The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
Download
Publications Copernicus
Download
Citation
Articles | Volume XLIII-B1-2022
Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XLIII-B1-2022, 73–78, 2022
https://doi.org/10.5194/isprs-archives-XLIII-B1-2022-73-2022
Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XLIII-B1-2022, 73–78, 2022
https://doi.org/10.5194/isprs-archives-XLIII-B1-2022-73-2022
 
30 May 2022
30 May 2022

DEEP LEARNING-BASED METHOD TO EXTEND THE TIME SERIES OF GLOBAL ANNUAL VIIRS-LIKE NIGHTTIME LIGHT DATA

L. Wang1,2, W. Tan1, H. Xu1, H. He1, N. Chen1,3, D. Li4, M. A. Chapman5, and J. Li1,6 L. Wang et al.
  • 1Dept. of Geography and Environmental Management, University of Waterloo, Waterloo, ON N2L 3G1, Canada
  • 221AT North America R&D Ltd., Markham, ON, L3R 9T8, Canada
  • 3College of Geological Engineering and Geomatics, Chang’an University, Xi’an SX 710054, China
  • 4College of Computer Science and Technology, Huaqiao University, Xiamen, FJ 361021, China
  • 5Dept. of Civil Engineering, Ryerson University, Toronto, ON M5B 2K3, Canada
  • 6Dept. of Systems Design Engineering, University of Waterloo, Waterloo, ON N2L 3G1, Canada

Keywords: Super Resolution, VIIRS, DMSP, Deep Learning, Downscaling, Radiance Calibration, Data Fusion

Abstract. The nighttime light (NTL) remote sensed imagery has been applied in monitoring human activities from many perspectives. As the two most widely used NTL satellites, the Defense Meteorological Satellite Program (DMSP) Operational Linescan System and the Suomi National Polar-orbiting Partnership (NPP)-Visible Infrared Imaging Radiometer Suite (VIIRS) have different spatial and radiometric resolutions. Thus, some long-time series analysis cannot be conducted without effective and accurate cross-calibration of these two datasets. In this study, we proposed a deep-learning based model to simulate VIIRS-liked DMSP NTL data by integrating the enhanced vegetation index (EVI) data product from MODIS. By evaluating the spatial pattern of the results, the modified Self-Supervised Sparse-to-Dense networks delivered satisfying results of spatial resolution downscaling. The quantitative analysing of the simulated VIIRS-liked DMSP NTL with original VIIRS NTL showed a good consistency at the pixel level of four selected sub datasets with R2 ranging from 0.64 to 0.76, and RMSE ranging from 3.96-9.55. Our method presents that the deep learning model can learn from relatively raw data instead of fine processed data based on expert knowledge to cross-sensor calibration and simulation NTL data.