The Moesian platform has been extensively studied both from the tectonic point of view and from the perspective of its sedimentary bed which is rich in hydrocarbon resources. Extensive research has shown that the Moesian platform consists of Paleozoic sedimentary formations having their accouchement in four cycles, which according to in the Ordovician, Silurian, lower Devonian (dark and leaden argillites), upper Devonian (bituminous dolomites with pyritization) and mid-Triassic (muschelkalk) period, the oil and gas genesis took place. Moreover, such resources have been traced in rocks of all ages, including in the ones from the fourth sedimentation cycle. The present paper offers insight into the lithology and petrographical features of the Sarmatian stage since there is a lack of detailed petrographic published data regarding this topic. The study highlights the lithology, offering detailed petrographical features for the Sarmatian on a petroliferous structure located in the eastern part of the platform. Fossil and palynological correlations have been employed by numerous authors, resulting in a lack of focus on lithological correspondence, which is mainly due to the absence of scarce presence of available data on the Sarmatian. We therefore hold firm belief that our study could help develop future links and serve as a knowledge database.

This study utilizes machine-learning algorithms to reinterpret existing datasets originally plotted using Decline-Curve Analysis (DCA), aiming to enhance predictive accuracy without requiring new field-data acquisition. Historical production records were compiled: monthly oil/gas rates, bottom-hole pressures, and cumulative productions, which were fitted to Arps equations via least-squares optimization, and key decline parameters, such as initial rate, nominal decline rate, and hyperbolic exponent, served as input data. Four machine-learning models were trained and validated: Artificial Neural Networks (ANN), Support Vector Machines (SVM), and Linear Regression (LR), using 80/20 train–test splits and 5-fold cross-validation. Models were evaluated using Mean Squared Error (MSE), Root Mean Square Error (RMSE), Mean Absolute Error (MAE), and coefficient of determination (R²). The ANN emerged as the best-performing method, achieving near-unity predictive accuracy (R² ≈ 1) on the independent test set, with low error values (MSE = 0.0012 Ncm²/month², RMSE = 0.035 Ncm/month, MAE = 0.028 Ncm/month) for oil production rates. Similar levels of accuracy were obtained for gas rates and pressures. These results reflect the strong and highly regular relationships present in the dataset analyzed rather than an exact zero-error fit. The multi-layer architecture of the ANN effectively captured the nonlinear interactions between Arps parameters and transient flow regimes, outperforming the empirical and physics-constrained approaches. Linear regression yielded strong results (R² = 0.98, RMSE = 0.15 Ncm/month) but faltered in high-decline scenarios, failing to model exponential tails accurately. SVM exhibited the highest deviations (RMSE = 0.42 Ncm/month, R² = 0.89), attributable to kernel sensitivity in sparse, noisy decline data. RF provided intermediate performance (R² = 0.97). This ANN-driven approach redefines decline analysis by automating parameter tuning and uncertainty quantification, reducing forecasting errors by 85% versus classical Arps methods.

Well-log measurements provide essential information for lithological identification, petrophysical characterization, and reservoir interpretation but incomplete log intervals may occur because of technical, operational, or economic constraints. This study investigates machine-learning-based reconstruction of missing open-hole well-log curves using a depth-indexed dataset from a single well in the Bărbuncești oil and gas field, Romania. Seven predictors (DEPTH, AC, GR, RFOC, RILD, RILM, and SP) were used to estimate ten target properties (CALI, CGR, NPHI, NPOR, PEF, POTA, RHOB, SGR, THOR, and URAN) using Random Forest, Extra Trees, and Artificial Neural Networks. Approximately 2350 valid observations were used for model development and evaluation. Robustness was first assessed using 20 repeated 70/15/15 training/validation/testing partitions and an additional 80/10/10 sensitivity analysis. Under repeated 70/15/15 random partitioning, mean R² values ranged from 0.809 for URAN to 0.935 for RHOB, with relatively small standard deviations, while the 80/10/10 configuration produced only limited changes in performance. However, a nested 10-fold depth-blocked cross-validation procedure, in which model-family selection was performed exclusively on training/validation data and each outer-test block remained completely untouched during model development, yielded negative mean outer-test R² values for all ten target properties when DEPTH was included as a predictor. This marked discrepancy demonstrates that random hold-out validation can substantially overestimate predictive performance in densely sampled, depth-indexed, single-well data and that strong random-split performance should not be interpreted as evidence of generalization to unseen contiguous depth intervals. The reconstructed missing intervals are therefore presented as model-based estimates showing qualitative geological and petrophysical consistency rather than as quantitatively validated reconstructions, because measured target values are unavailable within those intervals. These findings highlight the importance of depth-structured validation for assessing machine-learning-based well-log reconstruction and the need for independent validation using additional wells and geological settings.

The Jurassic formation, west of Capidava-Ovidiu fault, to the north-eastern part of the Moesian Platform, is known relatively little from a petrographic standpoint, an impediment being the insufficient sampling of rock probes. This area of the platform is tectonically active and is part of the Vrancea Seismic Zone, the reason for which numerous studies focused on this aspect rather than other details. The Moesian Platform has long been studied for its hydrocarbon potential, but this feature is in the western part and in isolated areas belonging to the center. The eastern sector, and north-eastern part where our study is conducted, have not been studied in depth due to their correspondence with the Central Dobrogean formations of the same age, for which various studies have been conducted. Our findings reveal the presence of bioturbations during sedimentations which had as result a slight increase in clay material and organic matter in the initial deposits. Also, simultaneously with the recrystallized carbonate as microsparite, small quantities of detrital siliciclastic, somewhat coarser, carbonates have sedimented which resulted in formation of porous space. Keywords: Eastern Moesia, microsparitic carbonate, bioturbations, crystalline limestone, porous lenticles