Retrieving canopy nitrogen content of mangrove forests from Sentinel-2 super-resolution reconstruction data
- Vol. 26, Issue 6, Pages: 1206-1219(2022)
Published: 07 June 2022
DOI: 10.11834/jrs.20221461
扫 描 看 全 文
浏览全部资源
扫码关注微信
Published: 07 June 2022 ,
扫 描 看 全 文
甄佳宁,蒋侠朋,赵德梅,王俊杰,苗菁,邬国锋.2022.利用Sentinel-2影像超分辨率重建的红树林冠层氮含量反演.遥感学报,26(6): 1206-1219
Zhen J N,Jiang X P,Zhao D M,Wang J J,Miao J and Wu G F. 2022. Retrieving canopy nitrogen content of mangrove forests from Sentinel-2 super-resolution reconstruction data. National Remote Sensing Bulletin, 26(6):1206-1219
氮素是植被整个生命周期的必要元素,红树林冠层氮素含量(CNC)遥感估算对红树林健康监测具有重要意义。以广东湛江高桥红树林保护区为研究区,本文旨在基于Sentinel-2影像超分辨率重建技术进行红树林CNC估算和空间制图。研究首先基于三次卷积重采样、Sen2Res和SupReMe算法实现Sentinel-2影像从20 m分辨率到10 m的重建;然后以重建后的影像和原始20 m影像为数据源构建40个相关植被指数,采用递归特征消除法(SVM-RFE)确定CNC估算的最优变量组合,进而构建CNC反演的核岭回归(KRR)模型;最后选取最优模型实现CNC制图。研究结果表明:基于Sen2Res和SupReMe超分辨率算法的重建影像不仅与原始影像具有很高的光谱一致性,且明显提高了影像的清晰度和空间细节。红树林CNC反演波段主要集中在红(B4)、红边(B5)、近红外波段(B8a)以及短波红外波段(B11和B12),与“红边波段”相关的植被指数(RSSI和TCARIre1/OSAVI)也是红树林CNC反演的有效变量。基于3种方法重建后10 m的影像构建的模型反演精度(
R
2
val
>
0.579)均优于原始20 m的影像(
R
2
val=0.504);基于Sen2Res算法重建影像构建的反演模型拟合精度(
R
2
val=0.630,RMSE_val=5.133,RE_val=0.179)与基于三次卷积重采样重建影像的模型拟合精度(
R
2
val=0.640,RMSE_val=5.064,RE_val=0.179)基本相当,前者模型验证精度(
R
2
cv=0.497,RMSE_cv=5.985,RE_cv=0.214)较高且模型变量选择数量最为合理。综合重建影像光谱细节及模型精度,基于Sen2Res算法重建的Sentinel-2影像在红树林CNC估算中具有良好的应用潜力,能为区域尺度红树林冠层健康状况的精细监测提供有效的方法借鉴和数据支撑。
Nitrogen content is an essential element in the whole life cycle of vegetation. The estimation of mangrove Canopy Nitrogen Content (CNC) by remote sensing is greatly important for mangrove health monitoring. At present
studies that use satellite hyperspectral data to retrieve CNC of forest at regional scales
especially for mangroves
are few. In addition
the low spatial resolution of most satellite hyperspectral images and the difficulty of measuring the average leaf nitrogen content of a single image pixel in real time limit the inversion accuracy. In this study
the super-resolution reconstruction of Sentinel-2 image and in-site measurement data was used for retrieving mangrove CNC to explore the application potential of enhanced Sentinel-2 image in mangrove monitoring.
Taking Zhanjiang Gaoqiao Mangrove National Nature Reserve
China as the study area
the red edge bands
near-infrared
and short wave bands of Sentinel-2 were reconstructed from 20 m to 10 m by resampling
Sen2Res
and SupReMe algorithms
respectively. The reconstructed images are used to build 40 vegetation indices and analyze their correlation with CNC. Then
the SVM-RFE iterative feature deletion method was used to determine the optimal variable combination of mangrove CNC estimation
and the Kernel Ridge Regression (KRR) model was used to construct the prediction model of mangrove CNC. Finally
the optimal model was used to map CNC spatial distribution of mangrove forests.
Significant differences in canopy nitrogen content and leaf nitrogen content were found among different mangrove species
and the variation of intraspecific CNC was abundant. The reconstructed images based on Sen2Res and supreme super resolution algorithm not only had high spectral consistency (the
R
2
values of all bands are above 0.96) with the resampled image
but also significantly improved the clarity and spatial detail of the image compared with the 20 m resolution image. The bands sensitive to mangrove CNC are mainly concentrated in the red band (B4)
red-edge band (B5)
near-infrared band (B8a)
and short-wave infrared band (B11 and B12). Vegetation indices related to red-edge band (RSSI and TCARIre1/OSAVI) are also effective variables to predict mangrove CNC. The inversion accuracy (
R
2
val
>
0.579) of the reconstructed 10 m image based on the three methods is better than that of the original 20 m image (
R
2
val=0.504). The fitting accuracy of the inversion model based on the reconstructed Sen2Res image (
R
2
val=0.630
RMSE_val=5.133
RE_val=0.179) is almost the same as the resampled (
R
2
val=0.640
RMSE_val
=
5.064
RE_val
=
0.179)
and its model validation accuracy (
R
2
cv=0.497
RMSE_cv=5.985
RE_cv=0.214) is higher. In addition
the variable number of Sen2Res is the most reasonable.
Based on the spectral details and model accuracy of reconstructed images
Sentinel-2 images constructed by Sen2Res algorithm have good application potential in mangrove canopy nitrogen content estimation and can provide effective method reference and data support for fine monitoring of mangrove canopy health status at regional scale. Compared with vegetation
such as crops and grasslands
the factors influencing CNC inversion of mangroves are more complex. Although the influence of the main canopy structure factor (LAI) was considered in this study
other factors
such as species
community structure
leaf inclination
and synergistic changes
in other biochemical components should be further investigated.
遥感红树林冠层氮素含量Sentinel-2影像重建SVM-RFEKRR
remote sensingmangrove forestscanopy nitrogen contentSentinel-2image reconstructionSVM-RFEKRR
Ali A M, Darvishzadeh R, Skidmore A, Gara T W, O’connor B, Roeoesli C, Heurich M and Paganini M. 2020. Comparing methods for mapping canopy chlorophyll content in a mixed mountain forest using Sentinel-2 data. International Journal of Applied Earth Observation and Geoinformation, 87: 102037 [DOI: 10.1016/j.jag.2019.102037http://dx.doi.org/10.1016/j.jag.2019.102037]
Brodu N. 2017. Super-resolving multiresolution images with band-independent geometry of multispectral pixels. IEEE Transactions on Geoscience and Remote Sensing, 55(8): 4610-4617 [DOI: 10.1109/TGRS.2017.2694881http://dx.doi.org/10.1109/TGRS.2017.2694881]
Camino C, González-Dugo V, Hernández P, Sillero J C and Zarco-Tejada P J. 2018. Improved nitrogen retrievals with airborne-derived fluorescence and plant traits quantified from VNIR-SWIR hyperspectral imagery in the context of precision agriculture. International Journal of Applied Earth Observation and Geoinformation, 70: 105-117 [DOI: 10.1016/j.jag.2018.04.013http://dx.doi.org/10.1016/j.jag.2018.04.013]
Chen J M. 1996. Evaluation of vegetation indices and a modified simple ratio for boreal applications. Canadian Journal of Remote Sensing, 22(3): 229-242 [DOI: 10.1080/07038992.1996.10855178http://dx.doi.org/10.1080/07038992.1996.10855178]
Chen Y Z, Fu B J and Feng X M. 2017. Overview and outlook of remote sensing inversion of vegetation nitrogen content. Acta Ecologica Sinica, 37(18): 6240-6252
陈永喆, 傅伯杰, 冯晓明. 2017. 遥感反演植被含氮量研究进展. 生态学报, 37(18): 6240-6252 [DOI: 10.5846/stxb201707131271http://dx.doi.org/10.5846/stxb201707131271]
Clevers J G P W and Gitelson A A. 2013. Remote estimation of crop and grass chlorophyll and nitrogen content using red-edge bands on Sentinel-2 and -3. International Journal of Applied Earth Observation and Geoinformation, 23: 344-351 [DOI: 10.1016/j.jag.2012.10.008http://dx.doi.org/10.1016/j.jag.2012.10.008]
Cristianini N and Shawe-Taylor J. 2000. An Introduction to Support Vector Machines and Other Kernel-Based Learning Methods. Cambridge: Cambridge University Press
Daughtry C S T, Walthall C L, Kim M S, de Colstoun E B and McMurtrey III J E. 2000. Estimating corn leaf chlorophyll concentration from leaf and canopy reflectance. Remote Sensing of Environment, 74(2): 229-239 [DOI: 10.1016/s0034-4257(00)00113-9http://dx.doi.org/10.1016/s0034-4257(00)00113-9]
Estévez J, Vicent J, Rivera-Caicedo J P, Morcillo-Pallarés P, Vuolo F, Sabater N, Camps-Valls G, Moreno J and Verrelst J. 2020. Gaussian processes retrieval of LAI from Sentinel-2 top-of-atmosphere radiance data. ISPRS Journal of Photogrammetry and Remote Sensing, 167: 289-304 [DOI: 10.1016/j.isprsjprs.2020.07.004http://dx.doi.org/10.1016/j.isprsjprs.2020.07.004]
Gao C J, Jiang X P, Zhen J N, Wang J J and Wu G F. 2022. Mangrove species classification with combination of WorldView-2 and Zhuhai-1 satellite images. National Remote Sensing Bulletin, 26(6): 1155-1168
高常军, 蒋侠朋, 甄佳宁, 王俊杰, 邬国锋, 2022. 耦合WorldView-2和珠海一号影像的红树林物种分布. 遥感学报, 26(6): 1155-1168 [DOI: 10.11834/jrs.20221487http://dx.doi.org/10.11834/jrs.20221487]
Gitelson A and Merzlyak M N. 1994. Spectral reflectance changes associated with autumn senescence of Aesculus hippocastanum L. and Acer platanoides L. leaves. Spectral features and relation to chlorophyll estimation. Journal of Plant Physiology, 143(3): 286-292 [DOI: 10.1016/s0176-1617(11)81633-0http://dx.doi.org/10.1016/s0176-1617(11)81633-0]
Gitelson A A, Gritz Y and Merzlyak M N. 2003. Relationships between leaf chlorophyll content and spectral reflectance and algorithms for non-destructive chlorophyll assessment in higher plant leaves. Journal of Plant Physiology, 160(3): 271-282 [DOI: 10.1078/0176-1617-00887http://dx.doi.org/10.1078/0176-1617-00887]
Gitelson A A, Viña A, Ciganda V, Rundquist D C and Arkebauer T J. 2005. Remote estimation of canopy chlorophyll content in crops. Geophysical Research Letters, 32(8): L08403 [DOI: 10.1029/2005gl022688http://dx.doi.org/10.1029/2005gl022688]
Haboudane D, Miller J R, Pattey E, Zarco-Tejada P J and Strachan I B. 2004. Hyperspectral vegetation indices and novel algorithms for predicting green LAI of crop canopies: modeling and validation in the context of precision agriculture. Remote Sensing of Environment, 90(3): 337-352 [DOI: 10.1016/j.rse.2003.12.013http://dx.doi.org/10.1016/j.rse.2003.12.013]
Haboudane D, Miller J R, Tremblay N, Zarco-Tejada P J and Dextraze L. 2002. Integrated narrow-band vegetation indices for prediction of crop chlorophyll content for application to precision agriculture. Remote Sensing of Environment, 81(2/3): 416-426 [DOI: 10.1016/S0034-4257(02)00018-4http://dx.doi.org/10.1016/S0034-4257(02)00018-4]
Haboudane D, Tremblay N, Miller J R and Vigneault P. 2008. Remote estimation of crop chlorophyll content using spectral indices derived from hyperspectral data. IEEE Transactions on Geoscience and Remote Sensing, 46(2): 423-437 [DOI: 10.1109/tgrs.2007.904836http://dx.doi.org/10.1109/tgrs.2007.904836]
Homolová L, Malenovský Z, Clevers J G P W, García-Santos G and Schaepman M E. 2013. Review of optical-based remote sensing for plant trait mapping. Ecological Complexity, 15: 1-16 [DOI: 10.1016/j.ecocom.2013.06.003http://dx.doi.org/10.1016/j.ecocom.2013.06.003]
Inoue Y, Sakaiya E, Zhu Y and Takahashi W. 2012. Diagnostic mapping of canopy nitrogen content in rice based on hyperspectral measurements. Remote Sensing of Environment, 126: 210-221 [DOI: 10.1016/j.rse.2012.08.026http://dx.doi.org/10.1016/j.rse.2012.08.026]
Jiang Z Y, Huete A R, Didan K and Miura T. 2008. Development of a two-band enhanced vegetation index without a blue band. Remote Sensing of Environment, 112(10): 3833-3845 [DOI: 10.1016/j.rse.2008.06.006http://dx.doi.org/10.1016/j.rse.2008.06.006]
Lanaras C, Bioucas-Dias J, Baltsavias E and Schindler K. 2017. Super-resolution of multispectral multiresolution images from a single sensor//Proceedings of 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops. Honolulu: IEEE: 1505-1513 [DOI: 10.1109/cvprw.2017.194http://dx.doi.org/10.1109/cvprw.2017.194]
Lee H, Wang J F and Leblon B. 2020. Using linear regression, random forests, and support vector machine with unmanned aerial vehicle multispectral images to predict canopy nitrogen weight in corn. Remote Sensing, 12(13): 2071 [DOI: 10.3390/rs12132071http://dx.doi.org/10.3390/rs12132071]
Lemaire G, Jeuffroy M H and Gastal F. 2008. Diagnosis tool for plant and crop N status in vegetative stage: theory and practices for crop N management. European Journal of Agronomy, 28(4): 614-624 [DOI: 10.1016/j.eja.2008.01.005http://dx.doi.org/10.1016/j.eja.2008.01.005]
Li Z, Tian H Q, Wang H, Xu L, Li F and Shi S D. 2016. Models of estimating sugar beet nitrogen using hyperspectral. Journal of Agricultural Mechanization Research, 38(6): 210-214
李哲, 田海清, 王辉, 徐琳, 李斐, 史树德. 2016. 基于高光谱的甜菜冠层氮素遥感估算研究. 农机化研究, 38(6): 210-214 [DOI: 10.3969/j.issn.1003-188X.2016.06.043http://dx.doi.org/10.3969/j.issn.1003-188X.2016.06.043]
Li Z H, Jin X L, Yang G J, Drummond J, Yang H, Clark B, Li Z H and Zhao C J. 2018. Remote sensing of leaf and canopy nitrogen status in winter wheat (Triticum aestivum L.) based on N-PROSAIL model. Remote Sensing, 10(9): 1463 [DOI: 10.3390/rs10091463http://dx.doi.org/10.3390/rs10091463]
Liu L Y. 2014. Quantitative Remote Sensing of Vegetation: Principle and Application. Beijing: Science Press
刘良云. 2014. 植被定量遥感原理与应用. 北京: 科学出版社
Loozen Y, Rebel K T, De Jong S M, Lu M, Ollinger S V, Wassen M J and Karssenberg D. 2020. Mapping canopy nitrogen in European forests using remote sensing and environmental variables with the random forests method. Remote Sensing of Environment, 247: 111933 [DOI: 10.1016/j.rse.2020.111933http://dx.doi.org/10.1016/j.rse.2020.111933]
Mao L J. 2011. Assessment of Changes in Mangrove Forest Patterns from Multitemporal Remotely Sensed Imagery Over Zhanjiang City, Guangdong Province. Nanjing: Nanjing Forestry University (毛丽君. 2011. 基于遥感的广东湛江红树林湿地动态变化研究. 南京: 南京林业大学)
Merzlyak M N, Gitelson A A, Chivkunova O B and Rakitin V Y. 1999. Non-destructive optical detection of pigment changes during leaf senescence and fruit ripening. Physiologia Plantarum, 106(1): 135-141 [DOI: 10.1034/j.1399-3054.1999.106119.xhttp://dx.doi.org/10.1034/j.1399-3054.1999.106119.x]
Rondeaux G, Steven M and Baret F. 1996. Optimization of soil-adjusted vegetation indices. Remote Sensing of Environment, 55(2): 95-107 [DOI: 10.1016/0034-4257(95)00186-7http://dx.doi.org/10.1016/0034-4257(95)00186-7]
Roujean J L and Breon F M. 1995. Estimating PAR absorbed by vegetation from bidirectional reflectance measurements. Remote Sensing of Environment, 51(3): 375-384 [DOI: 10.1016/0034-4257(94)00114-3http://dx.doi.org/10.1016/0034-4257(94)00114-3]
Rouse Jr J W, Haas R H, Schell J A, Deering D W and Harlan J C. 1974. Monitoring the Vernal Advancement and Retrogradation (Green Wave Effect) of Natural Vegetation. NASA/GSFC Type III Final Report. NASA/GSFC: 371
Sims D A and Gamon J A. 2002. Relationships between leaf pigment content and spectral reflectance across a wide range of species, leaf structures and developmental stages. Remote Sensing of Environment, 81(2/3): 337-354 [DOI: 10.1016/s0034-4257(02)00010-xhttp://dx.doi.org/10.1016/s0034-4257(02)00010-x]
Vincini M, Frazzi E and D’Alessio P. 2008. A broad-band leaf chlorophyll vegetation index at the canopy scale. Precision Agriculture, 9(5): 303-319 [DOI: 10.1007/s11119-008-9075-zhttp://dx.doi.org/10.1007/s11119-008-9075-z]
Wang J J, Li Z K, Jin X L, Liang G H, Struik P C, Gu J F and Zhou Y. 2019. Phenotyping flag leaf nitrogen content in rice using a three-band spectral index. Computers and Electronics in Agriculture, 162: 475-481 [DOI: 10.1016/j.compag.2019.04.042http://dx.doi.org/10.1016/j.compag.2019.04.042]
Wang L W and Wei Y X. 2013. Progress in Inversion of vegetation nitrogen concentration by hyperspectral remote sensing. Spectroscopy and Spectral Analysis, 33(10): 2823-2827.
王莉雯, 卫亚星. 2013. 植被氮素浓度高光谱遥感反演研究进展. 光谱学与光谱分析, 33(10): 2823-2827 [DOI: 10.3964/j.issn.1000-0593http://dx.doi.org/10.3964/j.issn.1000-0593(201310-2823-05]
Wang X K. 2006. Principles and Techniques of Plant Physiological Biochemical Experiment. 2nd ed. Beijing: Higher Education Press: 122-126
王学奎. 2006. 植物生理生化实验原理和技术. 2版. 北京: 高等教育出版社: 122-126
Wu C Y, Wang L, Niu Z, Gao S and Wu M Q. 2010. Nondestructive estimation of canopy chlorophyll content using Hyperion and Landsat/TM images. International Journal of Remote Sensing, 31(8): 2159-2167 [DOI: 10.1080/01431161003614382http://dx.doi.org/10.1080/01431161003614382]
Xie Q Y, Dash J, Huete A, Jiang A H, Yin G F, Ding Y L, Peng D L, Hall C C, Brown L, Shi Y, Ye H C, Dong Y Y and Huang W J. 2019. Retrieval of crop biophysical parameters from Sentinel-2 remote sensing imagery. International Journal of Applied Earth Observation and Geoinformation, 80: 187-195 [DOI: 10.1016/j.jag.2019.04.019http://dx.doi.org/10.1016/j.jag.2019.04.019]
Yang G J, Zhao C J, Pu R L, Feng H K, Li Z H, Li H L and Sun C H. 2015. Leaf nitrogen spectral reflectance model of winter wheat (Triticum aestivum) based on PROSPECT: simulation and inversion. Journal of Applied Remote Sensing, 9(1): 095976 [DOI: 10.1117/1.Jrs.9.095976http://dx.doi.org/10.1117/1.Jrs.9.095976]
Yu Q Z, Wang S Q and Zhou L. 2017. Investigation into the role of canopy structure traits and plant functional types in modulating the correlation between canopy nitrogen and reflectance in a temperate forest in Northeast China. Journal of Applied Remote Sensing, 11(4): 046013 [DOI: 10.1117/1.Jrs.11.046013http://dx.doi.org/10.1117/1.Jrs.11.046013]
Zhang M Z, Su W, Fu Y T, Zhu D H, Xue J H, Huang J X, Wang W, Wu J Y and Yao C. 2019. Super-resolution enhancement of Sentinel-2 image for retrieving LAI and chlorophyll content of summer corn. European Journal of Agronomy, 111: 125938 [DOI: 10.1016/j.eja.2019.125938http://dx.doi.org/10.1016/j.eja.2019.125938]
Zhang R and Ma J W. 2009. A feature selection algorithm for hyperspectral data with SVM-RFE. Geomatics and Information Science of Wuhan University, 34(7): 834-837
张睿, 马建文. 2009. 一种SVM-RFE高光谱数据特征选择算法. 武汉大学学报(信息科学版), 34(7): 834-837
Zhen J N, Jiang X P, Xu Y, Miao J, Zhao D M, Wang J J, Wang J Z and Wu G F. 2021. Mapping leaf chlorophyll content of mangrove forests with Sentinel-2 images of four periods. International Journal of Applied Earth Observation and Geoinformation, 102: 102387 [DOI: 10.1016/j.jag.2021.102387http://dx.doi.org/10.1016/j.jag.2021.102387]
Zhu Y J, Zhao F, Guo J L, Wu G J and Lin G X. 2016. Below-ground organic carbon distribution and burial characteristics of the Gaoqiao mangrove area in Zhanjiang, Guangdong, Southern China. Acta Ecologica Sinica, 36(23): 7841-7849
朱耀军, 赵峰, 郭菊兰, 武高洁, 林广旋. 2016. 湛江高桥红树林湿地有机碳分布及埋藏特征. 生态学报, 36(23): 7841-7849 [DOI: 10.5846/stxb201511102276http://dx.doi.org/10.5846/stxb201511102276]
相关文章
相关作者
相关机构