Journal cover Journal topic
Geoscientific Model Development An interactive open-access journal of the European Geosciences Union
Journal topic

Journal metrics

Journal metrics

  • IF value: 5.154 IF 5.154
  • IF 5-year value: 5.697 IF 5-year
    5.697
  • CiteScore value: 5.56 CiteScore
    5.56
  • SNIP value: 1.761 SNIP 1.761
  • IPP value: 5.30 IPP 5.30
  • SJR value: 3.164 SJR 3.164
  • Scimago H <br class='hide-on-tablet hide-on-mobile'>index value: 59 Scimago H
    index 59
  • h5-index value: 49 h5-index 49
Discussion papers
https://doi.org/10.5194/gmd-2019-128
© Author(s) 2019. This work is distributed under
the Creative Commons Attribution 4.0 License.
https://doi.org/10.5194/gmd-2019-128
© Author(s) 2019. This work is distributed under
the Creative Commons Attribution 4.0 License.

Submitted as: model description paper 25 Jun 2019

Submitted as: model description paper | 25 Jun 2019

Review status
This discussion paper is a preprint. It is a manuscript under review for the journal Geoscientific Model Development (GMD).

DINCAE 1.0: a convolutional neural network with error estimates to reconstruct sea surface temperature satellite observations

Alexander Barth1, Aida Alvera-Azcárate1, Matjaz Licer2, and Jean-Marie Beckers1 Alexander Barth et al.
  • 1GHER, University of Liège, Liège, Belgium
  • 2National Institute of Biology, Marine Biology Station, Piran, Slovenia

Abstract. A method to reconstruct missing data in satellite data using a neural network is presented. Satellite observations working in the optical and infrared bands are affected by clouds, which obscure part of the ocean underneath. In this paper, a neural network with the structure of a convolutional auto-encoder is developed to reconstruct the missing data based on the available cloud-free pixels in satellite images. However, it is unclear how to handle missing data (or data with variable accuracy) in a neural network when using incomplete satellite data in the training phase. The present work shows a consistent approach which uses essentially the satellite data and its expected error variance as input and provides the reconstructed field along with its expected error variance as output. The neural network is trained by maximizing likelihood of the observed value. The approach, called DINCAE (Data-Interpolating Convolutional Auto-Encoder) is applied to a relatively long time-series of Advanced Very High Resolution Radiometer (AVHRR) sea surface temperature data and compared to DINEOF (Data Interpolating Empirical Orthogonal Functions), a method to reconstruct missing data based on an EOF decomposition. The reconstruction error of both approaches is computed using cross-validation and in situ observations from the World Ocean Database. DINCAE results have lower error, while showing higher variability than the DINEOF reconstruction.

Alexander Barth et al.
Interactive discussion
Status: open (until 27 Nov 2019)
Status: open (until 27 Nov 2019)
AC: Author comment | RC: Referee comment | SC: Short comment | EC: Editor comment
[Subscribe to comment alert] Printer-friendly Version - Printer-friendly version Supplement - Supplement
Alexander Barth et al.
Data sets

AVHRR Pathfinder Level 3 Monthly Daytime SST Version 5 NODC and Rosenstiel School of Marine and Atmospheric Science https://doi.org/10.5067/PATHF-MOD50

Model code and software

DINCAE (Data-Interpolating Convolutional Auto-Encoder) A. Barth https://doi.org/10.5281/zenodo.3251813

Alexander Barth et al.
Viewed  
Total article views: 291 (including HTML, PDF, and XML)
HTML PDF XML Total BibTeX EndNote
214 75 2 291 1 4
  • HTML: 214
  • PDF: 75
  • XML: 2
  • Total: 291
  • BibTeX: 1
  • EndNote: 4
Views and downloads (calculated since 25 Jun 2019)
Cumulative views and downloads (calculated since 25 Jun 2019)
Viewed (geographical distribution)  
Total article views: 228 (including HTML, PDF, and XML) Thereof 227 with geography defined and 1 with unknown origin.
Country # Views %
  • 1
1
 
 
 
 
Cited  
Saved  
No saved metrics found.
Discussed  
No discussed metrics found.
Latest update: 21 Oct 2019
Publications Copernicus
Download
Short summary
DINCAE is a method for reconstructing missing data in satellite data using a neural network. Satellite observations working in the optical and infrared bands are affected by clouds, which obscure part of the ocean underneath. In this paper, a neural network with the structure of a convolutional auto-encoder is developed to reconstruct the missing data based on the available cloud-free pixels in satellite images.
DINCAE is a method for reconstructing missing data in satellite data using a neural network....
Citation