In practical oilfield production, the phenomenon of water influx typically shortens the water-free recovery period of wells, leading to water flooding and causing a sharp decline in the production well yields, bringing great harm to production. Water invasion usually occurs as a result of the elastic expansion of the water as well as the compaction of the aquifer pore space. However, it can be due to the special characteristics of fractured-vuggy reservoirs such as non-homogeneity and the discrete distribution of the pore spaces. It is challenging to use traditional seepage flow theories to analyze the characteristics of water influx. Also, reservoir numerical simulation methods require numerous parameters which are difficult to obtain, which significantly reduces the accuracy of the results. In this study, considering the driving energy for water influx, a water influx characteristic model was obtained by fitting a graph plate. Subsequently, an iterative calculation method was used to simultaneously obtain water influx volume and OOIP. The aquifer to hydrocarbon ratio was determined by fitting the water influx curve with the graphic plate. Results show that the calculation method is sensitive to the values of reservoir pressure and the crude oil formation volume factor. After applying the method to one field case, it was discovered that water influx performance can be characterized into two types, i.e., linear water influx and logarithmic water influx. In the early stages, the water influx rate of logarithmic water influx is greater compared to linear water influx. However, the volume and energy of waterbody are limited, and the water invasion phenomenon occurs almost exclusively within a short period after the invasion. On the other hand, the volume of waterbody invaded by linear water influx is larger, and it can maintain a stable rate of water influx. The results of the study can provide theoretical support for the waterbody energy evaluation and dynamic analysis of water influx, as well as the control and management of water in these types of reservoirs.

Pressure-dependent pore-volume deformation is a critical but poorly constrained variable in dynamic reserve assessment for ultra-deep fractured-vuggy carbonate reservoirs, where fractures, dissolution pores, and vugs respond differently to effective-stress loading. In this work, a pore-structure-aware evaluation strategy was developed by integrating high-temperature and high-pressure volumetric measurements with data-driven regression. Twelve carbonate core plugs from the Ordovician Yijianfang and Yingshan formations of the Fuman Oilfield were selected to represent matrix-pore, dissolution-pore, fracture-vug, and fracture-dominated pore systems. Stepwise net-pressure experiments were performed under simulated reservoir conditions, and pore-volume compressibility (Cp) was calculated from corrected pore-volume changes. Measured C_p values reveal a distinct stress-sensitive response: C_p declines sharply during the low-net-pressure stage and then tends toward a quasi-stable level as net pressure increases, indicating progressive closure of mechanically compliant fractures, narrow throats, and weakly supported dissolution pores. Although porosity is positively associated with Cp, samples with comparable porosity display markedly different compressibility values, confirming that pore-space geometry and fracture-related compliance must be considered. Eight representative regression algorithms were then compared, using net pressure, porosity, permeability, initial pore volume, surface porosity, temperature, and a pore-structure index as model inputs. To further assess model generalization to completely unseen core plugs, additional core-ID-based leave-one-core-out (LOCO) validation was performed for k-nearest neighbors and AdaBoost. Under this grouped validation, k-nearest neighbors yielded an RMSE of 13.5978 × 10⁻⁴ MPa⁻¹ and an R² of 0.8408, whereas AdaBoost achieved an RMSE of 10.0160 × 10⁻⁴ MPa⁻¹ and an R² of 0.9136, indicating greater cross-core robustness of AdaBoost. Permutation-importance analysis of the split-specific KNN model indicated that net pressure, porosity, surface porosity, and pore-structure index made the largest predictive contributions within that model. Moreover, the predicted normalized Cp values reproduced the experimentally observed decreasing trend with increasing net pressure, supporting the physical consistency of the k-nearest neighbors predictions. The proposed experimental–machine learning framework offers a pressure-dependent method for estimating pore-volume compressibility within the geological and petrophysical domain represented by the investigated Fuman Oilfield cores, and provides more representative inputs for material-balance analysis, dynamic reserve evaluation, and production adjustment.