The drying kinetics of periwinkle meat, a seafood delicacy, is crucial for optimizing preservation methods and ensuring product quality. This study explores the application of Artificial Neural Networks (ANN) to predict the drying kinetics of periwinkle meat under various drying conditions. A comprehensive dataset was generated through experimental drying processes, capturing variables such as temperature, thickness and drying time. The ANN model was developed using multi-layer feed-forward architecture, with input parameters (independable variables) including initial dying time, drying temperature, and thickness while the output (dependable variables) was the moisture content at different time intervals. The model was trained and validated using a portion of the dataset, achieving a high degree of accuracy in predicting moisture loss over time. Performance metrics, including RMSE and R-squared values, indicated that the ANN model effectively captured the nonlinear relationships inherent in the drying process. The average range of the Deff values was 3.12 × 10−12 m2/s to 4.82 × 10−12 m2/s. The highest R2 value, 0.9996 was found in the ANN model, this demonstrated that ANN can serve as a powerful tool for modeling drying kinetics, offering insights that can enhance drying efficiency and product quality in the seafood industry. Ea had a value of 15.325 kJ/mol in oven drying method. This approach not only streamlines the drying process but also contributes to the development of more sustainable practices in food preservation. Future work will focus on refining the model and exploring its applicability to other seafood products.