Abstract In the present work, attempts have been made to predict the performance of an indirect solar dryer (ISD) integrated with V‐shaped fins using ivy gourd as the test material, through machine learning (ML). The experimental data are continuously recorded, and the ISD attained collector efficiencies of over 70% and drying efficiencies over 15%, and moisture content (MC) of the product dropped down to less than 10% in 16 h. The six ML models are developed using nine input variables to estimate three important performance parameters such as drying efficiency (DE), collector efficiency (CE), and MC. The models based on ensemble model showed better predictability than any one of the algorithms. Comparison with all the results, Gradient Boosting, and Extreme Gradient Boosting (XGBoost) are found to be the most efficient and accurate algorithms when compared for modeling the performance of the ISD system. The highest prediction accuracies were observed for Gradient Boosting and XGBoost, providing R 2 (coefficient of determination) of up to 0.9998 and 0.9996, respectively, indicating their high competence in capturing the nonlinear thermodynamic interactions during the drying process. The ability to model non‐linear and coupled thermal–mass transfer relationships enables better generalization and prediction accuracy for the DE, CE, and MC estimates. These observations indicate that ML models can reliably predict ISD performance, thereby reducing the need for repeated experimental trials. The results support the integration of ML‐based predictive tools for optimizing solar drying parameters and improving operational control in agricultural and food‐processing applications.
Padmavathy et al. (Wed,) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: