Журнал

About Editorial Board Information for authors and reviewers Publication ethics Contacts User Account: send / review a manuscript
Archive
Volume 21, 2024
Number 1 Number 2 Number 3 Number 4 Number 5
Volume 20, 2023
Number 1 Number 2 Number 3 Number 4 Number 5 Number 6
Volume 19, 2022
Number 1 Number 2 Number 3 Number 4 Number 5 Number 6
Volume 18, 2021
Number 1 Number 2 Number 3 Number 4 Number 5 Number 6
Volume 17, 2020
Number 1 Number 2 Number 3 Number 4 Number 5 Number 6 Number 7
Volume 16, 2019
Number 1 Number 2 Number 3 Number 4 Number 5 Number 6
Volume 15, 2018
Number 1 Number 2 Number 3 Number 4 Number 5 Number 6 Number 7
Volume 14, 2017
Number 1 Number 2 Number 3 Number 4 Number 5 Number 6 Number 7
Volume 13, 2016
Number 1 Number 2 Number 3 Number 4 Number 5 Number 6
Volume 12, 2015
Number 1 Number 2 Number 3 Number 4 Number 5 Number 6
Volume 11, 2014
Number 1 Number 2 Number 3 Number 4
Volume 10, 2013
Number 1 Number 2 Number 3 Number 4
Volume 9, 2012
Number 1 Number 2 Number 3 Number 4 Number 5
Volume 8, 2011
Number 1 Number 2 Number 3 Number 4
Volume 7, 2010
Number 1 Number 2 Number 3 Number 4
Issue 6, 2009
Volume 1 Volume 2
Issue 5, 2008
Volume 1 Volume 2
Issue 4, 2007
Volume 1 Volume 2
Issue 3, 2006
Volume 1 Volume 2
Issue 2, 2005
Volume 1 Volume 2
Issue 1, 2004
Volume 1
Search
Find:
русский
ISSN 2070-7401 (Print), ISSN 2411-0280 (Online)
Sovremennye problemy distantsionnogo zondirovaniya Zemli iz kosmosa
CURRENT PROBLEMS IN REMOTE SENSING OF THE EARTH FROM SPACE

  

Sovremennye problemy distantsionnogo zondirovaniya Zemli iz kosmosa, 2024, Vol. 21, No. 4, pp. 33-46

Leveraging machine learning for radar-optical cloud-free time series synthesis of high spatial and temporal resolution

D.E. Plotnikov 1 , Z. Zhou 2 
1 Space Research Institute RAS, Moscow, Russia
2 Lomonosov Moscow State University, Moscow, Russia
Accepted: 22.07.2024
DOI: 10.21046/2070-7401-2024-21-4-33-46
In the paper, we study the potential of the Random Forest machine learning algorithm with respect to the problem of synthesizing cloud-free NDVI images based on the joint use of Sentinel 1 C-band radar and Sentinel 2 optical satellite imaging system MSI (Multispectral Instrument) paired datasets. We developed a method for building and optimizing a machine learning model aimed at cross-sensor synthesis of cloud-free NDVI values based on radar, topographic and thematic predictors constructed for synchronous pairs of Sentinel 1 and Sentinel 2 satellite images acquired during the growing season of 2021. In the process of model optimization, recursive features elimination (RFE) and cross-validation were used, while grid search was used to find the best model parameters combination. As a result of model predictions, time series of cloud-free NDVI images of high spatial and temporal resolution were produced for Kaliningrad region area on the basis of only Sentinel 1 radar data. The effectiveness of the developed approach is indicated by the high performance metrics of the model obtained from the test set: root mean squared error (RMSE = 0.12), correlation coefficient (R = 0.78), mean absolute error (MAE = 0.08) and Willmott Index of Agreement (WIA = 0.87). We demonstrate that Random Forest has significant potential for use in cross-sensor synthesis of cloud-free NDVI time series reconstruction.
Keywords: cross-sensor synthesis, Sentinel 1, Sentinel 2, time series reconstruction, machine learning, cross-validation, recursive feature elimination, grid search
Full text

References:

  1. Gavrilyuk E. A., Plotnikova A. S., Plotnikov D. E., Land cover mapping of the Pechora-Ilych Nature Reserve and its vicinity based on reconstructed multitemporal Landsat satellite data, Sovremennye problemy distantsionnogo zondirovaniya Zemli iz kosmosa, 2018, Vol. 15, No. 5, pp. 141–153 (in Russian), DOI: 10.21046/2070-7401-2018-15-5-141-153.
  2. Loupian E. A., Bartalev S. A., Krasheninnikova Yu. S. et al., Analysis of winter crops development in the southern regions of the European part of Russia in spring of 2018 with use of remote monitoring, Sovremennye problemy distantsionnogo zondirovaniya Zemli iz kosmosa, 2018, Vol. 15, No. 2, pp. 272–276 (in Russian), DOI: 10.21046/2070-7401-2018-15-2-272-276.
  3. Loupian E. A., Proshin A. A., Bourtsev M. A. et al., Experience of development and operation of the IKI-Monitoring center for collective use of systems for archiving, processing and analyzing satellite data, Sovremennye problemy distantsionnogo zondirovaniya Zemli iz kosmosa, 2019, Vol. 16, No. 3, pp. 151–170 (in Russian), DOI: 10.21046/2070-7401-2019-16-3-151-170.
  4. Plotnikov D. E., Khvostikov S. A., Bartalev S. A. (2018a), Method for automated crop types mapping using remote sensing data and a plant growth simulation model, Sovremennye problemy distantsionnogo zondirovaniya Zemli iz kosmosa, 2018, Vol. 15, No. 4, pp. 131–141 (in Russian), DOI: 10.21046/2070-7401-2018-15-4-131-141.
  5. Plotnikov D. E., Kolbudaev P. A., Bartalev S. A., Loupian E. A. (2018b), Automated annual cropland mapping from reconstructed time series of Landsat data, Sovremennye problemy distantsionnogo zondirovaniya Zemli iz kosmosa, 2018, Vol. 15, No. 2, pp. 112–127 (in Russian), DOI: 10.21046/2070-7401-2018-15-2-112-127.
  6. Plotnikov D. E., Elkina E. S., Dunaieva Ie. A. et al., Development of the method for automatic winter crops mapping by means of remote sensing aimed at crops state assessment over the Republic of Crimea, Taurida Herald of the Agrarian Sciences, 2020, No. 1(21), pp. 64–83 (in Russian), DOI: 10.33952/2542-0720-2020-1-21-64-83.
  7. Savin I. Yu., Bartalev S. A., Loupian E. A., Tolpin V. A., Medvedeva M. A., Plotnikov D. E., Satellite monitoring of vegetation affected by drought (using drought 2010 in Russia as an example), Sovremennye problemy distantsionnogo zondirovaniya Zemli iz kosmosa, 2011, Vol. 8, No. 1, pp. 150–162 (in Russian).
  8. Sereda I. I., Denisov P. V., Troshko K. A. et al., The unique situation of winter crops development observed from remote sensing data in the European territory of Russia in October 2020, Sovremennye problemy distantsionnogo zondirovaniya Zemli iz kosmosa, 2020, Vol. 17, No. 5, pp. 304–310 (in Russian), DOI: 10.21046/2070-7401-2020-17-5-304-310.
  9. Shabanov N. V., Bartalev S. A., Eroshenko F. V., Plotnikov D. E., Development of capabilities for remote sensing estimate of Leaf Area Index from MODIS data, Sovremennye problemy distantsionnogo zondirovaniya Zemli iz kosmosa, 2018, Vol. 15, No. 4, pp. 166–178 (in Russian), DOI: 10.21046/2070-7401-2018-15-4-166-178.
  10. Alvarez-Mozos J., Villanueva J., Arias M., Gonzalez-Audicana M., Correlation between NDVI and Sentinel 1 derived features for maize, 2021 IEEE Intern. Geoscience and Remote Sensing Symp. IGARSS, 2021. pp. 6773–6776, DOI: https://10.1109/IGARSS47720.2021.9554099.
  11. Breiman L., Random Forests, Machine Learning, 2001, Vol. 45, No. 1, DOI: 10.1023/A:1010933404324.
  12. Dos Santos E. P., Da Silva D. D., Do Amaral C. H., Vegetation cover monitoring in tropical regions using SAR-C dual-polarization index: seasonal and spatial influences, Intern. J. Remote Sensing, 2021, Vol. 42, Issue 19, pp. 7581–7609, DOI: 10.1080/01431161.2021.1959955.
  13. Dos Santos E. P., Da Silva D. D., Do Amaral C. H. et al., A Machine Learning approach to reconstruct cloudy affected vegetation indices imagery via data fusion from Sentinel 1 and Landsat-8, Computers and Electronics in Agriculture, 2022, Vol. 194, Article 106753, DOI: https://doi.org/10.1016/j.compag.2022.106753.
  14. Gao F., Masek J., Schwaller M., Hall F., On the blending of the Landsat and MODIS surface reflectance: Predicting daily Landsat surface reflectance, IEEE Trans. Geoscience and Remote Sensing, 2006, Vol. 44, No. 8, P. 2207–2218, DOI: 10.1109/TGRS.2006.872081.
  15. Gorelick N., Hancher M., Dixon M. et al., Google Earth Engine: Planetary-scale geospatial analysis for everyone, Remote Sensing of Environment, 2017, Vol. 202, pp. 18–27, https://doi.org/10.1016/j.rse.2017.06.031.
  16. Karra K., Kontgis C., Statman-Weil Z. et al., Global land use/land cover with Sentinel 2 and deep learning, 2021 IEEE Intern. Geoscience and Remote Sensing Symp. IGARSS, 2021, pp. 4704–4707, DOI: 10.1109/IGARSS47720.2021.9553499.
  17. Lin H., Chen J., Pei Z., Zhang S., Hu X., Monitoring sugarcane growth using Envisat ASAR, IEEE Trans. Geoscience and Remote Sensing, 2009, Vol. 47, No. 8, pp. 2572–2579.
  18. Mishra D., Pathak G., Singh B. P. et al., Crop classification by using dual-pol SAR vegetation indices derived from Sentinel 1 SAR-C data, Environmental Monitoring Assessment, 2022, Vol. 195, No. 1, Article 115, DOI: 10.1007/s10661-022-10591-x.
  19. Müller H., Rufin P., Griffiths P. et al., Mining dense Landsat time series for separating cropland and pasture in a heterogeneous Brazilian savanna landscape, Remote Sensing of Environment, 2015, Vol. 156, pp. 490–499, https://doi.org/10.1016/j.rse.2014.10.014.
  20. Plotnikov D. E., Loupian E. A., Kolbudaev P. A. et al., Daily surface reflectance reconstruction using LOWESS on the example of various satellite systems, 8 th Intern. Conf. Information Technology and Nanotechnology (ITNT), 2022, DOI: 10.1109/ITNT55410.2022.9848630.
  21. Roy D. P., Yan L., Robust Landsat-based crop time series modeling, Remote Sensing of Environment, 2018, Vol. 238, Article 110810, https://doi.org/10.1016/j.rse.2018.06.038.
  22. Van Tricht K., Gobin A., Gilliams S., Piccard I., Synergistic use of radar Sentinel 1 and optical Sentinel 2 imagery for crop mapping: a case study for Belgium, Remote Sensing, 2018, V. 10, No. 10, Article 1642, DOI: 10.3390/rs10101642.
  23. Veloso A., Mermoz S., Bouvet A. et al., Understanding the temporal behavior of crops using Sentinel 1 and Sentinel 2-like data for agricultural applications, Remote Sensing of Environment, 2017, Vol. 199, pp. 415–426, https://doi.org/10.1016/j.rse.2017.07.015.
  24. Waldner F., Schucknecht A., Lesiv M. et al., Conflation of expert and crowd reference data to validate global binary thematic maps, Remote Sensing of Environment, 2019, Vol. 221, pp. 235–246, DOI: 10.1016/j.rse.2018.10.039.
  25. Wang Q., Shi W., Li Z., Atkinson P. M., Fusion of Sentinel 2 images, Remote Sensing of Environment, 2016, Vol. 187, pp. 241–252, https://doi.org/10.1016/j.rse.2016.10.030.
  26. Wu M., Zhang X., Huang W. et al., Reconstruction of daily 30 m data from HJ CCD, GF-1 WFV, Landsat, and MODIS data for crop monitoring, Remote Sensing, 2015, Vol. 7, No. 12, pp. 16293–16314, DOI: 10.3390/rs71215826.
  27. Wu M., Wu C., Huang W., Niu Z., Wang C., Li W., Hao P., An improved high spatial and temporal data fusion approach for combining Landsat and MODIS data to generate daily synthetic Landsat imagery, Information Fusion, 2016, Vol. 31, Issue 31, pp. 14–25.
  28. Wu B., Zhang M., Zeng H. et al., Challenges and opportunities in remote sensing-based crop monitoring: A review, National Science Review, 2023, Vol. 10, Issue 4, Article nwac290, DOI: doi.org/10.1093/nsr/nwac290.
  29. Yan L., Roy D. P., Large-area gap fFilling of Landsat reflectance time series by Spectral-Angle-Mapper Based Spatio-Temporal Similarity (SAMSTS), Remote Sensing, 2018, Vol. 10, No. 4, Article 609, DOI: 10.3390/rs10040609.
  30. Zhou T., Pan J., Zhang P. et al., Mapping winter wheat with multi-temporal SAR and optical images in an Urban Agricultural Region, Sensors, 2017, Vol. 17, No. 6, Article 1210, DOI: 10.3390/s17061210.