A hybrid computational fluid dynamics-artificial neural network approach is applied to predict the thermo-hydraulic performance factor (THPF) of a solar air heater with vertical cylindrical ribs. 3-D CFD analysis considering effects of rib height, rib diameter, rib pitches are simulated for Re ranging 5000-24000. A total of 504 data sets for different cases are generated using CFD. Based on these data sets, an optimized ANN model is developed to predict the thermo-hydraulic performance. The optimized ANN model has an architecture of 5-25-1 and the mean squared error for this ANN model is 0.000051 for the testing data sets. The maximum THPF value achieved is 1.43 for rib height of 3.5 mm, rib diameter of 3 mm, rib transverse pitch of 20 mm and relative roughness pitch of 10 at Re = 8000. Global sensitivity analysis is also performed based on SHAP (SHapley Additive exPlanations) for the ANN model - Reynolds number is observed to be the most influencing factor with mean absolute SHAP value of 0.031 in predicting THPF along with transverse pitch which has SHAP value very close to Re. Computational CPU time comparison is also performed and approximately 100% reduction is achieved using the optimized ANN model. This research proposed a novel approach that could be successfully implemented in assessing thermal performance of solar-thermal collector systems.