|
Records |
Links |
|
Author |
Aderemi, B.A.; Olwal, T.O.; Ndambuki, J.M.; Rwanga, S.S. |
![find record details (via OpenURL) openurl](img/xref.gif)
|
|
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 |
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 ![sorted by Medium field, descending order (down)](img/sort_desc.gif) |
|
|
|
Area |
|
Expedition |
|
Conference |
|
|
|
Notes |
|
Approved |
no |
|
|
Call Number |
THL @ christoph.kuells @ Aderemi2023200049 |
Serial |
219 |
|
Permanent link to this record |
|
|
|
|
Author |
Ollivier, C.C.; Carrière, S.D.; Heath, T.; Olioso, A.; Rabefitia, Z.; Rakoto, H.; Oudin, L.; Satgé, F. |
![find record details (via OpenURL) openurl](img/xref.gif)
|
|
Title |
Ensemble precipitation estimates based on an assessment of 21 gridded precipitation datasets to improve precipitation estimations across Madagascar |
Type |
Journal Article |
|
Year |
2023 |
Publication |
Journal of Hydrology: Regional Studies |
Abbreviated Journal |
|
|
|
Volume |
47 |
Issue |
|
Pages |
101400 |
|
|
Keywords |
Precipitation products, Remote sensing, Ensemble approach, Hydrology, Madagascar |
|
|
Abstract |
Study region this study focuses on Madagascar. This island is characterized by a great diversity of climate, due to trade winds and the varying topography. This country is also undergoing extreme rainfall events such as droughts and cyclones. Study focus the rain gauge network of Madagascar is limited (about 30 stations). Consequently, we consider relevant satellite-based precipitation datasets to fill gaps in ground-based datasets. We assessed the reliability of 21 satellite-based and reanalysis precipitation products (P-datasets) through a direct comparison with 24 rain gauge station measurements at the monthly time step, using four statistical indicators: Kling-Gupta Efficiency (KGE), Correlation Coefficient (CC), Root Mean Square Error (RMSE), and Bias. Based on this first analysis, we produced a merged dataset based on a weighted average of the 21 products. New hydrological insights for the region based on the KGE and the CC scores, WFDEI (WATCH Forcing Data methodology applied to ERA-Interim), CMORPH-BLD (Climate Prediction Center MORPHing satellite-gauge merged) and MSWEP (Multi-Source Weighted Ensemble Precipitation) are the most accurate for estimating rainfall at the national scale. Additionally, the results reveal a high discrepancy between bio-climatic regions. The merged dataset reveals higher performance than the other products in all situations. These results demonstrate the usefulness of a merging approach in an area with a deficit of rainfall data and a climatic and topographic diversity. |
|
|
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 ![sorted by Medium field, descending order (down)](img/sort_desc.gif) |
|
|
|
Area |
|
Expedition |
|
Conference |
|
|
|
Notes |
|
Approved |
no |
|
|
Call Number |
THL @ christoph.kuells @ Ollivier2023101400 |
Serial |
288 |
|
Permanent link to this record |
|
|
|
|
Author |
Zwartendijk, B.W.; Ghimire C. P.; Ravelona M.; Lahitiana J.; van Meerveld H. J. |
![goto web page (via DOI) doi](img/doi.gif)
|
|
Title |
Hydrometric data and stable isotope data for streamflow and rainfall in the Marolaona catchment, Madagascar, 2015-2016 |
Type |
Miscellaneous |
|
Year |
2023 |
Publication |
|
Abbreviated Journal |
|
|
|
Volume |
|
Issue |
|
Pages |
|
|
|
Keywords |
|
|
|
Abstract |
|
|
|
Address |
|
|
|
Corporate Author |
|
Thesis |
|
|
|
Publisher |
NERC EDS Environmental Information Data Centre |
Place of Publication |
|
Editor |
|
|
|
Language |
|
Summary Language |
|
Original Title |
|
|
|
Series Editor |
|
Series Title |
|
Abbreviated Series Title |
|
|
|
Series Volume |
|
Series Issue |
|
Edition |
|
|
|
ISSN |
|
ISBN |
|
Medium ![sorted by Medium field, descending order (down)](img/sort_desc.gif) |
|
|
|
Area |
|
Expedition |
|
Conference |
|
|
|
Notes |
|
Approved |
no |
|
|
Call Number |
THL @ christoph.kuells @ ref10.5285/f93d87ed-7bc4-4d03-9690-3856e6cbbd11 |
Serial |
289 |
|
Permanent link to this record |
|
|
|
|
Author |
Hall, S.M.; Gosen, B.S.V.; Zielinski, R.A. |
![find record details (via OpenURL) openurl](img/xref.gif)
|
|
Title |
Sandstone-hosted uranium deposits of the Colorado Plateau, USA |
Type |
Journal Article |
|
Year |
2023 |
Publication |
Ore Geology Reviews |
Abbreviated Journal |
|
|
|
Volume |
155 |
Issue |
|
Pages |
105353 |
|
|
Keywords |
Colorado, Plateau, Uranium, Vanadium |
|
|
Abstract |
More than 4,000 sandstone-hosted uranium occurrences host over 1.2 billion pounds of mined and in situ U3O8 throughout the Colorado Plateau. Most of the resources are in two distinct mineral systems with deposits hosted in the Triassic Chinle and Jurassic Morrison Formations. In the Chinle mineral system, base metal sulfides typically accompany mineralization. The Morrison mineral system is characterized by V/U ratios up to 20. The uranium source was likely volcanic ash preserved as bentonitic mudstones in the Brushy Basin Member of the Morrison Formation, and lithic volcanic clasts, ash shards, and bentonitic clay in the lower part of the Chinle Formation. Vanadium originated from two possible sources: iron–titanium oxides that are extensively altered in bleached rock near deposits or from similar minerals in variably bleached red beds interbedded with and beneath the Morrison. In Chinle-hosted deposits, in addition to volcanic ash, a contributing source of both vanadium and uranium is proposed here for the first time to be underlying red beds in the Moenkopi and Cutler Formations that have undergone a cycle of reddening-bleaching-reoxidation. Transport in both systems was likely in groundwater through the more permeable sandstones and conglomerate units. The association of uranium minerals with carbonate and more rarely apatite, suggests that transport of uranium was as a carbonate or phosphate complex. The first comprehensive examination of paleoclimate, paleotopography, and subsurface structure of aquifers coupled with analysis of the geochronology of deposits suggests that that there were distinct pulses of uranium mineralization/redistribution during the period from about 259 Ma to 12 Ma when oxidized mineralizing fluids were intermittently rejuvenated in the Plateau in response to changes in tectonic regime and climate. Multiple lines of evidence indicate that deposits formed at ambient temperatures of about 25 °C to no greater than about 140 °C. In both systems, deposits formed where groundwater flow slowed and was subject to evaporative concentration. Stagnant conditions allowed for prolonged interaction of U- and V-enriched groundwater with ferrous iron-bearing reductants, such as illite and iron–titanium oxides, and more rarely organic material such as plant debris. Paragenetically late in the sequence, reducing fluids introduced additional organic matter to some deposits. Reducing fluids and introduced organic matter (now amorphous and altered by radiolysis) may originate from regional petroleum systems where peak oil and gas generation was from ∼ 82 to ∼ 5 Ma. Our novel analysis indicates that these reducing fluids bleached rock and protected affected deposits from remobilization during exposure and weathering that followed uplift of the Plateau (∼80 to 40 Ma). |
|
|
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 |
0169-1368 |
ISBN |
|
Medium ![sorted by Medium field, descending order (down)](img/sort_desc.gif) |
|
|
|
Area |
|
Expedition |
|
Conference |
|
|
|
Notes |
|
Approved |
no |
|
|
Call Number |
THL @ christoph.kuells @ hall_sandstone-hosted_2023 |
Serial |
111 |
|
Permanent link to this record |
|
|
|
|
Author |
Smedley, P.L.; Kinniburgh, D.G. |
![find record details (via OpenURL) openurl](img/xref.gif)
|
|
Title |
Uranium in natural waters and the environment: Distribution, speciation and impact |
Type |
Journal Article |
|
Year |
2023 |
Publication |
Applied Geochemistry |
Abbreviated Journal |
|
|
|
Volume |
148 |
Issue |
|
Pages |
105534 |
|
|
Keywords |
Drinking water, Mine water, NORM, Radionuclide, Redox, U isotopes, Uranium, Uranyl |
|
|
Abstract |
The concentrations of U in natural waters are usually low, being typically less than 4 μg/L in river water, around 3.3 μg/L in open seawater, and usually less than 5 μg/L in groundwater. Higher concentrations can occur in both surface water and groundwater and the range spans some six orders of magnitude, with extremes in the mg/L range. However, such extremes in surface water are rare and linked to localized mineralization or evaporation in alkaline lakes. High concentrations in groundwater, substantially above the WHO provisional guideline value for U in drinking water of 30 μg/L, are associated most strongly with (i) granitic and felsic volcanic aquifers, (ii) continental sandstone aquifers especially in alluvial plains and (iii) areas of U mineralization. High-U groundwater provinces are more common in arid and semi-arid terrains where evaporation is an additional factor involved in concentrating U and other solutes. Examples of granitic and felsic volcanic terrains with documented high U concentrations include several parts of peninsular India, eastern USA, Canada, South Korea, southern Finland, Norway, Switzerland and Burundi. Examples of continental sandstone aquifers include the alluvial plains of the Indo-Gangetic Basin of India and Pakistan, the Central Valley, High Plains, Carson Desert, Española Basin and Edwards-Trinity aquifers of the USA, Datong Basin, China, parts of Iraq and the loess of the Chaco-Pampean Plain, Argentina. Many of these plains host eroded deposits of granitic and felsic volcanic precursors which likely act as primary sources of U. Numerous examples exist of groundwater impacted by U mineralization, often accompanied by mining, including locations in USA, Australia, Brazil, Canada, Portugal, China, Egypt and Germany. These may host high to extreme concentrations of U but are typically of localized extent. The overarching mechanisms of U mobilization in water are now well-established and depend broadly on redox conditions, pH and solute chemistry, which are shaped by the geological conditions outlined above. Uranium is recognized to be mobile in its oxic, U(VI) state, at neutral to alkaline pH (7–9) and is aided by the formation of stable U–CO3(±Ca, Mg) complexes. In such oxic and alkaline conditions, U commonly covaries with other similarly controlled anions and oxyanions such as F, As, V and Mo. Uranium is also mobile at acidic pH (2–4), principally as the uranyl cation UO22+. Mobility in U mineralized areas may therefore occur in neutral to alkaline conditions or in conditions with acid drainage, depending on the local occurrence and capacity for pH buffering by carbonate minerals. In groundwater, mobilization has also been observed in mildly (Mn-) reducing conditions. Uranium is immobile in more strongly (Fe-, SO4-) reducing conditions as it is reduced to U(IV) and is either precipitated as a crystalline or ‘non-crystalline’ form of UO2 or is sorbed to mineral surfaces. A more detailed understanding of U chemistry in the natural environment is challenging because of the large number of complexes formed, the strong binding to oxides and humic substances and their interactions, including ternary oxide-humic-U interactions. Improved quantification of these interactions will require updating of the commonly-used speciation software and databases to include the most recent developments in surface complexation models. Also, given their important role in maintaining low U concentrations in many natural waters, the nature and solubility of the amorphous or non-crystalline forms of UO2 that result from microbial reduction of U(VI) need improved quantification. Even where high-U groundwater exists, percentage exceedances of the WHO guideline value are variable and often small. More rigorous testing programmes to establish usable sources are therefore warranted in such vulnerable aquifers. As drinking-water regulation for U is a relatively recent introduction in many countries (e.g. the European Union), testing is not yet routine or established and data are still relatively limited. Acquisition of more data will establish whether analogous aquifers elsewhere in the world have similar patterns of aqueous U distribution. In the high-U groundwater regions that have been recognized so far, the general absence of evidence for clinical health symptoms is a positive finding and tempers the scale of public health concern, though it also highlights a need for continued investigation. |
|
|
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 |
0883-2927 |
ISBN |
|
Medium ![sorted by Medium field, descending order (down)](img/sort_desc.gif) |
|
|
|
Area |
|
Expedition |
|
Conference |
|
|
|
Notes |
|
Approved |
no |
|
|
Call Number |
THL @ christoph.kuells @ smedley_uranium_2023 |
Serial |
118 |
|
Permanent link to this record |