Feedback

Faculté des Sciences appliquées
Faculté des Sciences appliquées
MASTER THESIS
VIEW 62 | DOWNLOAD 38

Reconstruction of missing data in HF radar observations using the convolutional autoencoder DINCAE

Download
Houyoux, Aimée ULiège
Promotor(s) : Barth, Alexander ULiège
Date of defense : 24-Jun-2021/25-Jun-2021 • Permalink : http://hdl.handle.net/2268.2/11517
Details
Title : Reconstruction of missing data in HF radar observations using the convolutional autoencoder DINCAE
Author : Houyoux, Aimée ULiège
Date of defense  : 24-Jun-2021/25-Jun-2021
Advisor(s) : Barth, Alexander ULiège
Committee's member(s) : Beckers, Jean-Marie ULiège
Capet, Arthur ULiège
Geurts, Pierre ULiège
Language : English
Keywords : [fr] HF radars, Deep Learning, Autoencoder
Discipline(s) : Engineering, computing & technology > Electrical & electronics engineering
Physical, chemical, mathematical & earth Sciences > Multidisciplinary, general & others
Institution(s) : Université de Liège, Liège, Belgique
Degree: Master : ingénieur civil électricien, à finalité spécialisée en "electronic systems and devices"
Faculty: Master thesis of the Faculté des Sciences appliquées

Abstract

[fr] [eng]The goal of this work is to evaluate the possiblility to reconstruct missing surface current datafrom high frequency radars (HFR) with a convolutional neural network. HF radars measure surfacecurrents based on Bragg scattering of electromagnetic waves upon gravity waves on the ocean surface.Perturbation of the process can occur due to interferences or presence of metallic objects in the measuredfield and cause gaps in the collected data.Data-Interpolating Convolutional Autoencoder (DINCAE) is here applied to total currents measure-ments in the Ibiza Channel that are and made freely available by the Balearic Islands Coastal OceanObserving and Forecasting System (SOCIB) since 2012. The structure of the Autoencoder allows thenetwork to be trained on fields with missing data.Both zonal currents (U) and meridional currents (V) are given as inputs to the network are reconstructedalong with the expected standard deviation of the error of reconstruction, following a gaussian curve. Mainpatterns in the data are captured by the encoder part of the network thanks to convolutional filters andpooling and from there, the full fields are reconstructed by the decoder part.During training of the network, a part of the data was set aside to perform cross-validation. Maskswere added to those data to assess the ability of DINCAE to reconstruct the hidden data. Performancesof the reconstruction were computed for different hyperparameter combinations. Presence of drifters inthe area in 2014 further gave the possibility to make a second validation with external data.Since the two validation strategies gave different results from each other, a configuration selected byeach validation was further analysed. It came out that cross-validation selected configuration is presumablytrapped in a local minimum because of a too high lower limit on the expected standard deviation. Infact this is an issue encountered with many tests that were carried out. Drifter selected configuration isthus more reliable and will lead to better generalization, though some time instances are polluted withartefacts, explaining the poor results with cross-validation (performed on a longer time interval).Finally, drifter validation makes comparison with other reconstruction methods possible. DINCAE isfound to make more accurate reconstructions than Open-Boundary Model Analysis (OMA), which is avery commonly used method, but not as good as Data Interpolation Variational Analysis in n-dimensions(DIVAnd).


File(s)

Document(s)

File
Access HOUYOUX_A_tfe.pdf
Description:
Size: 5.33 MB
Format: Adobe PDF
File
Access Erratum_HOUYOUX_A_tfe.pdf
Description: -
Size: 230.25 kB
Format: Adobe PDF

Annexe(s)

File
Access HOUYOUX_a_summary.pdf
Description:
Size: 188.49 kB
Format: Adobe PDF

Author

  • Houyoux, Aimée ULiège Université de Liège > Master ingé. civ. électr., à fin.

Promotor(s)

Committee's member(s)

  • Beckers, Jean-Marie ULiège Université de Liège - ULiège > Département d'astrophys., géophysique et océanographie (AGO) > GeoHydrodynamics and Environment Research (GHER)
    ORBi View his publications on ORBi
  • Capet, Arthur ULiège Université de Liège - ULiège > Département d'astrophys., géophysique et océanographie (AGO) > MAST (Modeling for Aquatic Systems)
    ORBi View his publications on ORBi
  • Geurts, Pierre ULiège Université de Liège - ULiège > Dép. d'électric., électron. et informat. (Inst.Montefiore) > Algorith. des syst. en interaction avec le monde physique
    ORBi View his publications on ORBi
  • Total number of views 62
  • Total number of downloads 38










All documents available on MatheO are protected by copyright and subject to the usual rules for fair use.
The University of Liège does not guarantee the scientific quality of these students' works or the accuracy of all the information they contain.