Preprints
https://doi.org/10.5194/npg-2020-32
https://doi.org/10.5194/npg-2020-32

  24 Aug 2020

24 Aug 2020

Review status: this preprint was under review for the journal NPG but the revision was not accepted.

Hybrid Neural Network – Variational Data Assimilation algorithm to infer river discharges from SWOT-like data

Kevin Larnier1,2,3 and Jerome Monnier1,2 Kevin Larnier and Jerome Monnier
  • 1Institut de Mathématiques de Toulouse (IMT), France
  • 2INSA Toulouse, France
  • 3CS corporation, Business Unit Espace, Toulouse, France

Abstract. A new algorithm to estimate river discharges from altimetry measurements only is designed. A first estimation is obtained by an artificial neural network trained from the altimetry large scale water surface measurements plus drainage area information. The combination of this purely data-based estimation and a dedicated algebraic flow model provides a first physically-consistent estimation. The latter is next employed as the first guess of an advanced variational data assimilation formulation. The final estimation is highly accurate for rivers presenting features within the learning partition; for rivers far outside the learning partition, the space-time variations of discharge remain accurately approximated however the global estimation presents a potential bias. Indeed, it is shown that if the estimation is based on the hydrodynamics models only, the inverse problem may be well-defined but up to a bias only (the bias scales the global estimation). This bias is removed thanks to the ANN but for rivers in the learning partition only. For rivers outside the learning partition, any mean value (eg. annual, seasonal) enables to remove the bias. Finally, the present hybrid and hierarchical inversion strategy seems to provide much more accurate estimations compared to the state-of-the-art for the considered 29 heterogeneous river portions.

Kevin Larnier and Jerome Monnier

 
Status: closed
Status: closed
AC: Author comment | RC: Referee comment | SC: Short comment | EC: Editor comment
Printer-friendly Version - Printer-friendly version Supplement - Supplement
 
Status: closed
Status: closed
AC: Author comment | RC: Referee comment | SC: Short comment | EC: Editor comment
Printer-friendly Version - Printer-friendly version Supplement - Supplement

Kevin Larnier and Jerome Monnier

Kevin Larnier and Jerome Monnier

Viewed

Total article views: 711 (including HTML, PDF, and XML)
HTML PDF XML Total BibTeX EndNote
636 71 4 711 17 14
  • HTML: 636
  • PDF: 71
  • XML: 4
  • Total: 711
  • BibTeX: 17
  • EndNote: 14
Views and downloads (calculated since 24 Aug 2020)
Cumulative views and downloads (calculated since 24 Aug 2020)

Viewed (geographical distribution)

Total article views: 587 (including HTML, PDF, and XML) Thereof 586 with geography defined and 1 with unknown origin.
Country # Views %
  • 1
1
 
 
 
 

Cited

Latest update: 21 Sep 2021
Download
Short summary
A hybrid A.I. algorithm (data-driven and physically-informed) to estimate river discharges observed by the altimetry satellite SWOT (launch 2021).