Band Reconstruction Using a Modified UNet for Sentinel-2 Images

• Published in: IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
• Main Authors: Iulia Coca Neagoe, Daniela Faur, Corina Vaduva, Mihai Datcu
• Format: Article in Journal/Newspaper
• Language: English
• Published: IEEE 2023
• Subjects: Band reconstruction; multispectral (MS) images; remote sensing; Sentinel-2 (S2); UNet; Ocean engineering; TC1501-1800; Geophysics. Cosmic physics; QC801-809; North Pole
• Online Access: https://doi.org/10.1109/JSTARS.2023.3276912; https://doaj.org/article/84b89aac42bb47dab3d87fef2a164e35

Multispectral (MS) remote sensing images are of great interest for various applications, yet, quite often, an MS product exhibits one or more noisy bands, strip lines, or even missing bands, which leads to decreased confidence in the information it contains. Meeting this challenge, this article proposes a UNet-based neural network architecture to reconstruct a spectral band. The worst case scenario is considered, that of a missing band, the reconstruction being performed based on the available bands. Besides the comparison with state-of-the-art methods, both the qualitative and quantitative analyses are fulfilled considering several metrics: root-mean-square error, structural similarity index, signal-to-reconstruction error, peak-signal-to-noise ratio, and spectral angle mapper. The experiments focus on Sentinel-2 open data within the Copernicus program. Various patterns of urban areas, agricultural regions, and regions from North Pole or Kyiv, Ukraine are included in our dataset to prove the efficiency of band reconstruction regardless of land-cover diversity.