The current study is devoted to the determination and interpretation of geochemical trends reflecting hydrocarbon generation, migration and accumulation in unconventional reservoirs; the study is performed on the Bazhenov shale rock formation (Western Siberia, Russia). Results are based on more than 3000 Rock-Eval analyses of the samples from 34 wells drilled in the central part of the West Siberian petroleum basin, which is characterized by common marine sedimentation environments. Pyrolysis studies were carried out before and after the extraction of rocks by organic solvent. As a result, we have improved the accuracy of kerogen content and maturity determination and complemented the standard set of pyrolysis parameters with the content of heavy fraction of hydrocarbons. The data obtained for the wells from areas of different organic matter maturity was summarized in the form of cross-plots and diagrams reflecting geochemical evolution of the source rocks from the beginning to the end of the oil window. Interpretation of the obtained results revealed quantitative trends in the changes of generation potential, amount, and composition of generated hydrocarbons in rocks at different stages of oil generation process. The analysis of geochemical trends allowed us to improve approaches for the productivity evaluation of the formation and study the effect of organic matter maturity on distribution of productive intervals of different types.

The paper reports comprehensive analysis of different factors affecting uranium content in oil source rocks and the relationship between uranium content and productivity of source rocks. The analysis of data for 13 wells of the Bazhenov Formation (Western Siberia, Russia) was carried out. The uranium content of the rocks was measured by gamma-ray spectrometry on core samples. In order to analyze factors affecting uranium accumulation in source rocks, we studied content and characteristics of organic matter (Rock-Eval pyrolysis), and also mineral, element, and isotope composition of rocks. We have shown that redox conditions at the sedimentation stage have the most pronounced impact on the uranium accumulation in the rocks of the Bazhenov Formation. It was also shown that productive intervals, containing increased amounts of mobile hydrocarbons, are characterized by low (<20 ppm) concentration of uranium. However, the intervals, containing phosphorite minerals may show better reservoir properties and oil saturation at higher concentration of uranium. The analysis of correlations and relationships between uranium content and Rock-Eval pyrolysis indexes (oil saturation index and productivity index) enabled formulation of criteria for selection of oil-saturated intervals using the spectral gamma and pulsed neutron spectroscopy log data.

The increasing urbanization has intensified air pollution exposure, seriously threatening public health. This study examines how various machine learning and deep learning models can enhance the optimization of traffic changes within an urban planning framework, with a particular emphasis on air quality. Using local pollutant data from stations located in Novi Sad (Serbia), the models estimate emission changes from major transport infrastructure modifications. Two complementary approaches are used: (1) multi-output regression aimed at predicting air pollutant concentrations, and (2) multi-output classification focused on predicting the air quality index (AQI). For daily predictions, the Long Short-Term Memory (LSTM) model achieved the best R² = 0.5, while the Balanced Random Forest classifier reached 0.775 balanced accuracy for AQI classification. Finally, the most accurate models were applied to two prospective city network scenarios projected - (1) construction of two river bridges rerouting heavy traffic, and (2) creation of an extended pedestrian zone downtown - to quantify the expected reduction in pollutant concentrations and estimate possible changes in AQI categories. Depending on the pollutant, the results indicate a relative daily decrease between \(0.7\%\) and \(2.9\%\) on average for both scenarios. Although the improvement might seem small, this reduction is obtained for 13 street segments within a 100-meter radius around air stations, and a potential reduction for the whole city could be more substantial. Additionally, to turn forecasts into policy-ready evidence for traffic system decisions, we paired predictive models with explainable artificial intelligence (XAI) methods. Applying XAI methods reveals that meteorological factors, including relative humidity, total precipitation, temperature, and wind speed, primarily account for the predictions of developed models. Overall, the XAI methods highlight the combined influence of temporal, spatial, and meteorological factors on AQI.