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: Pyrite is common in roll-front type uranium deposit in Chu-sarysu basin, Kazakhstan. Combined in-situ microstructural, isotopic and chemical analysis of pyrite indicates variation in precipitation conditions and in fluid composition. Broad-scale δ34S heterogeneity indicates a complex multi-facet evolution. First generation authigenic framboïdal aggregates are biogenic as demonstrated by the lowest δ34S values of -48‰ to -28‰. The latest generation pyrites are probably hydrothermal with greater δ34S variation (-30‰ to +12‰). This hydrothermal pyrite commonly displays variable enrichment of several trace elements especially As, Co and Ni. Strong variation in δ34S values and variable trace element enrichment is interpreted in terms of continuous variations in fluid composition.

Abstract: In 2003 examination of aerial photographs revealed a series of previously unknown relict shorelines on the arcuate ridge, possibly a clay lunette dune, that marks the western boundary of Etosha Pan in Namibia. The shorelines are 120–600m wide and the most prominent extend for tens of km around the lunette dune. The shorelines were examined on the ground in 2004 and an attempt was made to date the three lowest levels at ca. 5, 2.5 and 1m above the present pan surface. The OSL ages obtained indicate higher and more prolonged lake conditions than today at ca. 6.4, 4.0 and 2.1ka with the youngest shoreline sediments resting on an ancient pan surface dating to ca. 13ka. The evidence indicates dry conditions in the pan at ca. 13ka, wetter conditions and higher lake levels in the middle Holocene followed by a decline in lake levels to the present. Periods of inundation were of sufficient duration to produce shorelines at the southwestern end of the pan due to the prevailing northeasterly winds that would have maximized wave action along this section of the pan margin. The Etosha findings, together with other regional paleoclimate data, suggest four periods of increased wetness in SW Africa during the Holocene at 7–5, 4.5–3.5, 2.5–1.7 and ca. 1.0ka. There is widespread evidence for the oldest of these periods suggesting that it was a prominent and widespread interval of wetness. Prior to ca. 8.0ka the climate may have been drier than today.

Abstract: Previous research on lacustrine stromatolites from Etosha Pan in Namibia obtained ages on carbonate close to or beyond the limits of radiocarbon dating. These ages suggested that the basin was likely not subject to extensive flooding during the last ca. 40ka. This study shows that AMS radiocarbon ages for the carbonate of a stromatolite from Poacher’s Point are 15–21ka older than ages for organic material in the stromatolite structure. Calibrated ages range from 30 to 40ka for carbonate and 3–19ka for the organic residue. The new ages, together with petrographic and isotopic data for the stromatolite, have provided important new information on past flooding of Etosha Pan including evidence of prolonged lacustrine conditions during the Holocene Climatic Optimum.

Abstract: Paleohydrological data from the African tropics and subtropics, including lake, groundwater and speleothem records, are reviewed to show how environments and climates from both hemispheres are inter-related. Although orbitally induced changes in the monsoon strength account for a large part of long-term climatic changes in tropical Africa, the Late Pleistocene–Holocene hydrological fluctuations rather appear to have been a series of abrupt events that reflect complex interactions between orbital forcing, atmosphere, ocean and land surface conditions. During the Last Glacial Maximum (23–18ka BP), most records indicate that generally dry conditions have prevailed in both hemispheres, associated with lower tropical land- and sea-surface temperatures. This agrees with simulations using coupled ocean–atmosphere models, which predict cooling and reduced summer precipitation in tropical Africa; the global hydrological cycle was weaker than today when the extent of large polar ice-sheets and sea-ice was a prominent forcing factor of the Earth’s climate. Glacial-interglacial climatic changes started early: a first wetting/warming phase at ca. 17–16ka BP took place during a period of rapid temperature increase in Antarctica. Next, two drastic arid-humid transitions in equatorial and northern Africa occurred around 15–14.5ka BP and 11.5–11ka BP. Both are thought to match the major Greenland warming events, in concert with the switching of the oceanic thermohaline circulation to modern mode. However, part of the climatic signal after 15 ka BP also seems related to the Antarctica climate. During the Holocene, Africa has also experienced rapid hydrological fluctuations of dramatic magnitude compared to the climatic changes at high latitudes. In particular, major dry spells occurred around 8.4–8ka and 4.2–4ka BP in the northern monsoon domain. Comparison with other parts of the world indicates that these events have a worldwide distribution but different regional expressions. In the absence of large polar ice sheets, changes in the continental hydrological cycles in the tropics may have a significant impact on the global climate system. Climate information gathered here allows to identify geographical and methodological gaps, and raise some scientific questions that remain to be solved to better understand how the tropics respond to changes in major climate-forcing factors, and how they influence climate globally.