Please wait a minute...
img

官方微信

遥感技术与应用  2021, Vol. 36 Issue (2): 411-419    DOI: 10.11873/j.issn.1004-0323.2021.2.0411
农业遥感专栏     
遥感探测小麦条锈病严重度的GBRT模型研究
金航1,2(),竞霞1(),高媛1,2,刘良云2
1.西安科技大学 测绘科学与技术学院,陕西 西安 710054
2.中国科学院遥感与数字地球研究所 数字地球重点实验室,北京 100094
GBRT Model for Detecting the Severity of Wheat Stripe Rust by Remote Sensing
Hang Jin1,2(),Xia Jing1(),Yuan Gao1,2,Liangyun Liu2
1.College of Geomatics,Xi’an University of Science and Technology,Xi’an 710054,China
2.Key Laboratory of Digital Earth Science,Institute of Remote Sensing and Digital Earth,Chinese Academy of Sciences,Beijing 100094,China
 全文: PDF(1315 KB)   HTML
摘要:

为了提高小样本数据模型的稳定性,构建具有更高精度和鲁棒性的小麦条锈病遥感探测模型。首先基于辐亮度和反射率荧光指数方法提取了冠层日光诱导叶绿素荧光(SIF)数据,然后结合对小麦条锈病病情严重度敏感的反射率光谱指数并基于改进的分类与回归树(CART)——梯度提升回归树(GBRT)算法,构建了融合反射率和冠层SIF数据的小麦条锈病遥感探测的GBRT模型,并将其与CART及多元线性回归(MLR)模型进行比较。结果表明:①反射率导数荧光指数D705/D722、短波红外谷反射率和反射率比值荧光指数R740/R800是影响遥感探测小麦条锈病严重度精度的主控因素,其中SIF数据的重要性值高于反射率光谱数据,冠层SIF能够比反射率光谱更加敏感地反映小麦条锈病害信息;②GBRT模型病情指数(DI)预测值和实测值间的均方根误差(RMSE)比CART和MLR模型分别减小了15.50%和13.49%,决定系数(R2)分别提高了6.16%和11.57%,GBRT模型估测DI值更接近于实测值,且估测结果波动小,鲁棒性高;CART模型在小样本数据中易将不同特征的数据集划分为同一特征的子集,预测结果波动较大;MLR模型的预测结果相对比较稳定,但其预测精度较低。

关键词: GBRT日光诱导叶绿素荧光反射率光谱小麦条锈病病情严重度    
Abstract:

In order to improve the stability of the small sample data model, a remote sensing detection model of wheat stripe rust with higher accuracy and better robustness was constructed. Firstly, the data of canopy solar-Induced chlorophyll Fluorescence (SIF) were extracted based on radiance and reflectance fluorescence index method, and then combined with reflectance spectral index sensitive to severity of wheat stripe rust, the Gradient Boost Regression Tree (GBRT) was used to detect wheat stripe rust. By comparing GBRT model with CART and Multiple Linear Regression (MLR) model, the results showed that: (1) Reflectivity derivative fluorescence index D705/D722, short-wave infrared Valley reflectance and reflectance ratio fluorescence index R740/R800 were the main factors affecting the accuracy of remote sensing detection of wheat stripe rust. The importance of chlorophyll fluorescence data was higher than that of reflectance spectrum data, and canopy SIF could reflect wheat stripe rust information more sensitively than reflectance spectrum. (2) Compared with CART model and MLR model, the Root Mean Square Error (RMSE) of GBRT model was reduced by 15.50% and 13.49%, and the determination coefficient (R2) was increased by 6.16% and 11.57% respectively. The estimated DI value of GBRT model is closer to the measured value, and the fluctuation of the estimated result is low, and the robustness of CART model is high. In small sample data, it is easy to divide data sets with different features into subsets of the same feature, and the prediction results fluctuate greatly. The prediction results of MLR model are relatively stable, but its prediction accuracy is low.

Key words: GBRT    Solar-induced chlorophyll fluorescence    Reflectance spectrum    Wheat stripe rust    Disease severity
收稿日期: 2019-10-09 出版日期: 2021-05-24
ZTFLH:  TP79  
基金资助: 国家自然科学基金项目资助(41601467)
通讯作者: 竞霞     E-mail: web@qq.com;jingxia1001@163.com
作者简介: 金航(1996-),男,陕西西安人,硕士研究生,主要从事灾害遥感研究。E?mail: jinhang?web@qq.com
服务  
把本文推荐给朋友
加入引用管理器
E-mail Alert
RSS
作者相关文章  
金航
竞霞
高媛
刘良云

引用本文:

金航,竞霞,高媛,刘良云. 遥感探测小麦条锈病严重度的GBRT模型研究[J]. 遥感技术与应用, 2021, 36(2): 411-419.

Hang Jin,Xia Jing,Yuan Gao,Liangyun Liu. GBRT Model for Detecting the Severity of Wheat Stripe Rust by Remote Sensing. Remote Sensing Technology and Application, 2021, 36(2): 411-419.

链接本文:

http://www.rsta.ac.cn/CN/10.11873/j.issn.1004-0323.2021.2.0411        http://www.rsta.ac.cn/CN/Y2021/V36/I2/411

光谱特征变量参数说明
蓝边面积[24] Blue edge area(X1)蓝光范围(490~530 nm)内的反射率光谱对波长的积分值
蓝边斜率 Blue edge slope(X2)蓝边位置对应的一阶微分值
黄边面积[24] Yellow edge area (X3)黄光范围(560~590 nm)内的反射率光谱对波长的积分值
黄边斜率Yellow edge area(X4)黄边位置对应的一阶微分值
红边面积[24] Red edge area (X5)红光范围(680~760 nm)内的反射率光谱对波长的积分值
红边斜率[26] Red edge slope(X6)红边位置对应的一阶微分值
红边位置[25] Red edge position (X7)红光范围内一阶微分光谱对应的一阶微分值
绿峰位置[24] Green peak position (X8)波长在510~560 nm 波段反射率最大值所对应的波长
红谷反射率[27] Red Valley reflectivity (X9)波长在640~700 nm 波段反射率最小值
红谷面积Red Valley area(X10)波长在640~700 nm内原始光谱曲线所包围的面积
短波红外谷反射率[28]Short-Wave Infrared Valley Reflectivity (X11)波长在1400~1800 nm波段反射率最小值
红光区反射率最大值[29]Red Light Area Reflectivity Maximum (X12)红光区(620~680 nm)反射率最大值
红边反射率最大值Red Edge Reflectance Maximum (X13)红边(680~780 nm)反射率最大值
近红外区反射率最大值Near-Infrared Reflectance Maximum (X14)近红外区(780~1100 nm)反射率最大值
黄光区反射率总和Yellow Light Area Reflectance Sum (X15)黄光区(560~590 nm)反射率总和
红光区反射率总和Red Light Area Reflectance Sum (X16)红光区(620~680 nm)反射率总和
红边反射率总和Red Edge Reflectance Sum (X17)红边(680~780 nm)反射率总和
近红外区反射率总和Near-Infrared Reflectance Sum (X18)近红外区(780~1100 nm)反射率总和
绿峰反射高度[29] Green Peak Reflection Height (X19)1-R490+R670-R490670-490(560-490)R560
红谷吸收深度[29] Red Valley Absorption Depth (X20)1-R670R560+R760-R560760-560(670-560)
短波红外谷吸收深度[29]Short-Wave Infrared Valley Absorption Depth (X21)1-R1450R1400+R1670-R14001670-1400(1450-1400)
反射率荧光比值指数[22]Reflectance Fluorescence Ratio Index (X22)R740/R800
反射率荧光导数指数[23]Reflectance Fluorescence Derivative Index (X23)D705/D722
日光诱导叶绿素荧光[14]Solar-Induced Chlorophyll Fluorescence (X24)Finˉ=Lin×(ωleft×Ileft+ωright×Iright)-Iin×(ωleft×Lleft+ωright×Lright)(ωleft×Ileft+ωright×Iright)-Iin
表1  高光谱及荧光特征参数与定义
nsplitCPRELerrorXerror
00.678 91911.063 38
10.143 4750.321 080 60.507 58
20.070 1930.177 605 90.460 05
30.043 1760.107 412 90.469 07
40.016 4670.064 2370.357 14
50.010 2150.031 303 30.349 4
60.009 330.021 088 30.359 14
70.003 4530.011 7580.402 98
80.002 9190.008 304 90.389 39
表2  CART模型复杂度参数(CP)、相对误差(RELerror)及其交叉验证相对误差(Xerror)
图1  平均绝对误差随分类回归树数量的变化趋势
图2  平均绝对误差随分类回归树深度的变化趋势
图3  不同预测模型对条锈病病情指数预测结果
图4  不同模型的预测DI值与实测DI值拟合
1 Yang Yuheng, Su Qiaoyan, Wang Ze, et al. Occurrence Regularity and Influence Factors of Wheat Strip Rust in Chongqing[J]. Journal of Northwest A&F University (Natural Science Edition), 2016, 44(9):151-157.
1 杨宇衡, 宿巧燕, 王泽, 等. 重庆市小麦条锈病发生规律和影响因素分析[J]. 西北农林科技大学学报(自然科学版), 2016, 44(9):151-157.
2 Huang Muyi, Wang Jihua, Huang Wenjiang, et al. Hyperspectral Character of Stripe Rust on Winter Wheat and Monitoring by Remote Sensing[J]. Transactions of the CSAE, 2003, 19(6):154-158.
2 黄木易, 王纪华, 黄文江,等. 冬小麦条锈病的光谱特征及遥感监测[J]. 农业工程学报, 2003, 19(6):154-158.
3 Davoud A, Mohammad M, Alfredo H. Developing Two Spectral Disease Indices for Detection of Wheat Leaf Rust (Pucciniatriticina)[J]. Remote Sensing,2014,6(6):4723-4740.
4 Gao Yuan, Jing Xia, Liu Liangyun, et al. Remote Sensing Monitoring of Wheat Stripe Rust based on Multiple Kernel SVM[J]. Journal of Triticeae Crops, 2020(1):1-9.高媛, 竞霞, 刘良云,等. 基于多核支持向量机的小麦条锈病遥感监测研究[J]. 麦类作物学报, 2020(1):1-9.
5 Jing Xia, Xiaoyan Lü , Zhang Chao, et al. Early Detection of Winter Wheat Stripe Rust based on SIF-PLS Model [J]. Transactions of the Chinese Society for Agricultural Machinery, 2020,51(6):191-197.
5 竞霞, 吕小艳, 张超, 等. 基于SIF-PLS模型的冬小麦条锈病早期光谱探测[J].农业机械学报,2020,51(6):191-197.
6 Hu Gensheng, Wu Wentian, Huang Wenjiang, et al. Application of PSO-LSSVM in Wheat Powdery Mildew Monitoring[J]. Remote Sensing Technology and Application, 2017, 32(2):299-304.
6 胡根生, 吴问天, 黄文江, 等. 粒子群优化的最小二乘支持向量机在小麦白粉病监测中的应用[J]. 遥感技术与应用, 2017, 32(2):299-304.
7 Jin Xiu, Lu Jie, Fu Yunzhi, et al. A Classification Method for Hyperspectral Imaging of Fusarium Head Blight Disease Symptom based on Deep Convolutional Neural Network[J]. Acta Agriculturae Zhejiangensis, 2019, 31(2):315-325.
7 金秀, 卢杰, 傅运之, 等. 基于深度卷积神经网络的小麦赤霉病高光谱病症点分类方法[J]. 浙江农业学报, 2019, 31(2):315-325.
8 Hu Jiaochan, Liu Liangyun, Liu Xinjie. Assessing Uncertainties of Sun-induced Chlorophyll Fluorescence Retrieval Using FluorMOD Model[J]. Journal of Remote Sensing, 2015, 19(4):594-608.
8 胡姣婵, 刘良云, 刘新杰. FluorMOD模拟叶绿素荧光夫琅和费暗线反演算法不确定性分析[J]. 遥感学报, 2015, 19(4):594-608.
9 Liu Liangyun. Principle and Application of Vegetation Quantitative Remote Sensing[M]. Beijing: Science Press, 2014.
9 刘良云. 植被定量遥感原理与应用[M]. 北京:科学出版社, 2014.
10 Murchie E H, Lawson T. Chlorophyll Fluorescence Analysis: A Guide to Good Practice and Understanding Some New Applications[J]. Journal of Experimental Botany,2013,64(13):3983-3998.
11 Zarco-Tejada P J, Camino C, Beck P S A, et al. Previsual Symptoms of Xylella Fastidiosa Infection Revealed in Spectral Plant-trait Alterations[J]. Nature Plants, 2018, 4(7):432-439.
12 Sun Y, Fu R, Dickinson R, et al. Drought Onset Mechanisms Revealed by Satellite Solar-induced Chlorophyll Fluorescence: Insights from Two Contrasting Extreme Events[J]. Journal of Geophysical Research: Biogeosciences, 2015, 120(11):2427-2440.
13 Liu L, Yang X, Zhou H, et al. Evaluating the Utility of Solar-induced Chlorophyll Fluorescence for Drought Monitoring by Comparison with NDVI Derived from Wheat Canopy[J]. Science of the Total Environment, 2018, 625:1208-1217.
14 Zhang Yongjiang, Huang Wenjiang, Wangjihua, et al. Chlorophyll Fluorescence Sensing to Detect Stripe Rust in Wheat (Triticum Aestivum L.) Fields based on Fraunhofer Lines[J]. Scientia Agricultura Sinica, 2007(1):78-83.张永江, 黄文江, 王纪华,等. 基于Fraunhofer线的小麦条锈病荧光遥感探测[J]. 中国农业科学, 2007(1):78-83.
15 Liu Qi, Wang Cuicui, Wang Rui, et al. Hyperspectral Qualitative Identification on Latent Period of Wheat Stripe Rust[J]. Journal of Plant Protection, 2018,45(1):153-160.
15 刘琦, 王翠翠, 王睿, 等. 潜育期小麦条锈菌的高光谱定性识别[J]. 植物保护学报, 2018,45(1): 153-160.
16 Jing Xia, Bai Zongfan, Gao Yuan, et al. Wheat Stripe Rust Monitoring by Random Forest Algorithm Combined with SIF and Reflectance Spectrum[J]. Transactions of the Chinese Society of Agricultural Engineering,2019,35(13):154-161.
16 竞霞,白宗璠,高媛,等.利用随机森林法协同SIF和反射率光谱监测小麦条锈病[J].农业工程学报,2019,35(13):154-161.
17 Chen Siyuan, Jing Xia, Dong Yingying, et al. Detection of Wheat Stripe Rust Using Solar-induced Chlorophyll Fluorescence and Reflectance Spectral Indices[J]. Remote Sensing Technology and Application, 2019,34(3):511-520.
17 陈思媛, 竞霞, 董莹莹,等. 基于日光诱导叶绿素荧光与反射率光谱的小麦条锈病探测研究[J]. 遥感技术与应用, 2019,34(3):511-520.
18 Wang Jing, Jing Yuanshu, Huang Wenjiang, et al. Comparative Research on Estimating the Severity of Yellow Rust in Winter Wheat[J]. Spectroscopy and Spectral Analysis, 2015, 35(6):1649-1653.
18 王静, 景元书, 黄文江, 等. 冬小麦条锈病严重度不同估算方法对比研究[J]. 光谱学与光谱分析, 2015, 35(6):1649-1653.
19 Ma Huiqin. Remote Sensing Monitoring and Forecasting Models of Wheat Powdery Mildew based on Multi-Source Data[D]. Nanjing: Nanjing University of Information Science and Technology,2017.
19 马慧琴.基于多源数据的小麦白粉病遥感监测与预测模型研究[D].南京:南京信息工程大学, 2017.
20 Liu Yunxiang, Wu Hao. Establishment of Water Bloom Warning Model based on Improved CART Decision Tree[J]. China Rural Water and Hydropower, 2018(1):26-28.
20 刘云翔, 吴浩. 基于改进CART决策树建立水华预警模型[J]. 中国农村水利水电, 2018(1):26-28.
21 Huang Wenjiang, Zhang Jingcheng, Shi Yue, et al. Progress in Monitoring and Forecasting of Crop Pests and Diseases by Remote Sensing[J]. Journal of Nanjing University of Information Science & Technology (Natural Science Edition), 2018,10(1):30-43.
21 黄文江, 张竞成, 师越, 等. 作物病虫害遥感监测与预测研究进展[J]. 南京信息工程大学学报(自然科学版), 2018,10(1):30-43.
22 Zarco-Tejada P J, Miller J R, Mohammed G H, et al. Chlorophyll Fluorescence Effects on Vegetation Apparent Reflectance: I. Leaf-level Measurements and Model Simulation[J]. Remote Sensing of Environment, 2000, 74:582-595.
23 Zorco-Tejada P J, Pushnik J C, Dobrowski S Z, et al. Steady-state Chlorophyll a Fluorescence Detection from Canopy Derivative Reflectance and Double-peak Red-edge Effects[J]. Remote sensing of Environment, 2003, 84(2):283-294.
24 Bi Yinli, Sun Jiangtao, Ypyszhan, et al. Hyperspectral Characterization and Nutrition Condition of Maize Inoculated with Arbuscular Mycorrhiza in Different Phosphorus Levels[J]. Journal of China Coal Society, 2016,41(5):1227-1235.
24 毕银丽, 孙江涛, Ypyszhan, 等. 不同施磷水平下接种菌根玉米营养状况及光谱特征分析[J]. 煤炭学报, 2016, 41(5):1227-1235.
25 Zhang Yonghe, Chen Wenhui, Guo Qiaoying, et al. Hyperspectral Estimation Models for Photosynthetic Pigment Contents in Leaves of Eucalyptus[J]. Acta Ecologica Sinica, 2013,33( 3) : 876-887.
25 张永贺, 陈文惠, 郭乔影, 等. 桉树叶片光合色素含量高光谱估算模型[J]. 生态学报, 2013, 33(3):876-887.
26 Yang X H, Wang F M, Huang J F, et al. Comparison between Radial Basis Function Neural Network and Regression Model for Estimation of Rice Biophysical Parameters Using Remote Sensing[J]. Pedosphere, 2009, 19(2):176-188.
27 Huang J F, Blackburn G A. Optimizing Predictive Models for Leaf Chlorophyll Concentration based on Continuous Wavelet Analysis of Hyperspectral Data[J]. International journal of remote sensing, 2011, 32(24):9375-9396.
28 Huang Xiaojun, Xie Yaowen, Bao Yuhai. Spectral Detection of Damaged Lever of Larch Affected by Jas’s Larch Inchworm[J]. Spectroscopy and Spectral Analysis, 2018(3):905-911.
28 黄晓君, 颉耀文, 包玉海. 落叶松受雅氏落叶松尺蠖危害程度光谱检测[J]. 光谱学与光谱分析, 2018(3):905-911.
29 Zhang Sulan, Tan Ju, Tang Xiaodong, et al. Spectral Characteristics and Evaluation Model of Pinus Massoniana Suffering from Bursaphelenchus Xylophilus Disease[J]. Spectroscopy and Spectral Analysis, 2019,39(3):865-872.
29 张素兰, 覃菊, 唐晓东, 等. 松材线虫危害下马尾松光谱特征与估测模型研究[J]. 光谱学与光谱分析,2019,39(3):865-872.
30 Maier S W, Günther K P, Stellmes M. Sun-induced Fluorescence: A New Tools for Precision Farming[C]∥ Digital Imaging and Spectral Techniques: Aplications to Precision Agriculture and Crop Physiology. Madison: American Society of Agronomy, 2003: 209-222.
31 Yu Wenqi, Dai Xue, Yang Ying, et al. The Relationship between Water-level Fluctuation Factors and the Distribution of Carex in Floodplain Grassland Around Poyang Lake[J]. Journal of Lake Sciences, 2018, 30(6):204-212.
31 于文琪, 戴雪, 杨颖, 等. 基于CART模型的鄱阳湖草滩苔草分布与水位波动要素关系[J]. 湖泊科学, 2018, 30(6):204-212.
32 Han Jiaqi, Mao Kebiao, Ge Feifan, et al. Application of Classification and Regression Tree in Soil Moisture Estimation[J]. Remote Sensing Information, 2018, 33(3):49-56.
32 韩家琪, 毛克彪, 葛非凡, 等. 分类回归树算法在土壤水分估算中的应用[J]. 遥感信息, 2018, 33(3):49-56.
33 Huang Xiaojun, Xie Yaowen, Wei Jiaojiao, et al. Automatic Recognition of Desertification Information based on the Pattern of Change Detection-CART Decision Tree[J]. Journal of Catastrophology, 2017, 32(1):36-42.
33 黄晓君, 颉耀文, 卫娇娇, 等. 基于变化检测-CART决策树模式自动识别沙漠化信息[J]. 灾害学, 2017, 32(1):36-42.
34 Friedman J H. Greedy Function Approximation: A Gradient Boosting Machine[J]. The Annals of Statistics, 2001, 29(5):1189-1232.
35 Qiu Xin, Hong Haoyu, Yang Qing, et al. Prediction of Temperature of Asphalt Pavement Surface based on APRIORI-GBDT Algorithm.[J]. Journal of Highway and Transportation Research and Development,2019,36(5):1-10,19.
35 邱欣,洪皓珏,杨青,等. 基于APRIORI-GBDT算法的沥青路面路表温度预测[J].公路交通科技,2019,36(5):1-10,19.
36 Zhang Jialong, Xu Hui, Lu Chi. Estimating Above Ground Biomass of Pinus Densata based on Landsat8 OLI and Gradient Boost Regression Tree[J]. Journal of Northeast Forestry University, 2018, 46(8):27-32.
36 张加龙, 胥辉, 陆驰. 应用Landsat8 OLI和GBRT对高山松地上生物量的估测[J]. 东北林业大学学报, 2018, 46(8):27-32.
37 Zuur A F, Ieno E N, Elphick C S. A Protocol for Data Exploration to Avoid Common Statistical Problems[J]. Methods in Ecology and Evolution, 2010, 1(1):3-14.
38 Subhash N, Subhash N, Ravi V, et al. Detection of Mosaic Virus Disease in Cassava Plants by Sunlight-induced Fluorescence Imaging: A Pilot Study for Proximal Sensing[J]. International Journal of Remote Sensing, 2015, 36(11):2880-289.
39 Krause G H, Weis E. Chlorophyll Fluorescence and Photosynthesis: The Basics[J]. Annual Review of Plant Biology, 1991, 42(1): 313-349.
40 Liu L, Zhao J, Guan L, et al. Tracking Photosynthetic Injury of Paraquat-treated Crop Using Chlorophyll Fluorescence from Hyperspectral Data[J]. European Journal of Remote Sensing, 2013, 46(1):459-473.
41 Huang Muyi, Huang Wenjiang, Liu Liangyun, et al. Spectral Reflectance Feature of Winter Wheat Single Leaf Infected with Stripe Rust and Severity Level Inversion[J]. Transactions of the CSAE, 2004, 20(1):176-180.
41 黄木易, 黄文江, 刘良云, 等. 冬小麦条锈病单叶光谱特性及严重度反演[J]. 农业工程学报, 2004, 20(1):176-180.
42 Beck P S A, Goetz S J. Satellite Observations of High Northern Latitude Vegetation Productivity Changes between 1982 and 2008: Ecological Variability and Regional Differences[J]. Environmental Research Letters, 2011, 6(4): 045501. doi:iop science.iop.org/1748-9326/6141045501.
doi: iop science.iop.org/1748-9326/6141045501
43 Gamon J A, Kovalchuck O, Wong C Y S, et al. Monitoring Seasonal and Diurnal Changes in Photosynthetic Pigments with Automated PRI and NDVI Sensors[J]. Biogeosciences, 2015, 12(13):4149-4159.
44 Song L, Guanter L, Guan K, et al. Satellite Sun-induced Chlorophyll Fluorescence Detects Early Response of Winter Wheat to Heat Stress in the Indian Indo-gangetic Plains[J]. Global Change Biology,2018-05-10. doi:10.1111/gcb.14302.
doi: 10.1111/gcb.14302
45 Baker, Neil R. Chlorophyll Fluorescence: A Probe of Photosynthesis In Vivo[J]. Annual Review of Plant Biology, 2008, 59(1): 89-113.
46 Bai Zongfan, Jing Xia, Zhang Teng, et al. Canopy SIF Synergize with Total Spectral Reflectance Optimized by the MDBPSO Algorithm to Monitor Wheat Stripe Rust[J]. Acta Agronomica Sinica, 2020, 46(8):1248-1257.
46 白宗璠,竞霞,张腾,等.MDBPSO算法优化的全波段光谱数据协同冠层SIF监测小麦条锈病[J].作物学报,2020,46(8):1248-1257.
[1] 陈思媛, 竞霞, 董莹莹, 刘良云. 基于日光诱导叶绿素荧光与反射率光谱的小麦条锈病探测研究[J]. 遥感技术与应用, 2019, 34(3): 511-520.
[2] 刘青瑞,居为民,张永光. 日光诱导叶绿素荧光估算中国典型生态系统总初级生产力的能力[J]. 遥感技术与应用, 2017, 32(2): 363-373.