This paper presents a comprehensive study on the development of a neural network model aimed at predicting the cargo handling time and berthing time. Utilizing physical ship data (length, beam, draught, DWT, and GT), cargo type, daily weather conditions, cargo handling equipment data, and historical operation times, the model aims to enhance the operational efficiency of bulk terminals. A case study conducted at a bulk terminal, leveraging a three-year dataset, serves as the foundation of this research. The outcomes of the neural network analysis highlight the average cargo handling capacity under various conditions, providing crucial insights for port operation optimizations such as determining the optimal number of gangs, calculating berth occupancy ratios, and improving berth planning strategies. The implications of these findings are significant, offering a pathway toward more efficient and predictive port management strategies, with the potential to substantially reduce operational costs and increase throughput efficiency. This study not only contributes to the existing body of knowledge by integrating diverse data types into a predictive model but also proposes practical applications that can lead to more informed decision-making in port and terminal operations.