Search

Groundwater (GW) is an important natural resource for Europe and the world, and has been affected by extreme weather and climate, e.g., summer heat waves and droughts, and human overexploitation. As climate change and human interventions increase, extreme events and GW depletion are expected to become more frequent and severe in many parts of Europe in the future, aggravating the vulnerability of GW systems. This emphasizes the necessity of GW monitoring in GW management. Up to date, however, it is still challenging to monitor GW at the large, continental scale, mainly due to the lack of water table depth (wtd) observations. In order to address the challenge, the PhD work proposes an indirect, generic methodology based on advanced machine learning (ML) techniques, that are Long Short-Term Memory (LSTM) networks andtransfer learning (TL), to produce reliable monthly wtd anomaly (wtda) estimates at the continental scale. The methodology is named LSTM-TL. While in this work, LSTM-TL has been implemented over Europe, it is transferable to other regions in the world. The methodology relies on the close connection between GW and other atmospheric and terrestrial compartments in the water cycle, using precipitation and soil moisture anomalies (pra and θa) as input, which have data available at large scales from, e.g., remotely sensed observations. Several steps were involved in the development of LSTM-TL for GW monitoring. In the first step, LSTM networks were applied in combination with spatiotemporally continuous pra and wtda data from uncalibrated integrated hydrologic simulation results (named the TSMP-G2A data set) over Europe to capture the time-varying and time-lagged relationship between pra and wtda in order to obtain reliable networks to estimate wtda at the individual pixel level assuming that pra is a useful proxy for wtda. In most European regions, LSTM networks showed good skill with respect to the TSMP-G2A data set inpredicting wtda with pra as input. The results indicated that the local factors, that are yearly averaged wtd, evapotranspiration (ET), soil moisture (θ), and snow water equivalent (SWE), had a significant impact on the performance of the LSTM networks. Moreover, the decrease in the network test performance at some pixels was attributed to a change in the temporal TSMP-G2A pra-wtda pattern during the study period. In the second step, a number of input hydrometeorological variables, in addition to pra, were included in the construction of LSTM networks to arrive at improved wtda estimates at individual pixels over Europe in various experiments. All input and target data were derived from the TSMP-G2A data set. Improved LSTM networks were found with pra and θa as input. Considering θa strongly increased the network testperformance particularly in the areas with wtd ≤ 3 m (i.e., the major wtd category of Europe), suggesting the substantial contribution of θa to the estimation of wtda over Europe. The results highlight the importance to combine θ information with precipitation information in quantifying and predicting wtda.

With the upcoming L‐band Synthetic Aperture Radar (SAR) satellite mission Radar Ob-serving System for Europe L‐band SAR (ROSE‐L) and its integration into existing C‐band satellite missions such as Sentinel‐1, multi‐frequency SAR observations with high temporal and spatial resolution will become available. The SARSense campaign was conducted between June and August 2019 to investigate the potential for estimating soil and plant parameters at the agricultural test site in Selhausen (Germany). It included C‐ and L‐band air‐ and space‐borne observations accompanied by extensive in situ soil and plant sampling as well as unmanned aerial system (UAS) based multi-spectral and thermal infrared measurements. In this regard, we introduce a new publicly available SAR data set and present the first analysis of C‐ and L‐band co‐ and cross‐polarized backscattering signals regarding their sensitivity to soil and plant parameters. Results indicate that a multi‐fre-quency approach is relevant to disentangle soil and plant contributions to the SAR signal and to identify specific scattering mechanisms associated with the characteristics of different crop type, especially for root crops and cereals.

With the upcoming L-band Synthetic Aperture Radar (SAR) satellite mission Radar Ob-serving System for Europe L-band SAR (ROSE-L) and its integration into existing C-band satellite missions such as Sentinel-1, multi-frequency SAR observations with high temporal and spatial resolution will become available. The SARSense campaign was conducted between June and August 2019 to investigate the potential for estimating soil and plant parameters at the agricultural test site in Selhausen (Germany). It included C- and L-band air- and space-borne observations accompanied by extensive in situ soil and plant sampling as well as unmanned aerial system (UAS) based multi-spectral and thermal infrared measurements. In this regard, we introduce a new publicly available SAR data set and present the first analysis of C- and L-band co- and cross-polarized backscattering signals regarding their sensitivity to soil and plant parameters. Results indicate that a multi-fre-quency approach is relevant to disentangle soil and plant contributions to the SAR signal and to identify specific scattering mechanisms associated with the characteristics of different crop type, especially for root crops and cereals.

With the upcoming L-band Synthetic Aperture Radar (SAR) satellite mission Radar Observing System for Europe at L-band (ROSE-L) and its combination with existing C-band satellite missions such as Sentinel-1, multi-frequency SAR observations with high temporal and spatial resolution will become available. To investigate the potential for estimating soil and plant parameters, the SARSense campaign was conducted between June and August 2019 at the agricultural test site Selhausen in Germany. In this regard, we introduce a new publicly available, extensive SAR dataset and present a first analysis of C- and L-band co- and cross-polarized backscattering signals regarding their sensitivity to soil and plant parameters. The analysis includes C- and L-band airborne recordings as well as Senitnel-1 and ALOS-2 acquisitions, accompanied by in-situ soil moisture measurements and plant samplings. In addition, soil moisture was measured using cosmic-ray neutron sensing as well as unmanned aerial system (UAS) based multispectral and temperature measurements were taken during the campaign period. First analysis of the dataset revealed, that due to misalignments of corner reflectors during the SAR acquisition, temporal consistency of airborne SAR data is not given. In this regard, a scene-based, spatial analysis of backscatter behaviour from airborne SAR data was conducted, while the spaceborne SAR data enabled the analysis of temporal changes in backscatter behaviour. Focusing on root crops with radial canopy structure (sugar beet and potato) and cereal crops with elongated canopy structure (wheat, barley), the lowest correlations can be observed between backscattering signal and soil moisture, with R² values ranging below 0.35 at C-band and below 0.36 at L-band. Higher correlations can be observed focusing on vegetation water content, with R² values ranging between 0.12 and 0.64 at C-band and 0.06 and 0.64 at L-band. Regarding plant height, at C-band higher correlations with R² up to 0.55 can be seen compared to R² up to 0.36 at L-band. Looking at the individual agricultural corps in more detail, in almost all cases, the backscatter signals of C- and L-band contain a different amount of information about the soil and plant parameters, indicating that a multi-frequency approach is envisaged to disentangle soil and plant contributions to the signal and to identify specific scattering mechanisms related to the crop type, especially related to the different characteristics of root crops and cereals.

Near real-time groundwater table depth measurements are scarce over Europe, leading to challenges in monitoring groundwater resources at the continental scale. In this study, we leveraged knowledge learned from simulation results by Long Short-Term Memory (LSTM) networks to estimate monthly groundwater table depth anomaly (wtda) data over Europe. The LSTM networks were trained, validated, and tested at individual pixels on anomaly data derived from daily integrated hydrologic simulation results over Europe from 1996 to 2016, with a spatial resolution of 0.11° (Furusho-Percot et al., 2019), to predict monthly wtda based on monthly precipitation anomalies (pra) and soil moisture anomalies (θa). Without additional training, we directly fed the networks with averaged monthly pra and θa data from 1996 to 2016 obtained from commonly available observational datasets and reanalysis products, and compared the network outputs with available borehole in situ measured wtda. The LSTM network estimates show good agreement with the in situ observations, resulting in Pearson correlation coefficients of regional averaged wtda data in seven PRUDENCE regions ranging from 42% to 76%, which are ~ 10% higher than the original simulation results except for the Iberian Peninsula. Our study demonstrates the potential of LSTM networks to transfer knowledge from simulation to reality for the estimation of wtda over Europe. The proposed method can be used to provide spatiotemporally continuous information at large spatial scales in case of sparse ground-based observations, which is common for groundwater table depth measurements. Moreover, the results highlight the advantage of combining physically-based models with machine learning techniques in data processing. Reference: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).

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.