TY - GEN A1 - Jafari, Mitra A1 - Shafiee, Parisa A1 - Dorneanu, Bogdan A1 - Arellano-García, Harvey T1 - Towards efficient material design: use of machine learning to predict chemical reactions and retrosynthesis T2 - Annual Meeting of Process Engineering and Materials Technology 2024 Y1 - 2024 UR - https://www.researchgate.net/publication/388143384_Towards_efficient_material_design_Use_of_Machine_Learning_to_predict_chemical_reactions_and_retrosynthesis ER - TY - GEN A1 - Shafiee, Parisa A1 - Mbuya, Christel-Olivier Lenge A1 - Dorneanu, Bogdan A1 - Arellano-García, Harvey T1 - Novel approaches for preparation of 3D Ni-Al2O3 core with zeolite shell catalysts for dry reforming of methane T2 - 18th International Congress on Catalysis Y1 - 2024 UR - https://www.researchgate.net/publication/388109598_Novel_Approaches_for_Preparation_of_3D_Ni-Al2O3_Core_with_Zeolite_Shell_Catalysts_for_Dry_Reforming_of_Methane ER - TY - GEN A1 - Jafari, Mitra A1 - Shafiee, Parisa A1 - Santos da Silva, Jefferson A1 - Dorneanu, Bogdan A1 - Valverde Pontes, Karen A1 - Arellano-Garcia, Harvey T1 - Advancing catalyst design with machine learning : insights from FTS and DME production T2 - Annual Meeting on Reaction Engineering 2025 N2 - This contribution presents a ML-based framework to optimize heterogeneous catalysts, with a primary focus on the targeted application for FTS and DME production. However, the framework is designed to be generic, with applicability to a broader range of heterogeneous catalytic processes. The study analyzes a variety of catalyst parameters, including composition, pretreatment, and operating conditions, and employs advanced ML techniques such as regression models, ensemble learning, and neural networks to model the relationships between these factors and reaction outcomes. Hyperparameter optimization and performance evaluation using metrics like R², RMSE, MSE, and AIC further improve the accuracy and robustness of the models. In addition, the study provides a comparative analysis of applying this ML framework to both FTS and DME processes, highlighting the similarities and differences in optimizing catalyst performance and operating conditions. The study aims to identify the most influential parameters that drive catalyst performance and to assess the predictive power of each model. By enhancing understanding of how catalyst properties and operating conditions influence the efficiency of FTS and DME production, this work provides valuable insights into more efficient and sustainable catalytic process design. Y1 - 2025 UR - https://www.researchgate.net/publication/392137173_Advancing_catalyst_design_with_Machine_Learning_Insights_from_FTS_and_DME_production SP - 1 EP - 6 ER -