Hydrogen (H2) is at the forefront of sustainable energy solutions, crucial for achieving global decarbonization goals. By 2030, around 150 Mt of H2 will be needed to meet net zero emission targets by 2050. While Steam Methane Reforming (SMR) is cost-effective for H2 production, its significant CO2 emissions necessitate exploring cleaner methods. Traditional process-based models, though accurate, are computationally intensive for optimization. Incorporating Machine Learning (ML) can provide faster predictions and real-time optimization. Combining ML with process-based models offers a balance between efficiency and interpretability, crucial for safety-critical applications like H2 production. This hybrid approach has shown success in various processes, optimizing reactor performance effectively. In a recent study, a Python-based framework integrating process-based modeling and ML was developed for optimizing H2 production and reducing carbon emissions in a reactor. The model was validated against commercial software and optimized to minimize the cost of hydrogen (LCOH) and specific carbon emissions. This innovative approach enables real-time optimization while achieving a balance between economic viability and sustainability. The study's multi-objective optimization framework, utilizing ML and genetic algorithms, provides a new perspective on operational decision-making in sustainable energy production.