Research on method of surface reflectance reconstruction in the Tibetan Plateau based on MODIS data

CHEN Shanjing; ZHANG Wenjuan; ZHANG Bing; KANG Qing; XU Xu

doi:10.37188/OPE.20233104.0429

您当前的位置：

首页 >

文章列表页 >

Research on method of surface reflectance reconstruction in the Tibetan Plateau based on MODIS data

Modern Applied Optics | 更新时间：2026-09-12

- Research on method of surface reflectance reconstruction in the Tibetan Plateau based on MODIS data
- Optics and Precision Engineering Vol. 31, Issue 4, Pages: 429-441(2023)
- 作者机构：
  
  1.中国科学院空天信息创新研究院，数字地球重点实验室，北京 100094
  2.可持续发展大数据国际研究中心，北京 100094
  3.中国科学院空天信息创新研究院，北京 100094
  4.中国科学院大学，北京 100049
  5.陆军勤务学院，重庆 401311
- 作者简介：
- 基金信息：
- DOI：10.37188/OPE.20233104.0429
  CLC： TP75
- Received：01 July 2022，
  
  Revised：2022-10-25，
  
  Published：25 February 2023
- 稿件说明：
移动端阅览
陈善静,张文娟,张兵等.基于MODIS数据的青藏高原地表反射率重建方法研究[J].光学精密工程,2023,31(04):429-441.

CHEN Shanjing,ZHANG Wenjuan,ZHANG Bing,et al.Research on method of surface reflectance reconstruction in the Tibetan Plateau based on MODIS data[J].Optics and Precision Engineering,2023,31(04):429-441.
陈善静,张文娟,张兵等.基于MODIS数据的青藏高原地表反射率重建方法研究[J].光学精密工程,2023,31(04):429-441. DOI： 10.37188/OPE.20233104.0429.

CHEN Shanjing,ZHANG Wenjuan,ZHANG Bing,et al.Research on method of surface reflectance reconstruction in the Tibetan Plateau based on MODIS data[J].Optics and Precision Engineering,2023,31(04):429-441. DOI： 10.37188/OPE.20233104.0429.

摘要

青藏高原地表反射率在自然资源监测、生态环境保护和地球科学研究等方面有着重要应用。MOD09A1反射率数据由于云等因素的影响产生了大量异常像元，使得数据存在信息损失不完整的问题。考虑到邻近时序遥感影像具有高相关性，同类地物光谱具备高相似性，本文针对青藏高原地区提出了一种基于残缺多时相数据与地表覆盖分类信息的地表反射率深度学习重建方法。首先，以多时相MOD09A1反射率数据和MCD12Q1地表覆盖分类数据为基础，通过异常像元去除、有效图层提取、投影转换与拼接，得到目标区域基础反射率图像及辅助数据；其次，根据残差网络基本原理，构建了基于多时相数据与地表覆盖分类信息融合的深度学习网络模型；然后，利用MOD09A1数据完整区域裁剪的云掩膜样本、基于地表覆盖分类和K-means聚类算法生成的增广样本对模型进行训练；最后，将训练好的模型用于缺失数据区域地表反射率重建。通过两组对比试验表明，本文方法降低了对多时相辅助影像数据量和完整性的要求，在多时相数据残缺情况下，结合地表覆盖分类信息可实现对青藏高原大范围地表反射率的修复与重建。

Abstract

The surface reflectance of the Tibetan Plateau is exploited in numerous applications， such as natural resource monitoring， ecological environmental protection， and geoscience research. Typically， the reflectance data of MOD09A1 are affected by detector noise and clouds， producing numerous abnormal pixels and diminishing the integrity and accuracy of remote sensing data. To address these issues， considering the universal geoscience law indicating that neighboring time-series remote sensing images are correlative， and the spectra of adjacent ground objects belonging to the same classification are similar， this paper proposes a deep learning method of surface reflectance reconstruction in the Tibetan Plateau based on incomplete multi-temporal data and land cover classification information. First， based on the multi-temporal reflectance data of MOD09A1 and land cover classification data of MCD12Q1， the basic reflectance image and auxiliary data of the target area are obtained through abnormal pixel removal， effective layer extraction， projection conversion， and mosaic. Subsequently， a deep learning network model is constructed based on the fusion of multi-temporal data and land cover classification information， according to basic principles of the residual network. Third， the deep learning model is trained using cloud mask samples cropped from an area with complete data and augmented training samples generated based on land cover classification and the K-means clustering algorithm. Finally， the trained model is utilized for surface reflectance reconstruction in the area with missing data. Two groups of comparative experiments demonstrate that the proposed method reduces the requirements for the amount and integrity of multi-temporal auxiliary image data and achieves accurate restoration and reconstruction of large-scale surface reflectance in the Tibetan Plateau by combining incomplete multi-temporal data and land cover classification information.

关键词

Keywords

references

HONGBO ， ZHANG . Creating 1-km long-term （1980-2014） daily average air temperatures over the Tibetan Plateau by integrating eight types of reanalysis and land data assimilation products downscaled with MODIS-estimated temperature lapse rates based on machine learning ［J］. International Journal of Applied Earth Observation and Geoinformation ， 2021 ， 97 ： 102295 . doi: 10.1016/j.jag.2021.102295 http://dx.doi.org/10.1016/j.jag.2021.102295

王兴玲，刘龙飞，于钢，等 . 全球陆地光学遥感影像获取技术与应用［J］. 光学精密工程， 2012 ， 20 （ 10 ）： 2324 - 2330 . doi: 10.3788/ope.20122010.2324 http://dx.doi.org/10.3788/ope.20122010.2324

WANG X L ， LIU L F ， YU G ， et al . Global optical image acquisition technology and its applications ［J］. Opt. Precision Eng. ， 2012 ， 20 （ 10 ）： 2324 - 2330 . （in Chinese） . doi: 10.3788/ope.20122010.2324 http://dx.doi.org/10.3788/ope.20122010.2324

XIA M ， JIA K . Reconstructing missing information of remote sensing data contaminated by large and thick clouds based on an improved multitemporal dictionary learning method ［J］. IEEE Transactions on Geoscience and Remote Sensing ， 2022 ， 60 ： 1 - 14 . doi: 10.1109/tgrs.2021.3095067 http://dx.doi.org/10.1109/tgrs.2021.3095067

ANGEL Y ， HOUBORG R ， MCCABE M F . Reconstructing cloud contaminated pixels using spatiotemporal covariance functions and multitemporal hyperspectral imagery ［J］. Remote Sensing ， 2019 ， 11 （ 10 ）： 1145 . doi: 10.3390/rs11101145 http://dx.doi.org/10.3390/rs11101145

XIAO Z Q ， LIANG S L ， TIAN X D ， et al . Reconstruction of long-term temporally continuous NDVI and surface reflectance from AVHRR data ［J］. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing ， 2017 ， 10 （ 12 ）： 5551 - 5568 . doi: 10.1109/jstars.2017.2744979 http://dx.doi.org/10.1109/jstars.2017.2744979

WU Y H ， LI M R ， GUO L N ， et al . Investigating water variation of lakes in Tibetan Plateau using remote sensed data over the past 20 years ［J］. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing ， 2019 ， 12 （ 7 ）： 2557 - 2564 . doi: 10.1109/jstars.2019.2898259 http://dx.doi.org/10.1109/jstars.2019.2898259

TSENG D CH ， TSENG H T ， CHIEN CH L . Automatic cloud removal from multi-temporal SPOT images ［J］. Applied Mathematics and Computation ， 2008 ， 205 ： 584 – 600 . doi: 10.1016/j.amc.2008.05.050 http://dx.doi.org/10.1016/j.amc.2008.05.050

QING ， CHENG . Cloud removal for remotely sensed images by similar pixel replacement guided with a spatio-temporal MRF model ［J］. ISPRS Journal of Photogrammetry and Remote Sensing ， 2014 ， 92 ： 54 - 68 . doi: 10.1016/j.isprsjprs.2014.02.015 http://dx.doi.org/10.1016/j.isprsjprs.2014.02.015

WANG Y X ， ZHANG W J ， CHEN S J ， et al . Rapidly single-temporal remote sensing image cloud removal based on land cover data ［C］. IGARSS 2022 - 2022 IEEE International Geoscience and Remote Sensing Symposium . 1722，2022 ， Kuala Lumpur， Malaysia . IEEE ， 2022 ： 3307 - 3310 . doi: 10.1109/igarss46834.2022.9883184 http://dx.doi.org/10.1109/igarss46834.2022.9883184

ZHANG Y J ， WEN F ， GAO Z ， et al . A coarse-to-fine framework for cloud removal in remote sensing image sequence ［J］. IEEE Transactions on Geoscience and Remote Sensing ， 2019 ， 57 （ 8 ）： 5963 - 5974 . doi: 10.1109/tgrs.2019.2903594 http://dx.doi.org/10.1109/tgrs.2019.2903594

QIANG ， ZHANG . Thick cloud and cloud shadow removal in multitemporal imagery using progressively spatio-temporal patch group deep learning ［J］. ISPRS Journal of Photogrammetry and Remote Sensing ， 2020 ， 162 ： 148 - 160 . doi: 10.1016/j.isprsjprs.2020.02.008 http://dx.doi.org/10.1016/j.isprsjprs.2020.02.008

申茜，姚月，李利伟，等 . 北京市平原区2015年—2019年0.8 m地表反射率数据集［J］. 遥感学报， 2021 ， 25 （ 11 ）： 2303 - 2312 .

SHEN Q ， YAO Y ， LI L W ， et al . Annual 0.8 m surface reflectance data set of Beijing plain area from 2015 to 2019 ［J］. National Remote Sensing Bulletin ， 2021 ， 25 （ 11 ）： 2303 - 2312 . （in Chinese）

孙华生，张远，史云飞，等 . 利用无人机搭载的多光谱相机直接测定地表反射率的新方法［J］. 光谱学与光谱分析， 2022 ， 42 （ 5 ）： 1581 - 1587 . doi: 10.3964/j.issn.1000-0593(2022)05-1581-07 http://dx.doi.org/10.3964/j.issn.1000-0593(2022)05-1581-07

SUN H SH ， ZHANG Y ， SHI Y F ， et al . A new method for direct measurement of land surface reflectance with UAV-based multispectral cameras ［J］. Spectroscopy and Spectral Analysis ， 2022 ， 42 （ 5 ）： 1581 - 1587 . （in Chinese） . doi: 10.3964/j.issn.1000-0593(2022)05-1581-07 http://dx.doi.org/10.3964/j.issn.1000-0593(2022)05-1581-07

何兴伟，胡秀清，何灵莉，等 . 我国西北部沙漠定标场网的地表反射率光谱特征模型［J］. 光学学报， 2022 ， 42 （ 6 ）： 249 - 258 . doi: 10.3788/AOS202242.0628003 http://dx.doi.org/10.3788/AOS202242.0628003

HE X W ， HU X Q ， HE L L ， et al . Surface reflectance spectral characteristic model of desert calibration site network in northwest China ［J］. Acta Optica Sinica ， 2022 ， 42 （ 6 ）： 249 - 258 . （in Chinese） . doi: 10.3788/AOS202242.0628003 http://dx.doi.org/10.3788/AOS202242.0628003

徐芳，刘晶红，孙辉，等 . 光学遥感图像海面船舶目标检测技术进展［J］. 光学精密工程， 2021 ， 29 （ 4 ）： 916 - 931 . doi: 10.37188/OPE.2020.0419 http://dx.doi.org/10.37188/OPE.2020.0419

XU F ， LIU J H ， SUN H ， et al . Research progress on vessel detection using optical remote sensing image ［J］. Opt. Precision Eng. ， 2021 ， 29 （ 4 ）： 916 - 931 . （in Chinese） . doi: 10.37188/OPE.2020.0419 http://dx.doi.org/10.37188/OPE.2020.0419

ANDREA ， MERANER . Cloud removal in Sentinel-2 imagery using a deep residual neural network and SAR-optical data fusion ［J］. ISPRS Journal of Photogrammetry and Remote Sensing ， 2020 ， 166 ： 333 - 346 . doi: 10.1016/j.isprsjprs.2020.05.013 http://dx.doi.org/10.1016/j.isprsjprs.2020.05.013

车向红，冯敏，姜浩，等 . 2000—2013年青藏高原湖泊面积MODIS遥感监测分析［J］. 地球信息科学学报， 2015 ， 17 （ 1 ）： 99 - 107 . doi: 10.3724/SP.J.1047.2015.00099 http://dx.doi.org/10.3724/SP.J.1047.2015.00099

CHE X H ， FENG M ， JIANG H ， et al . Detection and analysis of Qinghai-Tibet Plateau Lake area from 2000 to 2013 ［J］. Journal of Geo-Information Science ， 2015 ， 17 （ 1 ）： 99 - 107 . （in Chinese） . doi: 10.3724/SP.J.1047.2015.00099 http://dx.doi.org/10.3724/SP.J.1047.2015.00099

赵凤美，戴聪明，魏合理，等 . 基于MODIS云参数的卷云反射率计算研究［J］. 红外与激光工程， 2018 ， 47 （ 9 ）： 270 - 276 . doi: 10.3788/irla201847.0917006 http://dx.doi.org/10.3788/irla201847.0917006

ZHAO F M ， DAI C M ， WEI H L ， et al . Calculating the reflectance of cirrus clouds based on cirrus properties from MODIS ［J］. Infrared and Laser Engineering ， 2018 ， 47 （ 9 ）： 270 - 276 . （in Chinese） . doi: 10.3788/irla201847.0917006 http://dx.doi.org/10.3788/irla201847.0917006

辛蕾，李峰，鲁啸天，等 . 面向光学遥感影像的高效编码与重构［J］. 光学精密工程， 2021 ， 29 （ 12 ）： 2956 - 2963 . doi: 10.37188/OPE.20212912.2956 http://dx.doi.org/10.37188/OPE.20212912.2956

XIN L ， LI F ， LU X T ， et al . Efficient coding and reconstruction for optical remote sensing images ［J］. Opt. Precision Eng. ， 2021 ， 29 （ 12 ）： 2956 - 2963 . （in Chinese） . doi: 10.37188/OPE.20212912.2956 http://dx.doi.org/10.37188/OPE.20212912.2956

Views

1573

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

High-precision deep learning-based single-frame interferometric decoupling for measuring optical homogeneity of parallel plates

Multi-scale image enhancement in turbid water via spatial-frequency domain fusion

Inverse design of efficient achromatic metalens based on channel attention enhanced network

Real-time prediction of subsequent frames in broadband video based on optical flow method

Monocular vision-based spatial registration for implant surgery robots

Related Author

ZHOU Shunye

TANG Liang

CUI Han

QIU Lirong

ZHAO Weiqian

ZHANG Hao

ZHANG Qingwen

LIU Fei

Related Institution

School of Optics and Photonics， Beijing Institute of Technology

School of Information Management， Qingdao University of Technology

School of Physics and Optoelectronic Engineering， Xidian University

School of Physical and Optoelectronic Engineering， Hangzhou Institute for Advanced Study， University of Chinese Academy of Sciences

Key Laboratory of Space Active Opto-Electronics Technology， Shanghai Institute of Technical Physics， Chinese Academy of Sciences

AI问答

Address：No.3888 Dong Nanhu Road, Changchun, Jilin, China Postal code：130033
Tel：0431-86176855 Email：gxjmgc@ciomp.ac.cn
Technical support is provided by Beijing Founder electronics co., LTD 吉ICP备11002662号-17 京公网安备11010802024621
It is recommended to read the content of this site in Chrome&IE9+. Please switch to extreme mode in browser 360.
Cookies We use cookies to help provide and enhance our service and tailor content. By continuing, you agree to the use of cookies.

⁰