Permeability is a property of rocks which refers to the ability of fluids to flow through each substance. It depends on several factors as pore shape and diameter. Also the presence and type of clay has a large influence on the permeability value. Permeability can be measured on rock sample in the laboratory by injecting fluid through the rock under known condition, but this provides only point information. Due to the dependence of the parameter on many factors, the deterministic estimation of permeability based on laboratory measurement and well logs is problematic. Many empirical methods for determining permeability are available in the literature and interpretation systems. An interesting approach to the problem is the use of artificial neural networks based on laboratory measurement and modern, high-resolution logging tools. The authors decided to use MLP artificial neural networks, which allow permeability estimation and can be used both in the test well and applied to neighbouring wells. The network was checked in several variants. Obtained results show the legitimacy of using artificial neural networks in the issue of estimating permeability. However, they also show limitations resulting from the lack of accurate data or influence of geological setting and processes.

Estimation and correct determination of vitrinite equivalent reflectance in rock is crucial for the assessment of the source rock in both conventional and unconventional hydrocarbon deposits. These parameters can be determined in laboratories on rock samples. Laboratory measurements provide only point information. However, the use of well logs could overcome discontinuities in the data and provide parameters throughout a study interval. Attention has been paid to the estimation of TOC based on well logs. Vitrinite equivalent reflectance estimation is less well discussed and most papers reported cases with high TOC content in analyzed deposits. In this paper, the estimation of improved R_o is presented using a calculated maturity indicator with well logs. As the organic matter content is not high, additional steps were required for the calculation. To improve the quality of the fit and to find similar intervals, the data were grouped using cluster and neural network analysis. The next step was to use the resistivity log to improve the obtained maturity indicator. Due to the changing properties of kerogen with the type and degree of thermal maturity, this approach turned out to be reliable. The use of resistivity significantly increased the correlation coefficient and reduced errors. The method was tested on two wells with different type and maturity of kerogen. The obtained results are satisfactory, which makes it possible to use the method even in formations with a low organic matter content.

The accurate interpretation of well-logging data is a crucial stage in the exploration of gas- and oil-bearing reservoirs. Geological formations, such as the Miocene deposits, present many challenges related to thin layers, whose thickness is often less than the measurement resolution. This research emphasizes the potential of utilizing electrofacies in such challenging environments. The application of electrofacies not only allows for the grouping of intervals with similar physical characteristics but can also be useful for estimating porosity and permeability parameters. For this purpose, various clustering methods were tested, including the 2D indexed and probabilized self-organizing map (IPSOM) method with and without supervision. Subsequently, the usefulness of the obtained results to improve the estimation of porosity and permeability parameters with the help of artificial neural networks was verified. As a result of the conducted analyses, significantly better results were obtained compared to classical petrophysical interpretation. The calculated porosity and permeability parameters were characterized by much greater variability and alignment with laboratory measurements on porosity and permeability. The best results were obtained for the IPSOM method, but the other methods did not differ significantly. In conclusion, the studies have shown a positive result of applying clustering methods, including the IPSOM method, to improve the estimation of permeability and porosity parameters in complicated, thinly-layered formations.

Thin-bedded Miocene formations of the Carpathian Foredeep represent a major challenge for reliable petrophysical characterization due to strong lithological heterogeneity, high clay minerals content, and the vertical resolution of standard well log interpretations. Accurate assessment of porosity and permeability in such reservoirs is essential for hydrocarbon exploitation, geothermal applications, and the evaluation of Carbon Capture and Storage (CCS) potential.This study presents an integrated pore-structure modeling workflow applied within a multi-well correlation framework, allowing the transfer and validation of petrophysical models across laterally variable, thin-layered deposits. The methodology combines multiscale laboratory measurements (NMR, nitrogen adsorption, MICP, X-ray CT, and FIB-SEM) with machine-learning–assisted interpretation of well log data to generate high-resolution continuous profiles of porosity and permeability. Models calibrated on core-scale laboratory data are propagated between correlated wells, enabling consistent characterization of reservoir properties beyond a single well.To increase the geological credibility of the multi-well interpretation, seismic data are incorporated as an independent constraint. Seismic attributes support stratigraphic correlation, identification of thin-bed architecture, and the lateral continuity of petrophysical units. This integration facilitates the upscaling of pore-scale information from laboratory and well log data into a seismic framework, reducing uncertainty related to heterogeneity and thin layering.The results indicate that the combined use of artificial neural networks, advanced statistical methods, and seismic support significantly improves both vertical and lateral resolution of petrophysical properties in thin-bedded reservoirs. The proposed workflow enables reliable application of pore-network–based models within a multi-well context and provides a scalable approach for reservoir characterization in complex clastic systems. The methodology is particularly relevant for unconventional reservoirs and mature fields considered for CCS or geothermal repurposing, where accurate representation of thin-layered architectures is critical for realistic resource assessment.