Unconfined Compressive Strength (UCS) is a crucial geomechanical parameter commonly used in petroleum engineering and geology to evaluate rock integrity and its response to stress. Therefore, accurate measurements or estimation of UCS values is essential for efficient reservoir management and operational planning due to their significant role in evaluating wellbore stability, constructing fracture stimulation, and implementing well control techniques. However, to precisely ascertain the values of UCS, it is important to acquire rock samples from the specified region of interest. Unfortunately, retrieved cores typically extend only to the reservoir section and often exhibit significant discontinuities. Moreover, the core extraction process is both time-consuming and costly. Therefore, selecting the most appropriate correlation to estimate the UCS profile for the study area is crucial. In this context, a field case study was conducted in southern Iraq to develop reliable and straightforward mathematical models—namely, multiple regression analysis (MRA) and artificial neural networks (ANN)—for sandstone formations, using well-logging data to generate the UCS profile. The results demonstrate that both ANN and MRA models effectively predict UCS values when compared to empirical correlations from the literature and actual UCS measurements. Moreover, the ANN model outperforms the MRA model, achieving a higher coefficient of determination (R²) of 0.99, compared to 0.84 for the MRA. This study ultimately presents efficient and cost-effective methods that integrate conventional well logs to predict the UCS profile accurately.