|
|
Merembayev, T., Yunussov, R., & Yedilkhan, A. (2019). Machine Learning Algorithms for Stratigraphy Classification on Uranium Deposits. Procedia Computer Science, 150, 46–52.
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.
|
|
|
|
Botha, R., Lindsay, R., Newman, R. T., Maleka, P. P., & Chimba, G. (2019). Radon in groundwater baseline study prior to unconventional shale gas development and hydraulic fracturing in the Karoo Basin (South Africa). Applied Radiation and Isotopes, 147, 7–13.
Abstract: The prospect of unconventional shale gas development in the semi-arid Karoo Basin (South Africa) has created the prerequisite to temporally characterise the natural radioactivity in associated groundwater which is solely depended on for drinking and agriculture purposes. Radon (222Rn) was the primary natural radionuclide of interest in this study; however, supplementary radium (226Ra and 228Ra) in-water measurements were also conducted. A total of 53 aquifers spanning three provinces were studied during three separate measurement campaigns from 2014 to 2016. The Karoo Basin’s natural radon-in-water levels can be characterised by a minimum of 1 ± 1 Bq/L (consistent with zero or below LLD), a maximum of 183 ± 18 Bq/L and mean of 41 ± 5 Bq/L. The mean radon-in-water levels for shallow aquifers were systematically higher (55 ± 10 Bq/L) compared to deep (14 ± 3 Bq/L) or mixed aquifers (20 ± 6 Bq/L). Radon-in-water activity concentration fluctuations were predominantly observed from shallow aquifers compared to the generally steady levels of deep aquifers. A collective seasonal mean radon-in-water levels increase from the winter of 2014 (44 ± 8 Bq/L) to winter of 2016 (61 ± 16 Bq/L) was noticed which could be related to the extreme national drought experienced in 2015. Radium-in-water (228Ra and 226Ra) levels ranged from below detection level to a maximum of 0.008 Bq/L (226Ra) and 0.015 Bq/L (228Ra). The 228Ra/226Ra ratio was characterised by a minimum of 0.93, a maximum of 6.5 and a mean value of 3.3 ± 1.3. Developing and improving baseline naturally occurring radionuclide groundwater databases is vital to study potential radiological environmental impacts attributed to industrial processes such as hydraulic fracturing or mining.
|
|
