Core extraction and analysis are fundamental components of reservoir development. Core samples provide continuous vertical sections of the subsurface, enabling detailed visual assessment of depositional sequences and variations in reservoir characteristics. A thorough examination of these cores yields critical information significantly contributing to understanding and optimizing reservoir development. This data can include direct evidence of hydrocarbons' presence, quantity, spatial distribution, and production potential. The analysis of core samples is vital for understanding the pore system properties within potential reservoir intervals. Insights derived from core data improve the ability to predict reservoir performance and inform the selection of strategies to maximize cost-effective hydrocarbon recovery. This study employs a representative dataset from the Arabian Peninsula, specifically within the United Arab Emirates, using the Costa model as a supporting framework. The analysis incorporates the largest and smallest available sample sizes to ensure the final results remain within an acceptable range of variation. Each input parameter—core length, diameter, weight, fluid volumes, oil density, brine salinity (ppm), and brine density—is systematically varied to evaluate its impact on key reservoir properties, including saturation, porosity, permeability, and grain density. Additionally, the study investigates the effects of various combinations of incorrect input parameters to assess their influence on overall measurement accuracy. This methodology underpins a novel, AI-driven approach to uncertainty estimation in reservoir analysis. This approach enables more accurate assessment and informed decision-making in reserve estimation and reservoir management by quantifying the uncertainty in core-derived measurements.