<p>Accurate mass estimation of agricultural products plays a vital role in enhancing post-harvest handling, storage and processing efficiency. This study presents a constructive approach to modelling the mass of potato (<i>Solanum tuberosum</i>) using targeted dimensional attributes, employing both artificial neural networks (ANN) and response surface methodology (RSM). By leveraging a dataset that encompasses essential physical parameters, such as length, width, projected area and perimeter, we have successfully constructed predictive models that can significantly improve the accuracy of mass estimations. The ANN model was carefully trained and optimised to effectively capture the nonlinear relationships inherent in the data, while the RSM approach offers a robust analytical framework for examining variable interactions. Our performance evaluation, utilising metrics like the coefficient of determination (<i>R</i>²), root mean square error (RMSE) and mean square error (MSE), reveals that the ANN model excels in predicting potato mass, surpassing traditional regression techniques. Notably, the RSM exhibited an impressive <i>R</i>² of 0.9981, and the ANN model reached an <i>R</i>² of 0.9943, both demonstrating a strong correlation with actual mass measurements. These findings underscore the potential of our proposed models for image-based weight estimation, facilitating improved sorting and grading of potatoes. By implementing these innovative mass estimation techniques, we can enable automated sorting processes, enhance yield estimations, optimise supply chains, conduct non-destructive quality assessments, incorporate smart farming practices and minimise post-harvest losses—all while ensuring standardised food processing. In conclusion, this research highlights the promising avenues for intelligent modelling techniques in agricultural engineering, offering scalable solutions that can significantly contribute to the efficiency and effectiveness of mass estimation in the agricultural sector.</p>