toggle visibility Search & Display Options

Select All    Deselect All
 |   | 
Details
   print
  Records Links
Author Aderemi, B.A.; Olwal, T.O.; Ndambuki, J.M.; Rwanga, S.S. url  openurl
  Title Groundwater levels forecasting using machine learning models: A case study of the groundwater region 10 at Karst Belt, South Africa Type Journal Article
  Year (down) 2023 Publication Systems and Soft Computing Abbreviated Journal  
  Volume 5 Issue Pages 200049  
  Keywords Artificial intelligence, Forecasting model, Groundwater levels, Machine learning, Neural networks, Rainfall, Regression, Temperature, Time series  
  Abstract The crucial role which groundwater resource plays in our environment and the overall well-being of all living things can not be underestimated. Nonetheless, mismanagement of resources, over-exploitation, inadequate supply of surface water and pollution have led to severe drought and an overall drop in groundwater resources’ levels over the past decades. To address this, a groundwater flow model and several mathematical data-driven models have been developed for forecasting groundwater levels. However, there is a problem of unavailability and scarcity of the on-site input data needed by the data-driven models to forecast the groundwater level. Furthermore, as a result of the dynamics and stochastic characteristics of groundwater, there is a need for an appropriate, accurate and reliable forecasting model to solve these challenges. Over the years, the broad application of Machine Learning (ML) and Artificial Intelligence (AI) models are gaining attraction as an alternative solution for forecasting groundwater levels. Against this background, this article provides an overview of forecasting methods for predicting groundwater levels. Also, this article uses ML models such as Regressions Models, Deep Auto-Regressive models, and Nonlinear Autoregressive Neural Networks with External Input (NARX) to forecast groundwater levels using the groundwater region 10 at Karst belt in South Africa as a case study. This was done using Python Mx. Version 1.9.1., and MATLAB R2022a machine learning toolboxes. Moreover, the Coefficient of Determination (R2);, Root Mean Square Error (RMSE), Mutual Information gain, Mean Absolute Percentage Error (MAPE), Mean Squared Error (MSE), Mean Absolute Error (MAE), and the Mean Absolute Scaled Error (MASE)) models were the forecasting statistical performance metrics used to assess the predictive performance of these models. The results obtained showed that NARX and Support Vector Machine (SVM) have higher performance metrics and accuracy compared to other models used in this study.  
  Address  
  Corporate Author Thesis  
  Publisher Place of Publication Editor  
  Language Summary Language Original Title  
  Series Editor Series Title Abbreviated Series Title  
  Series Volume Series Issue Edition  
  ISSN 2772-9419 ISBN Medium  
  Area Expedition Conference  
  Notes Approved no  
  Call Number THL @ christoph.kuells @ Aderemi2023200049 Serial 219  
Permanent link to this record
 

 
Author Rusli, S.R.; Weerts, A.H.; Mustafa, S.M.T.; Irawan, D.E.; Taufiq, A.; Bense, V.F. url  openurl
  Title Quantifying aquifer interaction using numerical groundwater flow model evaluated by environmental water tracer data: Application to the data-scarce area of the Bandung groundwater basin, West Java, Indonesia Type Journal Article
  Year (down) 2023 Publication Journal of Hydrology: Regional Studies Abbreviated Journal  
  Volume 50 Issue Pages 101585  
  Keywords Aquifer interaction, Multi-layer groundwater abstraction, Environmental water tracers, Groundwater flow model, Bandung groundwater basin  
  Abstract Study Region: Bandung groundwater basin, Indonesia. Study focus: Groundwater abstraction of various magnitudes, pumped out from numerous depths in a multitude of layers of aquifers, stimulates different changes in hydraulic head distribution, including ones under vertical cross-sections. This generates groundwater flow in the vertical direction, where groundwater flows within its storage from the shallow to the underlying confined aquifers. In the Bandung groundwater basin, previous studies have identified such processes, but quantitative evaluations have never been conducted, with data scarcity mainly standing as one of the major challenges. In this study, we utilize the collated (1) environmental water tracer data, including major ion elements (Na+/K+, Ca2+, Mg2+, Cl−, SO42−,HCO3−), stable isotope data (2H and δ18O), and groundwater age determination (14C), in conjunction with (2) groundwater flow modeling to quantify the aquifer interaction, driven mainly by the multi-layer groundwater abstraction in the Bandung groundwater basin, and demonstrate their correspondence. In addition, we also use the model to quantify the impact of multi-layer groundwater abstraction on the spatial distribution of the groundwater level changes. New hydrological insights for the region: In response to the limited calibration data availability, we expand the typical model calibration that makes use of the groundwater level observations, with in-situ measurement and a novel qualitative approach using the collated environmental water tracers (EWT) data for the model evaluation. The analysis in the study area using EWT data and quantitative methods of numerical groundwater flow modeling is found to collaborate with each other. Both methods show agreement in their assessment of (1) the groundwater recharge spatial distribution, (2) the regional groundwater flow direction, (3) the groundwater age estimates, and (4) the identification of aquifer interaction. On average, the downwelling to the deeper aquifer is quantified at 0.110 m/year, which stands out as a significant component compared to other groundwater fluxes in the system. We also determine the unconfined aquifer storage volume decrease, calculated from the change in the groundwater table, resulting in an average declining rate of 51 Mm3/year. This number shows that the upper aquifer storage is dwindling at a rate disproportionate to its groundwater abstraction, hugely influenced by losses to the deeper aquifer. The outflow to the deeper aquifer contributes to 60.3% of the total groundwater storage lost, despite representing only 32.3% of the total groundwater abstraction. This study shows the possibility of quantification of aquifer interaction and groundwater level change dynamics driven by multi-layer groundwater abstraction in a multi-layer hydrogeological setting, even in a data-scarce environment. Applying such methods can assist in deriving basin-scale groundwater policies and management strategies under the changing anthropogenic and climatic factors, thereby ensuring sustainable groundwater management.  
  Address  
  Corporate Author Thesis  
  Publisher Place of Publication Editor  
  Language Summary Language Original Title  
  Series Editor Series Title Abbreviated Series Title  
  Series Volume Series Issue Edition  
  ISSN 2214-5818 ISBN Medium  
  Area Expedition Conference  
  Notes Approved no  
  Call Number THL @ christoph.kuells @ Rusli2023101585 Serial 222  
Permanent link to this record
 

 
Author Bresinsky, L.; Kordilla, J.; Hector, T.; Engelhardt, I.; Livshitz, Y.; Sauter, M. url  openurl
  Title Managing climate change impacts on the Western Mountain Aquifer: Implications for Mediterranean karst groundwater resources Type Journal Article
  Year (down) 2023 Publication Journal of Hydrology X Abbreviated Journal  
  Volume 20 Issue Pages 100153  
  Keywords Groundwater recharge, Storage, Hydrogeological droughts, Climate change effects, Groundwater management, Mitigation of climate change effects  
  Abstract Many studies highlight the decrease in precipitation due to climate change in the Mediterranean region, making it a prominent hotspot. This study examines the combined impacts of climate change and three groundwater demand scenarios on the water resources of the Western Mountain Aquifer (WMA) in Israel and the West Bank. While commonly used methods for quantifying groundwater recharge and water resources rely on regression models, it is important to acknowledge their limitations when assessing climate change impacts. Regression models and other data-driven approaches are effective within observed variability but may lack predictive power when extrapolated to conditions beyond historical fluctuations. A comprehensive assessment requires distributed process-based numerical models incorporating a broader range of relevant physical flow processes and, ideally, ensemble model projections. In this study, we simulate the dynamics of dual-domain infiltration and precipitation partitioning using a HydroGeoSphere (HGS) model for variably saturated water flow coupled to a soil-epikarst water balance model in the WMA. The model input includes downscaled high-resolution climate projections until 2070 based on the IPCC RCP4.5 scenario. The results reveal a 5% to 10% decrease in long-term average groundwater recharge compared to a 30% reduction in average precipitation. The heterogeneity of karstic flow and increased intensity of individual rainfall events contribute to this mitigated impact on groundwater recharge, underscoring the importance of spatiotemporally resolved climate models with daily precipitation data. However, despite the moderate decrease in recharge, the study highlights the increasing length and severity of consecutive drought years with low recharge values. It emphasizes the need to adjust current management practices to climate change, as freshwater demand is expected to rise during these periods. Additionally, the study examines the emergence of hydrogeological droughts and their propagation from the surface to the groundwater. The results suggest that the 48-month standardized precipitation index (SPI-48) is a suitable indicator for hydrogeological drought emergence due to reduced groundwater recharge.  
  Address  
  Corporate Author Thesis  
  Publisher Place of Publication Editor  
  Language Summary Language Original Title  
  Series Editor Series Title Abbreviated Series Title  
  Series Volume Series Issue Edition  
  ISSN 2589-9155 ISBN Medium  
  Area Expedition Conference  
  Notes Approved no  
  Call Number THL @ christoph.kuells @ Bresinsky2023100153 Serial 223  
Permanent link to this record
 

 
Author Arya, S.; Kumar, A. url  openurl
  Title Evaluation of stormwater management approaches and challenges in urban flood control Type Journal Article
  Year (down) 2023 Publication Urban Climate Abbreviated Journal  
  Volume 51 Issue Pages 101643  
  Keywords Flood risk, Green infrastructure (GI), Stormwater management, Stormwater modelling, Vulnerability assessment, Urban floods  
  Abstract Across the globe, the damage caused by urban floods has increased manifold. The unchecked development has encroached the natural drainage, and the conventional drainage systems are inadequate in handling the augmented hydrological response. To counter this, a variety of approaches with the ability to adjust within the constraints of complex environments by managing surface runoff are being widely investigated and applied worldwide. These can put the flood water to better use, and the ecological balance may get restored. This review discusses recent progress made in the area of Green Infrastructure (GI), modelling tools that help in stormwater management, vulnerability analysis and flood risk assessment. Different ways of handling the problem are summarized through an extensive literature survey. The gaps and barriers that impede the implementation of stormwater management solutions and strategies for further improvement have also been presented. A case study of Gurugram city, India depicting the challenges being faced by urban flooding and the possible solutions through an expert survey is also presented.  
  Address  
  Corporate Author Thesis  
  Publisher Place of Publication Editor  
  Language Summary Language Original Title  
  Series Editor Series Title Abbreviated Series Title  
  Series Volume Series Issue Edition  
  ISSN 2212-0955 ISBN Medium  
  Area Expedition Conference  
  Notes Approved no  
  Call Number THL @ christoph.kuells @ Arya2023101643 Serial 224  
Permanent link to this record
 

 
Author Mekuria, W.; Tegegne, D. url  isbn
openurl 
  Title Water harvesting Type Book Chapter
  Year (down) 2023 Publication Encyclopedia of Soils in the Environment (Second Edition) Abbreviated Journal  
  Volume Issue Pages 593-607  
  Keywords Climate change, Ecosystem services, Environmental benefits, Population growth, Resilient community, Resilient environment, Socio-economic benefits, Urbanizations, Water harvesting, Water quality, Water security  
  Abstract Water harvesting is the intentional collection and concentration of rainwater and runoff to offset irrigation demands. Secondary benefits include decreased flood and erosion risk. Water harvesting techniques include micro- and macro-catchment systems, floodwater harvesting, and rooftop and groundwater harvesting. The techniques vary with catchment type and size, and the method of water storage. Micro-catchment water harvesting, for example, requires the development of small structures and targets increased water delivery and storage to the root zone whereas macro-catchment systems collect runoff water from large areas. The sustainability of water harvesting techniques at the local level are usually constrained by several factors such as labor, construction costs, loss of productive land, and maintenance, suggesting that multiple solutions are required to sustain the benefits of water harvesting techniques.  
  Address  
  Corporate Author Thesis  
  Publisher Academic Press Place of Publication Oxford Editor Goss, M.J.; Oliver, M.  
  Language Summary Language Original Title  
  Series Editor Series Title Abbreviated Series Title  
  Series Volume Series Issue Edition  
  ISSN ISBN 978-0-323-95133-3 Medium  
  Area Expedition Conference  
  Notes Approved no  
  Call Number THL @ christoph.kuells @ Mekuria2023593 Serial 225  
Permanent link to this record
Select All    Deselect All
 |   | 
Details
   print

Save Citations:
Export Records: