Please wait a minute...
img

官方微信

遥感技术与应用  2022, Vol. 37 Issue (1): 244-252    DOI: 10.11873/j.issn.1004-0323.2022.1.0244
草地遥感专栏     
基于Cubist的中国植被区域叶绿素荧光数据重建
沈洁1(),辛晓平1(),张景2,苗晨2,王旭1,丁蕾1,沈贝贝1
1.中国农业科学院农业资源与农业区划研究所,北京 100081
2.国家遥感中心,北京 100036
Reconstruction of SIF Remote Sensing Data of Vegetation in China based on Cubist
Jie Shen1(),Xiaoping Xin1(),Jing Zhang2,Chen Miao2,Xü Wang1,Lei Ding1,Beibei Shen1
1.Institute of Agricultural Resources and Agricultural Regional Planning,Chinese Academy of Agricultural Sciences,Beijing 100081,China
2.National Remote Sensing Center of China,Beijing 100036,China
 全文: PDF(5421 KB)   HTML
摘要:

日光诱导叶绿素荧光(Solar-Induced chlorophyll Fluorescence, SIF)是植物在太阳光照条件下,在光合作用过程中发射出的光谱信号(650~800 nm),SIF相比于植被指数等参数更能直接地反映植被光合作用的相关信息,为大尺度GPP估算带来了新的途径。但目前卫星SIF数据或存在分辨率较低的不足,或存在数据空间不连续的局限,对于应用到大尺度中连续GPP的估算中有一定难度。OCO-2 SIF数据拥有较高的空间分辨率,但却是空间离散数据。针对上述问题,着重研究对离散的OCO-2 SIF数据进行连续预测的方法,生成中国—蒙古草地生态系统的较高精度连续SIF数据集。结果如下:通过Cubist回归树算法,结合MODIS反射率数据,气象数据及土地利用类型,建立了每8 d的0.05°分辨率的连续SIF数据集,预测精度为R2=0.65,RMSE=0.114。其中,对作物类SIF预测的精度最高,为R2=0.71,RMSE=0.117;其次为对森林与草地的预测,两者的R2和RMSE分别为0.64/0.123,0.60/0.112。

关键词: 日光诱导叶绿素荧光Cubist模型数据重建    
Abstract:

Solar-Induced Chlorophyll Fluorescence (SIF) is the spectral signal (650~800 nm) emitted by plants in the process of photo-synthesis under sunlight conditions. SIF is more direct than vegetation index and other parameters. Reflecting the relevant infor-mation of vegetation photosynthesis, it brings a new way for large-scale Gross Primary Productivity(GPP)estimation. However, the current satellite SIF data may have insufficient resolution or discontinuity in the data space, which is difficult to apply to the estimation of continuous GPP on a large scale. OCO-2 SIF data has high spatial resolution, but it is spatially discrete data. In response to the above problems, this paper focuses on the method of con-tinuous prediction of discrete OCO-2 SIF data to generate a high-precision continuous SIF data set of the China-Mongolia grassland ecosy-stem. The results are as follows: Through the Cubist regression tree algorithm, combined with MODIS reflectance data, meteorologi-cal data and land use types, a continuous SIF data set with a resolution of 0.05° every 8 days is established, and the prediction accuracy is R2= 0.65 and RMSE = 0.114. Among them, the accuracy of crop SIF prediction is the highest, with R2= 0.71 and RMSE= 0.117; the second is the prediction of forest and grassland, with R2 and RMSE of 0.64/0.123 and 0.60/0.112 respectively.

Key words: Solar-Induced chlorophyll fluorescence    Cubist model    Data reconstruction
收稿日期: 2021-06-16 出版日期: 2022-04-08
ZTFLH:  Q948  
基金资助: 国家重点研发计划项目“草地碳收支监测评估技术合作研究”(2017YFE0104500);国家自然科学基金“基于全生命周期分析的多尺度草甸草原经营景观碳收支研究”(41771205);财政部和农业农村部国家现代农业产业技术体系,中央级公益性科研院所基本科研业务费专项(Y2020YJ19)
通讯作者: 辛晓平     E-mail: JShen_10@163.com;xinxiaoping@caas.cn
作者简介: 沈 洁(1996-),女,宁夏中卫人,硕士研究生,主要从事草地生态遥感研究。E?mail:JShen_10@163.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  
沈洁
辛晓平
张景
苗晨
王旭
丁蕾
沈贝贝

引用本文:

沈洁,辛晓平,张景,苗晨,王旭,丁蕾,沈贝贝. 基于Cubist的中国植被区域叶绿素荧光数据重建[J]. 遥感技术与应用, 2022, 37(1): 244-252.

Jie Shen,Xiaoping Xin,Jing Zhang,Chen Miao,Xü Wang,Lei Ding,Beibei Shen. Reconstruction of SIF Remote Sensing Data of Vegetation in China based on Cubist. Remote Sensing Technology and Application, 2022, 37(1): 244-252.

链接本文:

http://www.rsta.ac.cn/CN/10.11873/j.issn.1004-0323.2022.1.0244        http://www.rsta.ac.cn/CN/Y2022/V37/I1/244

图1  研究区域范围
图2  规则数与实例数参数优化
Land Use=TURE
FittingValidation
样本量MAERERR2RMSE
10 0000.0770.439 70.7900.632 70.104 7
50 0000.0770.435 60.7920.637 70.103 9
87 0000.0770.429 60.7970.639 40.103 7
139 2000.0760.428 90.7990.651 10.103 5
174 0000.0690.356 00.8170.662 10.097 0
Land Use=FALSE
FittingValidation
样本量MAERERR2RMSE
10 0000.0780.446 10.7810.616 80.106 9
50 0000.0780.439 50.7860.617 40.106 9
87 0000.0770.433 50.7910.621 50.106 3
139 2000.0770.432 10.7940.618 10.106 7
174 0000.0700.359 00.8130.641 60.100 1
表1  模型拟合精度与验证精度统计
图3  Cubist模型预测SIF与观测SIF验证
图4  误差统计(a)SIF观测值分布与(b)SIF观测值的累积误差
图5  不同生态群落中Cubist模型预测SIF与观测SIF验证(SIF预料值(W · m-2 · μm-1 · sr-1))
图6  每8天聚合到1°SIF格网数据,Cubist模型预测SIF数据对比(以2018年7月4日~11日为例)
1 Zhang Y, Guanter L, Berry J A, et al. Model-based analysis of the relationship between Sun-Induced chlorophyll Fluorescence and gross primary production for remote sensing applications[J]. Remote Sensing of Environment, 2016, 187 : 145-155.
2 Albert P C, Esa T, Jon A, et al. Linking chlorophyll a fluorescence to photosynthesis for remote sensing applications: mechanisms and challenges [J]. Journal of experimental botany, 2014, 65(15) : 4065-4095.
3 Frankenberg C, Berry J. Solar Induced chlorophyll Fluorescence: origins, relation to photosynthesis and retrieval[J]. Comprehensive Remote Sensing, 2018, 3:143-162.
4 Meroni M, Rossini M, Guanter L, et al. Remote sensing of Solar-Induced chlorophyll Fluorescence: Review of methods and applications[J]. Remote Sensing of Environment, 2009, 113(10):2037-2051.
5 Frankenberg, Fisher, J B, et al. New global observations of the terrestrial carbon cycle from GOSAT: Patterns of plant fluorescence with gross primary productivity[J]. Geophysical Research Letters, 2011, 38(17): 351-365.
6 Guanter L, Frankenberg C, Dudhia A,et al. Retrieval and glo-bal assessment of terrestrial chlorophyll fluorescence from GOSAT space measurements[J]. Remote Sensing of Environment, 2012, 121(none):236-251.
7 Joiner J, Yoshida Y, Vasilkov A P, et al. Filling-in of far-red and near-Infrared solar lines by terrestrial and atmospheric effects: simulations and space-based observations from SCIAMACHY and GOSAT[J]. Atmospheric Measurement Techniques Discussions, 2012, 5(1):163-210.
8 Köhler P, Guanter L, Joiner J. A linear method for the retrieval of Sun-Induced chlorophyll Fluorescence from GOME-2 and SCIAMACHY data[J]. Atmospheric Measurement Techniques,8,6(2015-06-26), 2015, 8:2589-2608.
9 Ji Menghao, Tang Bohui, Li Zhaoliang. Review of Solar-Induced chlorophyll Fluorescence retrieval methods from satellite data[J]. Remote sensing Technology And Application,2019,34(3):455-466.
9 纪梦豪,唐伯惠,李召良.太阳诱导叶绿素荧光的卫星遥感反演方法研究进展[J].遥感技术与应用,2019,34(3):455-466.
10 Li X, Xiao J, He B. Chlorophyll fluorescence observed by OCO-2 is strongly related to gross primary productivity estimated from flux towers in temperate forests[J]. Remote Sensing of Environment, 2018,204:659-671.
11 Frankenberg C, O'Dell C, Berry J, et al. Prospects for chlorophyll fluorescence remote sensing from the Orbiting Carbon Observatory-2[J]. Remote Sensing of Environment, 2014, 147:1-12.
12 Duveiller G, Cescatti A. Spatially downscaling Sun-Induced chlorophyll Fluorescence leads to an improved temporal correlation with gross primary productivity[J]. Remote Sensing of Environment, 2016, 182:72-89.
13 Yu L, Wen J, Chang C Y, et al. High‐resolution global contiguous SIF of OCO‐2[J]. Geophysical Research Letters, 2019, 46:1449-1458.
14 Bishop C M. Neural networks for pattern recognition[M]. Oxford: Oxford University Press, 1995.
15 Zhang Y, Joiner J, Alemohammad S H, et al. A global spatially contiguous Solar-Induced Fluorescence (CSIF) dataset using neural networks[J]. Biogeosciences, 2018, 15(19): 5779-5800.
16 Gentine P, Alemohammad S H. Reconstructed Solar-Induced Fluorescence: a machine learning vegetation product based on MODIS surface reflectance to reproduce GOME-2 solar-induced fluorescence[J]. Geophysical Research Letters, 2018, 45(7): 3136-3146.
17 Duveiller G, Filipponi F, Walther S, et al. A spatially downscaled Sun-Induced Fluorescence global product for enhanced monitoring of vegetation productivity[J]. Earth System Science Data, 2020, 12(2): 1101-1116.
18 Ma Y, Liu L, Chen R, et al. Generation of a global spatially continuous TanSat Solar-Induced chlorophyll Fluorescence product by considering the impact of the solar radiation intensity[J]. Remote Sensing, 2020, 12(13): 2167.
19 Huete A, Didan K, Miura T, et al. Overview of the radiometric and biophysical performance of the MODIS vegetation indices[J]. Remote Sensing of Environment, 2002, 83(1-2):195-213.
20 Zhengxing W, Chuang L, Alfredo H, et al. From AVHRR-NDVI to MODIS-EVI: advances in vegetation index research[J]. Acta Ecologica Sinica, 2003, 23(5):979-987.
20 王正兴, 刘闯, Alfredo H. 植被指数研究进展:从AVHRR-NDVI到MODIS-EVI[J]. 生态学报, 2003,23(5):143-151.
21 Zhang C. Using MODIS vegetation index to study urban expansion and change[J]. Meteorological, 2006,32(10):20-26.
21 张春桂. 用MODIS植被指数研究福州城区空间扩展变化[J]. 气象, 2006, 32(10):20-26.
22 Ma Rui. Research on enhanced vegetation index algorithm and its application in the ecological environmental remote sensing production subsystem[D]. Kaifeng: Henan University,2015.
22 马瑞. 增强植被指数算法的研究及其在生态环境遥感产品生产分系统的应用[D]. 开封:河南大学,2015.
23 Yu Longlong, Luo Ze, Yan Baoping. Reconstruction framework of high resolution sif remote sensing dataset in regions of interest[J]. Computer Systems & Applications, 2019, 28(9):133-139.
23 于龙龙, 罗泽, 阎保平. 兴趣区域高分辨率叶绿素荧光遥感数据集重建框架[J]. 计算机系统应用, 2019, 28(9):133-139.
24 Breiman L. Classification and regression trees[M]. New York:Chapman and Hall,1984.
25 Ma Ziqiang. Downscaling satellite-based precipitation estimates over the Oinghai-Tibetan Plateau at different temporal scales[D]. Hangzhou:Zhejiang University, 2017.
25 马自强. 青藏高原地区卫星降水数据时空降尺度研究[D]. 杭州:浙江大学, 2017.
26 Quinlan J R.Simplifying decision trees[J]. International Journal of Man-Machine Studies, 1987,27(3):221-234.
27 Dai S, Yingchun F U, Zhao Y, et al. The remote sensing model for estimating urban impervious surface percentage based on the cubist model tree[J]. Journal of Geo-Information Science, 2016,18(10):1399-1409.
27 戴舒 付迎春 赵耀龙. 基于Cubist模型树的城市不透水面百分比遥感估算模型[J]. 地球信息科学学报, 2016,18(10):1399-1409.
28 Zhuang X J. Estimation of net ecosystem carbon exchange for the conterminous United States by combining MODIS and AmeriFlux data[J]. Agricultural & Forest Meteorology Amsterdam Elsevier, 2008,148(11):1827-1847.
29 Gao F, Anderson M C, Kustas W P, et al. Retrieving Leaf Area Index from Landsat using MODIS LAI products and field measurements[J]. IEEE Geoscience & Remote Sensing Letters, 2014, 11(4):773-777.
30 Kuhn M, Weston S, Keefer C. Cubist: rule- and instance-based regression modeling. http:∥ftp.ussg.ju.edu/CRAN/web/packages/cubist/,2014.
31 Kuhn M, Johnson K. Applied Predictive Modeling[M]. New York:Springer,2013.
[1] 杨凤珠,王震山,张乾,孙善磊,柳艺博. 多源日光诱导叶绿素荧光产品在中国地区的一致性研究[J]. 遥感技术与应用, 2022, 37(1): 125-136.
[2] 孙忠秋,高显连,杜珊珊,刘新杰. 全球日光诱导叶绿素荧光卫星遥感产品研究进展与展望[J]. 遥感技术与应用, 2021, 36(5): 1044-1056.
[3] 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.
[4] 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.
[5] 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.