Abstract: Machine learning today becomes more and more effective instrument to solve many particular problems, where there are difficulties to apply well known and described math model. In other words – it is a great tool to describe non-linear phenomena. We tried to use this technique to improve existing process of stratigraphy, and reduce costs on site by applying computer leaded predictions on the basis of existing on-field collected data. Article describes usage of machine learning algorithms for stratigraphy boundaries classification based on geophysics logging data for uranium deposit in Kazakhstan. Correct marking of stratigraphy from geophysics logging data is complex non-linear task. To solve this task we applied several algorithms of machine learning: random forest, logistic regression, gradient boosting, k nearest neighbour and XGBoost.

Abstract: Elevated groundwater nitrate levels are common in drylands, often in excess of WHO guidelines, with concern for human and animal health. In light of recent attempts to identify nitrate sources in the Kalahari this paper presents the first unsaturated zone (USZ) nitrate profiles and recharge rate estimates for the important transboundary Stampriet Basin, alongside the first rainfall chemistry records. Elevated subsurface nitrate reaches 100–250 and 250–525 mg/L NO3–N, with NO3–N/Cl of 4–12, indicating input above evapotranspiration. Chloride mass balance recharge rates range from 4 to 27 mm/y, indicating a vertical movement of these nitrate pulses toward the water table over multi-decadal timescales. These profiles are sampled from dune crests, away from high concentrations of animals and without termite mounds. Given low-density animal grazing is unlikely to contribute consistent spot-scale nitrate over decades, these profiles give an initial estimate of naturally-produced concentrations. This insight is important for the management of the Stampriet Basin and wider Kalahari groundwater. This study expands our knowledge about elevated nitrate in dryland USZs, demonstrating that it can occur as pulses, probably in response to transient vegetation cover and that it is not limited to long-residence time USZs with very limited downward moisture flux (recharge).

Abstract: Elevated groundwater nitrate levels are common in drylands, often in excess of WHO guidelines, with concern for human and animal health. In light of recent attempts to identify nitrate sources in the Kalahari this paper presents the first unsaturated zone (USZ) nitrate profiles and recharge rate estimates for the important transboundary Stampriet Basin, alongside the first rainfall chemistry records. Elevated subsurface nitrate reaches 100–250 and 250–525 mg/L NO3–N, with NO3–N/Cl of 4–12, indicating input above evapotranspiration. Chloride mass balance recharge rates range from 4 to 27 mm/y, indicating a vertical movement of these nitrate pulses toward the water table over multi-decadal timescales. These profiles are sampled from dune crests, away from high concentrations of animals and without termite mounds. Given low-density animal grazing is unlikely to contribute consistent spot-scale nitrate over decades, these profiles give an initial estimate of naturally-produced concentrations. This insight is important for the management of the Stampriet Basin and wider Kalahari groundwater. This study expands our knowledge about elevated nitrate in dryland USZs, demonstrating that it can occur as pulses, probably in response to transient vegetation cover and that it is not limited to long-residence time USZs with very limited downward moisture flux (recharge).

Abstract: The Complexe Terminal (CT) multi-layer aquifer is formed by Neogene/Paleogene sand deposits, Upper Senonian (Campanian-Maastrichtian limestones) and Turonian carbonates. The chemical composition and isotopes of carbon and uranium were investigated in groundwater sampled from the main hydrogeological units of the (CT) aquifer in southern Tunisia. We paid special attention to the variability of uranium contents and isotopes ratio (234U/238U) to provide a better understanding of the evolution of the groundwater system. Uranium concentrations range from 1.5 to 19.5 ppb, typical of oxic or mildly reducing conditions in groundwaters. The lowest concentrations are found southeast of the study area, where active recharge is supposed to take place. When looking at the isotope composition, it appears that all the samples, including those from carbonate levels, are in radioactive disequilibrium with significant 234U excess. A clear-cut distinction is observed between Turonian and Senonian carbonate aquifers on the one hand, with 234U/238U activity ratios between 1.1 and 1.8, and the sandy aquifer on the other hand, showing higher ratios from 1.8 to 3.2. The distribution of uranium in this complex aquifer system seems to be in agreement with the lithological variability and are ultimately a function of a number of physical and chemical factors including the uranium content of the hosting geological formation, water-rock interaction and mixing between waters having different isotopic signatures. Significant relationships also appear when comparing the uranium distribution with the major ions composition. It is noticeable that uranium is better correlated with sulfate, calcium and magnesium than with other major ions as chloride or bicarbonate. The 14C activities and δ13C values of DIC cover a wide range of values, from 1.1 pmc to 30.2 pmc and from −3.6‰ to −10.7‰, respectively. 14C model ages estimated by the Fontes and Garnier model are all younger than 22 Ka and indicate that the recharge of CT groundwater occurred mainly during the end of the last Glacial and throughout the Holocene.