Modular CO2 capture plants can help reducing the cost of deploying capture systems across the globe. However, the CO2 variability and model uncertainty represent operational challenges to capture CO2 from different sources. This work proposes a framework for analyzing the optimal plant design considering different flue gas sources. We show a methodology to generate large data sets from optimization runs using rigorous models in Aspen Plus®. The efficiency of the approach allows its application to large-scale optimization problems (<45,000 variables and equations), with an average CPU time per run of 176 s. We also build surrogate models (SMs) for the capital and operating costs of the capture plants, considering the uncertainty of parameters. We propose an iterative procedure to generate SMs using ALAMO, rejecting SMs with high uncertainty in the estimated parameters. In this way, we obtain SMs with suitable bias-variance tradeoffs, allowing their application to optimization problems under uncertainty.