Home > Publications database > A Novel ML-Based Methodology for Estimating Water Table Depth Anomalies at the European Continent Scale > print

001     903941
005     20220118142823.0
037 _ _ |a FZJ-2021-05549
100 1 _ |a Ma, Yueling
|0 P:(DE-Juel1)176840
|b 0
|e Corresponding author
|u fzj
111 2 _ |a AGU Fall Meeting 2021
|c New Orleans, LA and online
|d 2021-12-13 - 2021-12-17
|w The US and online
245 _ _ |a A Novel ML-Based Methodology for Estimating Water Table Depth Anomalies at the European Continent Scale
260 _ _ |c 2021
336 7 _ |a Conference Paper
|0 33
|2 EndNote
336 7 _ |a INPROCEEDINGS
|2 BibTeX
336 7 _ |a conferenceObject
|2 DRIVER
336 7 _ |a CONFERENCE_POSTER
|2 ORCID
336 7 _ |a Output Types/Conference Poster
|2 DataCite
336 7 _ |a Poster
|b poster
|m poster
|0 PUB:(DE-HGF)24
|s 1642505765_6598
|2 PUB:(DE-HGF)
|x After Call
520 _ _ |a Effective and efficient groundwater monitoring at the continental scale is still a challenge, mainly due to the scarcity of water table depth (wtd) observations. In this study, we proposed a novel methodology based on advanced machine learning techniques, Long Short-Term Memory (LSTM) networks and transfer learning, for estimating monthly wtd anomalies (wtda) over Europe with monthly precipitation and soil moisture anomalies (pra and θa) as input. In the methodology, the LSTM networks were trained on simulation results and then, without additional training, utilized to estimate wtda based on pra and θa from observational datasets, thereby transferring the simulated input-output relationship to the observation-based estimation. The obtained estimates were evaluated based on in-situ wtd measurements at 2,604 wells distributed over different European regions, achieving R from 0.39 to 0.79 and RMSE from 0.37 to 1.1 for regional averaged values. This constitutes of a >0.10 increase in R and a >0.13 decrease in RMSE compared to the simulation results used for training. In addition, compared with the LSTM networks directly trained on observations, the proposed methodology showed slightly worse test performance at the individual pixel level, lending confidence to applications in areas without wtd observations. The study provides a validated methodology for producing reliable wtda estimates over the European domain in the absence of observations, which can be used for data reconstruction and online groundwater monitoring useful in European groundwater management.
536 _ _ |a 2173 - Agro-biogeosystems: controls, feedbacks and impact (POF4-217)
|0 G:(DE-HGF)POF4-2173
|c POF4-217
|f POF IV
|x 0
536 _ _ |a ERA-PLANET - The European network for observing our changing planet (689443)
|0 G:(EU-Grant)689443
|c 689443
|f H2020-SC5-2015-one-stage
|x 1
700 1 _ |a Montzka, Carsten
|0 P:(DE-Juel1)129506
|b 1
|u fzj
700 1 _ |a Naz, Bibi
|0 P:(DE-Juel1)169794
|b 2
|u fzj
700 1 _ |a Kollet, Stefan
|0 P:(DE-Juel1)151405
|b 3
|u fzj
909 C O |o oai:juser.fz-juelich.de:903941
|p openaire
|p VDB
|p ec_fundedresources
910 1 _ |a Forschungszentrum Jülich
|0 I:(DE-588b)5008462-8
|k FZJ
|b 0
|6 P:(DE-Juel1)176840
910 1 _ |a Forschungszentrum Jülich
|0 I:(DE-588b)5008462-8
|k FZJ
|b 1
|6 P:(DE-Juel1)129506
910 1 _ |a Forschungszentrum Jülich
|0 I:(DE-588b)5008462-8
|k FZJ
|b 2
|6 P:(DE-Juel1)169794
910 1 _ |a Forschungszentrum Jülich
|0 I:(DE-588b)5008462-8
|k FZJ
|b 3
|6 P:(DE-Juel1)151405
913 1 _ |a DE-HGF
|b Forschungsbereich Erde und Umwelt
|l Erde im Wandel – Unsere Zukunft nachhaltig gestalten
|1 G:(DE-HGF)POF4-210
|0 G:(DE-HGF)POF4-217
|3 G:(DE-HGF)POF4
|2 G:(DE-HGF)POF4-200
|4 G:(DE-HGF)POF
|v Für eine nachhaltige Bio-Ökonomie – von Ressourcen zu Produkten
|9 G:(DE-HGF)POF4-2173
|x 0
914 1 _ |y 2021
920 _ _ |l yes
920 1 _ |0 I:(DE-Juel1)IBG-3-20101118
|k IBG-3
|l Agrosphäre
|x 0
980 _ _ |a poster
980 _ _ |a VDB
980 _ _ |a I:(DE-Juel1)IBG-3-20101118
980 _ _ |a UNRESTRICTED

LibraryCollectionCLSMajorCLSMinorLanguageAuthor
Marc 21