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-2019-156
© Author(s) 2019. This work is distributed under
the Creative Commons Attribution 4.0 License.
https://doi.org/10.5194/gmd-2019-156
© Author(s) 2019. This work is distributed under
the Creative Commons Attribution 4.0 License.

Submitted as: model description paper 30 Aug 2019

Submitted as: model description paper | 30 Aug 2019

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

Efficient multi-scale Gaussian process regression for massive remote sensing data with satGP v0.1

Jouni Susiluoto1,2,3, Alessio Spantini1, Heikki Haario2,3, and Youssef Marzouk1 Jouni Susiluoto et al.
  • 1Massachusetts Institute of Technology, Department of Aeronautics and Astronautics, 77 Massachusetts Avenue, 33-207, Cambridge MA 02139, USA
  • 2Lappeenranta University of Technology, School of Engineering Science, P.O. Box 20, 53851 Lappeenranta, Finland
  • 3Finnish Meteorological Institute, Erik Palménin aukio 1, 00560 Helsinki, Finland

Abstract. Satellite remote sensing provides a global view to processes on Earth that has unique benefits compared to measurements made on the ground. The global coverage and the enormous amounts of data produced come, however, with the price of spatial and temporal gaps and less than perfect data quality. Meaningful statistical inference from such data requires overcoming these problems and that calls for developing efficient computational tools.

We design and implement a computationally efficient multi-scale Gaussian process (GP) software package, satGP, geared towards remote sensing applications. The software is designed to be able to handle problems of enormous sizes and is able to compute marginals and sample from a random process with at least over hundred million observations.

The mean function of the Gaussian process is described by approximating marginals of a Markov random field (MRF). For covariance functions, Matern, exponential, and periodic kernels are utilized in a multi-scale kernel setting to describe the spatial heterogeneity present in data. We further demonstrate how winds can be used to inform the covariance kernel formulation. The covariance kernel parameters are learned by calculating an approximate marginal maximum likelihood estimate and this is utilized to verify the validity of the multi-scale approach in synthetic experiments.

For demonstrating the techniques above, data from the Orbiting Carbon Observatory 2 (OCO-2) satellite is used. The satGP program is released as open source software.

Jouni Susiluoto et al.
Interactive discussion
Status: final response (author comments only)
Status: final response (author comments only)
AC: Author comment | RC: Referee comment | SC: Short comment | EC: Editor comment
[Login for Authors/Topical Editors] [Subscribe to comment alert] Printer-friendly Version - Printer-friendly version Supplement - Supplement
Jouni Susiluoto et al.
Jouni Susiluoto et al.
Viewed  
Total article views: 278 (including HTML, PDF, and XML)
HTML PDF XML Total BibTeX EndNote
183 91 4 278 7 5
  • HTML: 183
  • PDF: 91
  • XML: 4
  • Total: 278
  • BibTeX: 7
  • EndNote: 5
Views and downloads (calculated since 30 Aug 2019)
Cumulative views and downloads (calculated since 30 Aug 2019)
Viewed (geographical distribution)  
Total article views: 192 (including HTML, PDF, and XML) Thereof 190 with geography defined and 2 with unknown origin.
Country # Views %
  • 1
1
 
 
 
 
Cited  
Saved  
No saved metrics found.
Discussed  
No discussed metrics found.
Latest update: 15 Nov 2019
Publications Copernicus
Download
Short summary
We describe a new computer program that is able produce maps and videos of carbon dioxide or other quantities based on data collected by satellites that orbit the Earth. When working with such data there is often too much data in one area and none in another. The program is able to describe the fields even when data is not available. To be able to do so, new computational methods were developed. The program is also able to describe how uncertain the estimated carbon dioxide or other fields are.
We describe a new computer program that is able produce maps and videos of carbon dioxide or...
Citation