000875351 001__ 875351
000875351 005__ 20201230100817.0
000875351 0247_ $$2doi$$a10.5194/egusphere-egu2020-5367
000875351 0247_ $$2Handle$$a2128/26591
000875351 037__ $$aFZJ-2020-01969
000875351 041__ $$aEnglish
000875351 1001_ $$0P:(DE-Juel1)176840$$aMa, Yueling$$b0$$eCorresponding author
000875351 1112_ $$aEGU General Assembly 2020$$cOnline$$d2020-05-04 - 2020-05-08$$wOnline
000875351 245__ $$aModeling of groundwater table depth anomalies using Long Short-Term Memory networks over Europe
000875351 260__ $$c2020
000875351 3367_ $$033$$2EndNote$$aConference Paper
000875351 3367_ $$2DataCite$$aOther
000875351 3367_ $$2BibTeX$$aINPROCEEDINGS
000875351 3367_ $$2DRIVER$$aconferenceObject
000875351 3367_ $$2ORCID$$aLECTURE_SPEECH
000875351 3367_ $$0PUB:(DE-HGF)6$$2PUB:(DE-HGF)$$aConference Presentation$$bconf$$mconf$$s1608479487_7423$$xAfter Call
000875351 520__ $$a<p>Groundwater is the dominant source of fresh water in many European countries. However, due to a lack of near-real-time water table depth (wtd) observations, monitoring of groundwater resources is not feasible at the continental scale. Thus, an alternative approach is required to produce wtd data from other available observations near-real-time. In this study, we propose Long Short-Term Memory (LSTM) networks to model monthly wtd anomalies over Europe utilizing monthly precipitation anomalies as input. LSTM networks are a special type of artificial neural networks, showing great promise in exploiting long-term dependencies between time series, which is expected in the response of groundwater to precipitation. To establish the methodology, spatially and temporally continuous data from terrestrial simulations at the continental scale were applied with a spatial resolution of 0.11&#176;, ranging from the year 1996 to 2016 (Furusho-Percot et al., 2019). They were divided into a training set (1996 &#8211; 2012), a validation set (2012 &#8211; 2014) and a testing set (2015 -2016) to construct local models on selected pixels over eight PRUDENCE regions. The outputs of the LSTM networks showed good agreement with the simulation results in locations with a shallow wtd (~3m). It is important to note, the quality of the models was strongly affected by the amount of snow cover. Moreover, with the introduction of monthly evapotranspiration anomalies as additional input, pronounced improvements of the network performances were only obtained in more arid regions (i.e., Iberian Peninsula and Mediterranean). Our results demonstrate the potential of LSTM networks to produce high-quality wtd anomalies from hydrometeorological variables that are monitored at the large scale and part of operational forecasting systems potentially facilitating the implementation of an efficient groundwater monitoring system over Europe.</p><p>Reference:</p><p>Furusho-Percot, C., Goergen, K., Hartick, C., Kulkarni, K., Keune, J. and Kollet, S. (2019). Pan-European groundwater to atmosphere terrestrial systems climatology from a physically consistent simulation. Scientific Data, 6(1).</p>
000875351 536__ $$0G:(DE-HGF)POF3-255$$a255 - Terrestrial Systems: From Observation to Prediction (POF3-255)$$cPOF3-255$$fPOF III$$x0
000875351 536__ $$0G:(EU-Grant)689443$$aERA-PLANET - The European network for observing our changing planet (689443)$$c689443$$fH2020-SC5-2015-one-stage$$x1
000875351 588__ $$aDataset connected to CrossRef
000875351 7001_ $$0P:(DE-Juel1)129506$$aMontzka, Carsten$$b1
000875351 7001_ $$0P:(DE-Juel1)177038$$aBayat, Bagher$$b2
000875351 7001_ $$0P:(DE-Juel1)151405$$aKollet, Stefan$$b3$$ufzj
000875351 773__ $$a10.5194/egusphere-egu2020-5367
000875351 8564_ $$uhttps://meetingorganizer.copernicus.org/EGU2020/EGU2020-5367.html
000875351 8564_ $$uhttps://juser.fz-juelich.de/record/875351/files/MODELING%20OF%20GROUNDWATER%20TABLE%20DEPTH%20ANOMALIES%20USING%20LONG%20SHORT-TERM%20MEMORY%20NETWORKS%20OVER%20EUROPE.pdf$$yOpenAccess
000875351 8564_ $$uhttps://juser.fz-juelich.de/record/875351/files/MODELING%20OF%20GROUNDWATER%20TABLE%20DEPTH%20ANOMALIES%20USING%20LONG%20SHORT-TERM%20MEMORY%20NETWORKS%20OVER%20EUROPE.pdf?subformat=pdfa$$xpdfa$$yOpenAccess
000875351 909CO $$ooai:juser.fz-juelich.de:875351$$popenaire$$popen_access$$pVDB$$pdriver$$pec_fundedresources
000875351 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)176840$$aForschungszentrum Jülich$$b0$$kFZJ
000875351 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)129506$$aForschungszentrum Jülich$$b1$$kFZJ
000875351 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)177038$$aForschungszentrum Jülich$$b2$$kFZJ
000875351 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)151405$$aForschungszentrum Jülich$$b3$$kFZJ
000875351 9131_ $$0G:(DE-HGF)POF3-255$$1G:(DE-HGF)POF3-250$$2G:(DE-HGF)POF3-200$$3G:(DE-HGF)POF3$$4G:(DE-HGF)POF$$aDE-HGF$$bErde und Umwelt$$lTerrestrische Umwelt$$vTerrestrial Systems: From Observation to Prediction$$x0
000875351 9141_ $$y2020
000875351 915__ $$0StatID:(DE-HGF)0510$$2StatID$$aOpenAccess
000875351 920__ $$lyes
000875351 9201_ $$0I:(DE-Juel1)IBG-3-20101118$$kIBG-3$$lAgrosphäre$$x0
000875351 980__ $$aconf
000875351 980__ $$aVDB
000875351 980__ $$aUNRESTRICTED
000875351 980__ $$aI:(DE-Juel1)IBG-3-20101118
000875351 9801_ $$aFullTexts