Search

Water quality monitoring is essential for managing water resources and ensuring human and environmental health. However, obtaining reliable data can be challenging and costly, especially in complex systems such as estuaries. To address this problem, we propose a novel deep learning-based approach that uses limited available data to accurately estimate and reconstruct critical water quality variables, such as electrical conductivity, dissolved oxygen, and turbidity. Our approach included two tasks, numerical modeling and historical reconstruction, and was applied to the Seine River in the Normandy region of France at four quality stations. In the first task, we evaluated four deep learning approaches (GRU, BiLSTM, BiLSTM-Attention, and CNN-BiLSTM-Attention) to numerically simulate each variable for each station under different input data selection scenarios. We found that incorporating the quality data with the water level data collected at the various stations into the input data improved the accuracy of the water quality data simulation. Combining water levels from multiple stations reliably reproduced electrical conductivity, especially at stations near the sea where tidal fluctuations control saltwater intrusion in the area. While each model had its strengths, the CNN-BiLSTM-Attention model performed best in complex tasks with dissimilar input trends, and the GRU model outperformed other models in simple monitoring tasks with similar input-target trends. The second task involved automatically searching the optimal configurations for completing the missing historical data in sequential order using the modeling task results. The electrical conductivity data were filled before the dissolved oxygen data, which were in turn more reliable than the turbidity simulation. The deep learning models accurately reconstructed 15 years of water quality data using only six and a half years of modeling data. Overall, this research demonstrates the potential of deep learning approaches with their limitations and discusses the best configurations to improve water quality monitoring and reconstruction. [ABSTRACT FROM AUTHOR]

Copyright of Hydrogeology Journal is the property of Springer Nature and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Hydrogeology Journal is the property of Springer Nature and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

The study on the hydraulic properties of coastal aquifers has significant implications both in hydrological sciences and environmental engineering. Although many analytical solutions are available, most of them are based on the same basic assumption that assumes aquifers extend landward semi‐infinitely, which does not necessarily reflect the reality. In this study, the general solutions for a leaky confined coastal aquifer have been developed that consider both finitely landward constant‐head and no‐flow boundaries. The newly developed solutions were then used to examine theoretically the joint effects of leakage and aquifer length on hydraulic head fluctuations within the leaky confined aquifer, and the validity of using the simplified solution, which assumes the aquifer is semi‐infinite. The results illustrated that the use of the simplified solution may cause significant errors, depending on joint effects of leakage and aquifer length. A dimensionless characteristic parameter was then proposed as an index for judging the applicability of the simplified solution. In addition, practical application of the general solution for the constant‐head inland boundary was used to characterize the hydraulic properties of a leaky confined aquifer using the data collected from a field site at the Seine River estuary, France, and the versatility of the general solution was further justified. [ABSTRACT FROM AUTHOR]

Hydraulic tomography permits to map the subsurface properties from the information provided by punctual responses measured during a field investigation. In the case of karst fields, hydraulic tomography applications face problematics due to the existence of networks of fractures and conduits in such systems: constrained flows and high contrast in the distribution of the property values. It is then necessary to generate field data able to provide information on these constrained flows and their localization. It is also necessary to set up an inverse problem able the generate distributions of property values that can image the networks of fractures and conduits in the matrix rock.We have compared the information brought by responses to different pumping signals (constant or oscillatory) to characterize the flows in karst fields. We have also developed and studied different inverse problems to represent contrasted property values distributions with different modeling methods (equivalent porous media or discrete fractures network). Finally, our aim was to apply and test different hydraulic tomography on a same, well equipped, karst field (Terrieu experimental field, studied by the French observatory SNO Karst).We have associated different sets of measured field data with our different inversion algorithms to compare the imagery results generated by each association data/inversion. Globally, while the different inversion methods we tested all provide interesting results, it appears that oscillatory pumping signals are more efficient than constant signals to characterize the path generated by the constrained flows. In fact the information provided by responses to oscillatory signals at various frequencies are more specific and permit a fast resolution of the inversion by solving the problem in a frequency domain. [ABSTRACT FROM AUTHOR]