Slide 1

Production, visualization and analysis of large volumes of remote sensing images modeled as multidimensional data cubes for the entire Brazilian territory.

Deep Learning as a tool to interpolate cloudy pixels in Sentinel-2 time series

by Baggio Luiz de Castro e Silva 1 Wesley Augusto Campanharo 1 Felipe Souza 1 Karine Ferreira 1 Gilberto Ribeiro de Queiroz 1

¹ Instituto Nacional de Pesquisas Espaciais, Avenida dos Astronautas, 1758, Jardim da Granja, Sao Jose dos Campos, SP 12227-010, Brasil

Anais / Proceedings XX SBSR – Vol 20, 2023. – 156382:

Publisher: SBSR | Published: April 5, 2023


Optical remote sensors are extremely susceptible to clouds. Clouds and their shadows affect remote sensing image processing methods to automatically identify and classify land use and land cover types. To detect cloud and cloud shadows in remote sensing images, many algorithms have been proposed, such as FMask, Sen2Cor and s2cloudless. In image time series analysis, interpolation techniques are used to produce valid values when pixels are covered by clouds or shadows. This paper evaluates the use of deep learning approaches to interpolate cloudy pixels in Sentinel-2 time series. Twelve different model configurations were evaluated and their differences and limitations were highlighted. The model proved to be very promising in dealing with the limitations of the cloud mask interpolating clouds and cloud shadows.  View Full-Text

Keywords: Cloud interpolation, Satellite image time series, Cloud and shadows, Neural network, Multilayer perceptrons.

© This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited

Share and Cite

Baggio Luiz de Castro e Silva et al. DEEP LEARNING AS A TOOL TO INTERPOLATE CLOUDY PIXELS IN SENTINEL-2 TIME SERIES. In: ANAIS DO XX SIMPóSIO BRASILEIRO DE SENSORIAMENTO REMOTO, 2023, Florianópolis. Anais eletrônicos… São José dos Campos, INPE, 2023. ISBN: 978-65-89159-04-9, Vol 20, 2023. – 156382.

Brazil Data Cube - 2019 - 2024