG X T, BAO Y L, LIU J G, et al. Regional soil organic carbon prediction model based on a discrete wavelet analysis of hyperspectral satellite data[J]. International Journal of Applied Earth Observation and Geoinformation, 2020, 89: 102111. DOI URL
[39]	HOUBORG R, MCCABE M F. A hybrid training approach for leaf area index estimation via Cubist and random forests machine-learning[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2018, 135: 173-188. DOI URL

基于全局敏感性分析与机器学习的冬小麦叶面积指数估算

Leaf area index estimation of winter wheat based on global sensitivity analysis and machine learning

RichHTML

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

图/表 12

参考文献 39

相关文章 15

编辑推荐

Metrics

本文评价

[1]	张均, 张博, 胡碧博, 刘京亮, 张晓宇, 李春阳, 熊盛婷, 郭彬彬, 王秀存, 马超. 小麦SWEET和SUT家族基因鉴定与表达分析[J]. 浙江农业学报, 2025, 37(9): 1825-1839.
[2]	吴昊霖, 王淑珍, 朱祝军, 何勇. 基于近红外光谱技术和机器学习模型的基质氮含量快速检测[J]. 浙江农业学报, 2025, 37(5): 1159-1171.
[3]	刘胜男, 朱建义, 李明, 赵浩宇, 熊涛, 汤永禄, 周小刚, 李朝苏. 稻茬免耕带旋播种小麦的田间杂草防除效果与小麦产量[J]. 浙江农业学报, 2025, 37(10): 2129-2137.
[4]	杨晓雨, 马指挥, 魏青, 牛志鹏, 陈安琪, 胡正冲, 王林生. 一个小麦芒长基因的初步定位及候选基因预测[J]. 浙江农业学报, 2025, 37(1): 14-23.
[5]	沈峥嵘, 戴远兴, 郭留明, 汪芷瑶, 张恒木. 中国小麦花叶病毒(CWMV)外壳蛋白(CP)特异性抗体的制备与应用[J]. 浙江农业学报, 2024, 36(9): 2042-2050.
[6]	齐学礼, 李莹, 段俊枝. 耐盐基因在小麦耐盐基因工程中的应用[J]. 浙江农业学报, 2024, 36(6): 1447-1457.
[7]	李晶晶, 李闯, 路亚南, 郑文明. 小麦类硫素基因家族鉴定及表达分析[J]. 浙江农业学报, 2024, 36(4): 729-737.
[8]	张永彬, 李想, 满卫东, 刘明月, 樊继好, 胡皓然, 宋利杰, 刘玮佳. 融合Sentinel-1/2数据和机器学习算法的冬小麦产量估算方法研究[J]. 浙江农业学报, 2024, 36(12): 2812-2822.
[9]	刘永安, 黄业昌, 岳高红, 高锡腾, 邓立章, 潘彬荣. 优质小麦品种温麦10号籽粒蛋白质组学分析[J]. 浙江农业学报, 2024, 36(11): 2437-2446.
[10]	周丽丽, 冯海宽, 聂臣巍, 许晓斌, 刘媛, 孟麟, 薛贝贝, 明博, 梁齐云, 苏涛, 金秀良. 无人机观测时间对玉米冠层叶绿素密度估算的影响[J]. 浙江农业学报, 2024, 36(1): 18-31.
[11]	娄渊根, 李闯, 李晶晶, 邢国珍, 路亚南, 郑文明. 小麦HP基因家族鉴定和分析[J]. 浙江农业学报, 2023, 35(9): 2023-2032.
[12]	余桂红, 宋桂成, 张鹏, 王化敦, 范祥云. 十八个小麦品种(系)拔节期耐渍性的综合评价[J]. 浙江农业学报, 2023, 35(6): 1235-1242.
[13]	杨凯, 陈凯, 李红梅, 赵忠娟, 扈进冬, 李纪顺, 杨合同. 哈茨木霉LTR-2与产脲节杆菌DnL1-1协同对小麦茎基腐病的防治效果与机理[J]. 浙江农业学报, 2023, 35(6): 1385-1395.
[14]	任开明, 王犇, 杨文俊, 樊永惠, 张文静, 马尚宇, 黄正来. 施氮对稻茬弱筋小麦生长特性、品质与产量的影响[J]. 浙江农业学报, 2023, 35(4): 769-779.
[15]	鲁帅, 罗晓刚, 刘全伟, 张屹, 孟洋昊, 李洁, 张景来. 有机无机复混肥对小麦生长、土壤养分和重金属含量的影响[J]. 浙江农业学报, 2023, 35(4): 922-930.