предыдущий|следующий

Cloud detection for FY-3D MERSI Ⅱ images combine radiative transfer simulation and shallow neural network

  • role： First author第一作者
  • Affiliation：

    State Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing, Wuhan University, Wuhan 430072, China

    School of Electronic Information, Wuhan University, Wuhan 430072, China

  • Email：jinsk@whu.edu.cn
  • Introduction：金适宽，研究方向为气溶胶遥感。E-mail： jinsk@whu.edu.cn
JIN Shikuan12,  
  • role： Corresponding author通信作者
  • Affiliation：

    State Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing, Wuhan University, Wuhan 430072, China

  • Email：yym863@whu.edu.cn
  • Introduction：马盈盈，研究方向为大气遥感。E-mail： yym863@whu.edu.cn
MA Yingying1*,  
  • Affiliation：

    State Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing, Wuhan University, Wuhan 430072, China

    School of Electronic Information, Wuhan University, Wuhan 430072, China

GONG Wei12,  
  • Affiliation：

    Hubei University of Technology, School of Computer Science, Wuhan 430068, China

YE Zhiwei3,  
  • Affiliation：

    Hubei University of Technology, School of Computer Science, Wuhan 430068, China

XIA Xiaoyu3

реферат

Cloud pixel detection is a crucial pre-process in numerous remote sensing applications, such as the aerosol parameter retrieval, land use change, anomaly detection/classification, crop monitoring, and marine ecological survey. On the one hand, cloud pixel misidentification (mistaken as surface or aerosol) in optical images has substantial negative effects on the above-mentioned traditional applications, due to the significant influence of cloud layers on shortwave radiation. On the other hand, traditional threshold methods are largely constrained in applicability by the high spatiotemporal heterogeneity of aerosols and clouds as well as the diversification of satellite sensors and spectral channels. Therefore, a reliable cloud detection method with wide applicability is in demand, especially for studies over multiple surfaces (i.e., land, ocean, and cryosphere). Thus, this study proposed an innovative method based on the radiative transfer simulation and machine learning, namely CRMC (Combine Reflectance simulation and Machine learning for Cloud detection), to detect cloud pixels in optical images produced from the MERSI Ⅱ sensor onboard the FY-3D satellite. The biggest advantage of this method is its compatibility with different sensors, generating cloud pixel samples through the physical process simulation, and applying the machine learning technique to learn sample features, thereby excluding the influence of anthropogenic factors. Specifically, to address the mismatch between the MODIS cloud detection algorithm and MERSI-based aerosol inversion, the CRMC method sets different Inherent Optical Properties (IOPs) of surface and atmospheric objects, considering binomial reflection characteristics of underlying surfaces and various parameters of aerosols and clouds. In addition, the method outputs cloud probabilities in pixels and allows custom thresholds to control the strictness level of cloud pixel detection. The CRMC method mainly includes three steps: (1) Defining 11 typical underlying reflectance parameters from MODIS binomial reflection products using a cluster analysis approach; (2) Inputting the typical underlying reflectance and aerosol and cloud parameters with random inherent optical properties into the SBDART radiation transmission model to obtain a simulated reflectance dataset for training the shallow neural network; (3) Calculating the cloud probability of the target image with the trained shallow neural network and selecting a suitable threshold according to the actual need to complete the cloud detection. Compared with the CALIPSO Vertical Feature Mask (VFM), results of the CRMC method show a maximum total accuracy of 79.6% (78.5% and 81.2% on land and sea, respectively). Under the condition of cloud probability threshold=0.2 (hit rates for cloud and cloud-free pixels are the same in these cases), the CRMC outperforms MODIS cloud mask products (MYD35) over land, especially on broad-leaved forest, farmland, urban and bare soil. However, the accuracy of the CRMC over sea is lower than that of MYD35. In the view of the surface uniformity, the cloud detection over sea can enrich the brightness temperature information to optimize the corresponding performance. To sum up, while greatly improving the applicability to different optical sensors by not relying on special spectral range, the CRMC method can achieve a good cloud pixel identification effect for FY-3D MERSI Ⅱ images, with a similar hit rate compared with MODIS products. Also, the CRMC has certain anti-disturbance ability to haze.

ключеви́че слова́

cloud detection;Radiative Transfer Simulation;neural network;FY-3D;MERSI II

References

  1. 1.
    Ackerman S A, Strabala K I, Menzel W P, Frey R A, Moeller C C and Gumley L E. 1998. Discriminating clear sky from clouds with MODIS. Journal of Geophysical Research: Atmospheres, 103(D24): 32141-32157
  2. 2.
    Chen X D, Zhang X, Liu L Y and Wang X F. 2019. Enhanced multi-temporal cloud detection algorithm for optical remote sensing images. Journal of Remote Sensing, 23(2): 280-290
  3. 3.
    Gao B C, Goetz A F H and Wiscombe W J. 1993. Cirrus cloud detection from Airborne Imaging Spectrometer data using the 1.38 μm water vapor band. Geophysical Research Letters, 20(4): 301-304
  4. 4.
    Hughes M J and Hayes D J. 2014. Automated detection of cloud and cloud shadow in single-date landsat imagery using neural networks and spatial post-processing. Remote Sensing, 6(6): 4907-4926
  5. 5.
    Irish R R, Barker J L, Goward S N and Arvidson T. 2006. Characterization of the Landsat-7 ETM+ automated cloud-cover assessment (ACCA) algorithm. Photogrammetric Engineering and Remote Sensing, 72(10): 1179-1188
  6. 6.
    Jiao Z T, Li X W, Wang J D and Zhang H. 2011. Assessment of MODIS BRDF shape indicators. Journal of Remote Sensing, 15(3): 432-456
  7. 7.
    Jin S K, Zhang M, Ma Y Y, Gong W, Chen C, Yang L K, Hu X Q, Liu B M, Chen N, Du B and Shi Y F. 2021. Adapting the dark target algorithm to advanced MERSI sensor on the FengYun-3-D satellite: retrieval and validation of aerosol optical depth over land. IEEE Transactions on Geoscience and Remote Sensing, 59(10): 8781-8797
  8. 8.
    Kotchenova S Y, Vermote E F, Levy R and Lyapustin A. 2008. Radiative transfer codes for atmospheric correction and aerosol retrieval: intercomparison study. Applied Optics, 47(13): 2215-2226. [10.1364/AO.47.002215]
  9. 9.
    Li X H, Shen H F, Zhang L P, Zhang H Y, Yuan Q Q and Yang G. 2014. Recovering quantitative remote sensing products contaminated by thick clouds and shadows using multitemporal dictionary learning. IEEE Transactions on Geoscience and Remote Sensing, 52(11): 7086-7098
  10. 10.
    Li Z W, Shen H F, Cheng Q, Liu Y H, You S C and He Z Y. 2019. Deep learning based cloud detection for medium and high resolution remote sensing images of different sensors. ISPRS Journal of Photogrammetry and Remote Sensing, 150: 197-212
  11. 11.
    Lin C H, Lin B Y, Lee K Y and Chen Y C. 2015. Radiometric normalization and cloud detection of optical satellite images using invariant pixels. ISPRS Journal of Photogrammetry and Remote Sensing, 106: 107-117
  12. 12.
    Liu C L and Wu B F. 2004. Application of cloud detection algorithm for the AVHRR data. Journal of Remote Sensing, 8(6):677-687
  13. 13.
    McClatchey R A, Fenn R W, Selby J E A, Volz F E and Garing J S. 1971. Optical Properties of the Atmosphere. AFCRL-TR-71-0279, Environment Research Papers, No 354, L.G. Hancom Fiel Bedford, Mass. USA
  14. 14.
    Meng F, Yang X M, Zhou C H and Li Z. 2017. A sparse dictionary learning-based adaptive patch inpainting method for thick clouds removal from high-spatial resolution remote sensing imagery. Sensors (Basel), 17(9): 2130
  15. 15.
    Peng L K，Liu L C，Chen X H，Chen J，Cao X and Qiu Y A. 2021. Generalization ability of cloud detection network for satellite imagery based on DeepLabv3+. National Remote Sensing Bulletin，25（5）：1169-1186
  16. 16.
    Ricchiazzi P, Yang S R, Gautier C and Sowle D. 1998. SBDART: a research and teaching software tool for plane-parallel radiative transfer in the Earth's atmosphere. Bulletin of the American Meteorological Society, 79(10): 2101-2114
  17. 17.
    Roujean J L, Leroy M and Deschamps P Y. 1992. A bidirectional reflectance model of the Earth’s surface for the correction of remote sensing data. Journal of Geophysical Research, 97(D18): 20455-20468
  18. 18.
    Segal-Rozenhaimer M, Li A L, Das K and Chirayath V. 2020. Cloud detection algorithm for multi-modal satellite imagery using convolutional neural-networks (CNN). Remote Sensing of Environment, 237: 111446
  19. 19.
    Stamnes K, Hamre B, Stamnes J J, Ryzhikov G, Biryulina M, Mahoney R, Hauss B and Sei A. 2011. Modeling of radiation transport in coupled atmosphere-snow-ice-ocean systems. Journal of Quantitative Spectroscopy and Radiative Transfer, 112(4): 714-726
  20. 20.
    Stowe L L, Davis P A and McClain E P. 1999. Scientific basis and initial evaluation of the CLAVR-1 global clear cloud classification algorithm for the advanced very high resolution radiometer. Journal of Atmospheric and Oceanic Technology, 16(6): 656-681
  21. 21.
    Sun L, Wei J, Wang J, Mi X T, Guo Y M, Lv Y, Yang Y K, Gan P, Zhou X Y, Jia C and Tian X P. 2016. A Universal Dynamic Threshold Cloud Detection Algorithm (UDTCDA) supported by a prior surface reflectance database. Journal of Geophysical Research: Atmospheres, 121(12): 7172-7196
  22. 22.
    Vermote E F, Tanre D, Deuze J L, Herman M and Morcette J J. 1997. Second simulation of the satellite signal in the solar spectrum, 6S: an overview. IEEE Transactions on Geoscience and Remote Sensing, 35(3): 675-686
  23. 23.
    Wei J, Huang W, Li Z Q, Sun L, Zhu X L, Yuan Q Q, Liu L and Cribb M. 2020. Cloud detection for Landsat imagery by combining the random forest and superpixels extracted via energy-driven sampling segmentation approaches. Remote Sensing of Environment, 248: 112005
  24. 24.
    Wei L S, Shang H Z, Husi L T, Ma R, Hu D H, Zhao K F, Si F Q and Shi J C. 2021. Cloud detection algorithm based on GF-5 DPC data. National Remote Sensing Bulletin, 25 (10)：2053-2066
  25. 25.
    Xu N, Niu X H, Hu X Q, Wang X H, Wu R H, Chen S S, Chen L, Sun L, Ding L, Yang Z D and Zhang P. 2018. Prelaunch calibration and radiometric performance of the advanced MERSI Ⅱ on FengYun-3D. IEEE Transactions on Geoscience and Remote Sensing, 56(8): 4866-4875
  26. 26.
    Yang Z D, Zhang P, Gu S Y, Hu X Q, Tang S H, Yang L K, Xu N, Zhen Z J, Wang L, Wu Q, Dou F L, Liu R X, Wu X, Zhu L, Zhang L Y, Wang S J, Sun Y Q and Bai W H. 2019. Capability of Fengyun-3D satellite in earth system observation. Journal of Meteorological Research, 33(6): 1113-1130
  27. 27.
    Yu C Y, Liang B, Bao C G, Li M, Hu Y Y, Lan D D, Xu Y, Lu H and Ma M H. 2013. Study on eutrophication status and trend in Bohai Sea. Marine Environmental Science, 32(2): 175-177
  28. 28.
    Luo J C, Zhou C H and Yang Y. 2001. ANN Remote Sensing Classification Model and Its Integration Approach with Geo-knowledge. Journal of Remote Sensing, 5(2):122-129
  29. 29.
    Zhang C, Li H F and Shen H F. 2020. Thin cloud correction for GF-5 AHSI visible images by combining statistical information with scattering model. Journal of Remote Sensing, 24(4): 368-378
  30. 30.
    Zhou H M, Yang W X and Lu X. 1995. Study on detecting cloud of NOAA satellite image. Journal of Remote Sensing, 10(2):137-142
  31. 31.
    Zhu Z and Woodcock C E. 2012. Object-based cloud and cloud shadow detection in Landsat imagery. Remote Sensing of Environment, 118: 83-94

Читать полностью

The above content is generated by Large Model Translation. The translated content is for reference only. We do not assume any commercial or legal responsibilty for any consequences arising from the use of our website