Skip to main content
SpringerLink
Log in

Reconstruction of Missing Imagery Data Caused by Cloudcover Based on Beyesian Neural Network and Multitemporal Images

  • Conference paper
  • First Online:
Advances and Applications in Geospatial Technology and Earth Resources (GTER 2017)

  • 1142 Accesses

Abstract

One of passive sensor’s limitations is its high sensitivity to weather condition during image acquiring process. Consequently, the image is often affected by cloud cover. This phenomenon severely influences the completeness of land use/cover obtained from optical satellite imagery and make image processing more complicatedly. However, the pattern of pixel values based on the season and weather changes determined from substantial remote sensing data within a region can help to reconstruct the imagery data which was missed due to the presence of clouds. Taking advantage of datasets containing a substantial amount of multitemporal images, this study proposed a method to reconstruct missed imagery data caused by cloud cover based on relationship between air temperature, humidity, visibility, rainfall, normalized difference vegetation index, direct solar radiation, diffuse solar radiation, reflected radiation and spectral radiance of each pixel obtained by Beyesian Neural Network. The proposed method was applied to generate a cloud-free Landsat image. The results showed that pixels generated by the proposed algorithm are very similar to the actual pixels, especially in non-change area with percentage of correlation coefficients (R) over 0.99 is approximate to 91%. However, the similarity reduced in areas which changed significantly over time period, with the percentages of R over 0.99 are about 78%.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution
Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 189.00
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 249.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info
Hardcover Book
USD 249.99
Price excludes VAT (USA)
  • Durable hardcover edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

References

  1. Ju, J., Roy, D.P.: The availability of cloud-free Landsat ETM + data over the conterminous United States and globally. Remote Sens. Environ. 112, 1196–1211 (2008)

    Article  Google Scholar 

  2. Melgani, F.: Contextual reconstruction of cloud-contaminated multitemporal multispectral images. IEEE Trans. Geosci. Remote Sens. 44, 442–455 (2006)

    Article  Google Scholar 

  3. La, H.P., Eo, Y.D., Lee, S., Park, W.Y., Koo, J.H.: Image simulation from multitemporal landsat images. GISci. Remote Sens. 52, 586–608 (2015)

    Google Scholar 

  4. Liew, S.C., Li, M., Kwoh, L.K., Chen, P., Lim, H.: Cloud-free multi-scene mosaics of SPOT images. In: International Geoscience and Remote Sensing Symposium 2, pp. 1083–1085. IEEE Press, Seattle (1998)

    Google Scholar 

  5. Abd-Elrahman, A., Shaker, I.F., Abdel-Gawad, A.K., Abdel-Wahab, A.: Enhancement of cloud-associated shadow areas in satellite images using wavelet image fusion. World Appl. Sci. 4, 363–370 (2008)

    Google Scholar 

  6. Tseng, D.C., Tseng, H.T., Chien, C.L.: Automatic cloud removal from multi-temporal SPOT images. Appl. Math. Comput. 205, 584–600 (2008)

    Google Scholar 

  7. Gui, Z., Chen, F., Yang, J., Li, X., Li, F., Zhao, J.: Automatic cloud and cloud shadow removal method for landsat TM images. In: 10th International Conference on Electronic Measurement & Instruments (ICEMI), pp. 80–84. IEEE Press, Chengdu (2011)

    Google Scholar 

  8. Jin, S., Homer, C., Yang, L., Xian, G., Fry, J., Danielson, P., Townsend, P.A.: Automated cloud and shadow detection and filling using two-date Landsat imagery in the USA. Int. J. Remote Sens. 34, 1540–1560 (2013)

    Article  Google Scholar 

  9. Li, M., Liew, S., Kwoh, L.: Automated production of cloudfree and cloud shadow-free image mosaics from cloudy satellite imagery. In: 20th Congress of the International Society of Photogrammetry and Remote Sensing, pp. 15–23 (2004)

    Google Scholar 

  10. Gui, Z., Liu, J., Chen, F.: Automatic local phenology simulation for landsat TM image. In: 2012 IEEE International Conference on Information Science and Technology, Wuhan, Hubei, China (2012)

    Google Scholar 

  11. Helmer, E.H., Ruefenacht, B.: Cloud-free satellite image mosaics with regression trees and histogram matching. Photogram. Eng. Remote Sens. 9, 1079–1089 (2005)

    Article  Google Scholar 

  12. Hwang, T., Song, C., Bolstad, P.V., Band, L.E.: Downscaling real-time vegetation dynamics by fusing multi-temporal MODIS and Landsat NDVI in topographically complex terrain. Remote Sens. Environ. 115, 2499–2512 (2011)

    Article  Google Scholar 

  13. Lin, C.-H., Tsai, P.-H., Lai, K.-H., Chen, J.-Y.: Cloud removal from multitemporal satellite images using information cloning. IEEE Trans. Geosci. Remote Sens. 51, 232–241 (2013)

    Article  Google Scholar 

  14. Guyet, T., Nicolas, H.: Long term analysis of time series of satellite images. Pattern Recogn. Lett. 70, 17–23 (2016)

    Article  Google Scholar 

  15. Harter, F.P., de Campos Velho, H.F.: New approach to applying neural network in nonlinear dynamic model. Appl. Math. Model. 32, 2621–2633 (2008)

    Article  Google Scholar 

  16. Xiong, C., Li, T.: Application of artificial neural networks to prediction of deformation in deep foundation pit. In: 2011 International Conference on Multimedia Technology (ICMT), pp. 1448–1453. IEEE Press, Hangzhou (2011)

    Google Scholar 

  17. Amato, F., Havel, J., Gad, A.-A., El-Zeiny, A.M.: Remotely sensed soil data analysis using artificial neural networks: a case study of el-fayoum depression, Egypt. ISPRS Int. J. Geo-Inf. 4, 677–696 (2015)

    Article  Google Scholar 

  18. Ticknor, J.L.: A Bayesian regularized artificial neural network for stock market forecasting. Expert Syst. Appl. 40, 5501–5506 (2013)

    Article  Google Scholar 

  19. KMA. http://web.kma.go.kr/eng/biz/climate_01.jsp

  20. MacKay, D.J.C.: Bayesian interpolation. Neural Comput. 4, 415–447 (1992)

    Article  Google Scholar 

  21. Hernández-Lobato, J.M., Adams, R.P.: Probabilistic backpropagation for scalable learning of Bayesian neural networks. In: 32nd International Conference on Machine Learning, vol. 37, pp. 1861–1869. JMLR, Lille (2015)

    Google Scholar 

  22. Lampinen, J., Vehtari, A.: Bayesian approach for neural networks – review and case studies. Neural Netw. 14, 7–24 (2001)

    Article  Google Scholar 

  23. Burden, F., Winkler, D.: Bayesian regularization of neural networks. Methods Mol. Biol. 458, 25–44 (2008)

    Google Scholar 

  24. Chander, G., Markham, B.: Revised Landsat-5 TM radiometric calibration procedures and postcalibration dynamic ranges. IEEE Trans. Geosci. Remote Sens. 41, 2674–2677 (2003)

    Article  Google Scholar 

  25. Ouaidrari, H., Vermote, E.F.: Operational atmospheric correction of landsat TM data. Remote Sens. Environ. 70, 4–15 (1999)

    Article  Google Scholar 

  26. Ratti, C., Richens, P.: Raster analysis of urban form. Environ. Plan. 31, 297–309 (2004)

    Article  Google Scholar 

  27. Kumar, L., Skidmore, A.K., Knowles, E.: Modelling topographic variation in solar radiation in a GIS environment. Int. J. Geogr. Inf. Sci. 11, 475–497 (1997)

    Article  Google Scholar 

  28. Photon Research Associates: GCI Toolkit Manual. Photon Research Associates, San Diego, CA (1998)

    Google Scholar 

  29. Schott, J.R.: Remote Sensing: The Image Chain Approach, 2nd edn. Oxford University Press, New York (2007)

    Google Scholar 

  30. Rouse, J.W., Haas, R.H., Schell, J.A., Deering, D.W.: Monitoring vegetation systems in the great plains with ERTS. In: 3rd ERTS Symposium, pp. 309–317. NASA SP-351, NASA, Washington, DC (1974)

    Google Scholar 

  31. Pham, B.T., Bui, D.T., Prakash, I., Dholakia, M.B.: Hybrid integration of Multilayer Perceptron Neural Networks and machine learning ensembles for landslide susceptibility assessment at Himalayan area (India) using GIS. CATENA 149, 52–63 (2017)

    Article  Google Scholar 

  32. Maduako, I.D., Yun, Z., Patrick, B.: Simulation and prediction of land surface temperature (LST) dynamics within Ikom City in Nigeria using artificial neural network (ANN). J. Remote Sens. GIS 5, 1–7 (2016)

    Google Scholar 

  33. Zupan, J.G.J.: Neural Networks in Chemistry and Drug Design, 2nd edn. Wiley VCH, Weinheim (1999)

    Google Scholar 

  34. Ahmed, F.E.: Artificial neural networks for diagnosis and survival prediction in colon cancer. Mol. Cancer 4 (2005)

    Google Scholar 

  35. Carvalho Júnior, O.A., Guimarães, R.F., Gillespie, A.R., Silva, N.C., Gomes, R.A.T.: A new approach to change vector analysis using distance and similarity measures. Remote Sens. 3, 2473–2493 (2011)

    Article  Google Scholar 

  36. Benabdelkader, S., Melgani, F., Boulemden, M.: Cloud-contaminated image reconstruction with contextual spatio-spectral information. In: IEEE International Geoscience and Remote Sensing Symposium, pp. 373–376, IEEE Press, Barcelona (2007)

    Google Scholar 

Download references

Acknowledgement

This work was supported by Vietnam National Foundation of Science and Technology Development under the project 105.99-2014.15.

Author information

Authors and Affiliations

  1. Faculty of Geomatics and Land Administration, Hanoi University of Mining and Geology, Hanoi, Vietnam

    Hien Phu La & Minh Quang Nguyen

Authors
  1. Hien Phu La
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Minh Quang Nguyen
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Hien Phu La .

Editor information

Editors and Affiliations

  1. GIS group, Department of Business and IT, University College of Southeast Norway , Bo i Telemark, Norway

    Dieu Tien Bui

  2. Department of Underground and Mining Construction, Hanoi University of Mining and Geology , Hanoi, Vietnam

    Anh Ngoc Do

  3. Department of Exploration Geology, Hanoi University of Mining and Geology , Hanoi, Vietnam

    Hoang-Bac Bui

  4. Faculty of Civil Engineering, Duy Tan University , Da Nang, Vietnam

    Nhat-Duc Hoang

Rights and permissions

Reprints and permissions

Copyright information

© 2018 Springer International Publishing AG

About this paper

Cite this paper

La, H.P., Nguyen, M.Q. (2018). Reconstruction of Missing Imagery Data Caused by Cloudcover Based on Beyesian Neural Network and Multitemporal Images. In: Tien Bui, D., Ngoc Do, A., Bui, HB., Hoang, ND. (eds) Advances and Applications in Geospatial Technology and Earth Resources. GTER 2017. Springer, Cham. https://doi.org/10.1007/978-3-319-68240-2_6

Download citation

Publish with us

Policies and ethics

Search

Navigation