Data-Driven Design of Green Chemical Properties
Bioderived feedstocks offer the opportunity to design transportation fuels with dramatically improved efficiency, emissions, and carbon footprint but detailed chemical kinetic mechanisms of biofuel blendstocks are not well understood. We develop to construct reduced kinetic models that accurately describe soot precursor formation at a localized level and use YSI (Yield Sooting Index, https://ysi.ml.nrel.gov) for network-embedded validation. This project will enable us to provide one of the fundamental links in the chain of models connecting fuel chemical structure to particulate matter. The most significant advantage is the quick building of reduced kinetic mechanisms for any target molecule which doesn’t have a detailed mechanism. Moving beyond the prediction of molecular properties, we explore the potential to use a machine learning approach in automating QM calculations for large-scale kinetic simulations. This is an expansion of our bond dissociation energy (BDE) machine learning model (https://bde.ml.nrel.gov/). These efforts will dramatically expand our ability to design fuel blendstocks that optimally leverage bioderived functionality in new, efficient engine designs.
Related Publications
Versatile Mechanism-aware Yield Prediction Model of Ultrahigh-throughput Medicinal Chemistry Reactions, Sumin Song, Xueying Zhang, Taige Lu, Tim Cernak, and Seonah Kim. ChemRxiv, (2026)
Learning Diffusion from Sparse Data: A Machine-Learning Bridge between Molecular Motion and Macroscopic Transport, Hojin Jung, Su-min Song, Sabari Kumar, Collin Hansen, Maxwell Simon, Juhui Lee, Yutong Qi, Kyung-Min Lim, and Seonah Kim. J. Chem. Inf. Model. 66 (15), 8792–8804 (2026)
A Fragment Based Approach Towards Curating, Comparing and Developing Machine Learning Models Applied in Photochemistry, Raúl Pérez-Soto,† Mihai V. Popescu,† Sabari Kumar,† Leticia Adao Gomes, Changyeob Lee, Elijah Shore, Steven A. Lopez, Robert S. Paton, Seonah Kim, Chem. Sci. 16, 21874-21866, (2025)
Combining Geometry and Topology for Accurate Protein Solubility Prediction, Sabari N. Kumar, Olivia Harman, Su-min Song, Yeonjoon Kim, Robert S. Paton, Seonah Kim, ChemRxiv (10.26434/chemrxiv-2025-jmzwn), Digital Discovery (in review, 2025)
Enhancing Predictive Models for Solubility in Multicomponent Solvent Systems using Semi-Supervised Graph Neural Networks, Hojin Jung, Christopher D. Stubbs, Sabari Kumar, Raúl Pérez-Soto, Su-min Song, Yeonjoon Kim, Seonah Kim, Digital Discovery, 4, 1492-1504 (2025)
Predicting homopolymer and copolymer solubility through machine learning, Christopher D. Stubbs, Yeonjoon Kim, Ethan C. Quinn, Raúl Pérez-Soto, Eugene Y.-X. Chen, and Seonah Kim, Digital Discovery, 4, 424-437 (2025)
Designing solvent systems using self-evolving solubility databases and graph neural networks, Yeonjoon Kim, Hojin Jung, Sabari Kumar, Robert S. Paton, Seonah Kim†, Chem. Sci., 15, 923-939 (2024)
A Machine Learning Model for Automated Prediction of Bio-Oil Composition from Molecular Beam Mass Spectra, Mohammed Jabed, Yeonjoon Kim, Clark Yarbrough, Anne Harman-Ware, Jessica Olstad, Reinhard Seiser, Cheyenne Paeper, Anne Starace, Seonah Kim, ACS Sustainable Chemistry and Engineering, 11, 32, 11912-11923 (2023)
Designing high-performance fuels through graph neural networks for predicting cetane number of multicomponent surrogate mixtures. Yeonjoon Kim, Sabari Kumar, Jaeyoung Cho, Nimal Naser, Wonjong Ko, Peter C. St. John, Robert L. McCormick, Seonah Kim, SAE Technical Paper No. 2023-32-0052 (2023)
Sooting tendencies of terpenes and hydrogenated terpenes as sustainable transportation biofuels Junqing Zhu, Juan V. Alegre-Requena, Patrick Cherry, Dominic Curtis, Benjamin G. Harvey, Mohamed A. Jabed, Seonah Kim, Charles S. McEnally, Lisa D. Pfefferle, Josanne-Dee Woodroffe, Proc. Comb. Inst., 39, 1, 877-887 (2023)
Enhancing φ-sensitivity of ignition delay times through dilution of fuel-air mixture Jaeyoung Cho, Jon Luecke, Mohammad J Rahimi, Yeonjoon Kim, Bradley T Zigler, Seonah Kim†, Proc. Comb. Inst., 39, 4, 4939-4947 (2023)
Physics-informed graph neural networks for predicting cetane number with systematic data quality analysis, Yeonjoon Kim, Jaeyoung Cho, Nimal Naser, Sabari Kumar, Keunhong Jeong, Robert L. McCormick, Peter C. St. John, Seonah Kim†, Proc. Comb. Inst., 39, 4, 4969-4978 (2023)
A comprehensive experimental and kinetic modeling study of di-isobutylene isomers: Part 2, Nitin Lokachari, Goutham Kukkadapu, Brian D. Etz, Gina M. Fioroni, Seonah Kim, Mathias Steglich, Andras Bodi, Patrick Hemberger, Sergey S. Matveev, Anna Thomas, Hwasup Song, Guillaume Vanhove, Kuiwen Zhang, Guillaume Dayma, Maxence Lailliau, Zeynep Serinyel, Alexander A. Konnov, Philippe Dagaut, William J. Pitz, Henry J. Curran, Combustion and Flame, 251, 112547 (2023)
A comprehensive experimental and kinetic modeling study of di-isobutylene isomers: Part 1, Nitin Lokachari, Goutham Kukkadapu, Hwasup Song, Guillaume Vanhove, Guillaume Dayma, Zeynep Serinyel, Kuiwen Zhang, Roland Dauphin, Brian Etz, Seonah Kim, Mathias Steglich, Andras Bodi, Gina Fioroni, Patrick Hemberger, Sergey S. Matveev, Alexander A. Konnov, Philippe Dagaut, Scott W Wagnon, William J. Pitz, Henry J. Curran, Combustion and Flame, 251, 112301 (2023)
Bioderived ether design for low emission and high reactivity transport fuels. Jaeyoung Cho, Yeonjoon Kim, Brian D. Etz, Gina M. Fioroni, Nimal Naser, Junqing Zhu, Zhanhong Xiang, Cameron Hays, Juan V. Alegre-Requena, Peter C. St John, Bradley T. Zigler, Charles S. McEnally, Lisa D. Pfefferle, Robert L. McCormick, Seonah Kim†, Sustainable Energy and Fuels, 6, 3975-3988 (2022)
Chemical kinetic basis of synergistic blending for research octane number, Gina M. Fioroni, Mohammed J. Rahimi, Charles K. Westbrook, Scott W. Wagnon, William J. Pitz, Seonah Kim and Robert L. McCormick, Fuel, 307, 121865 (2022)
Understanding how chemical structure affects ignition-delay-time φ-sensitivity, Richard A. Messerly, Jon H. Luecke, Peter C. St. John, Brian D. Etz, Yeonjoon Kim, Bradley T. Zigler, Robert L. McCormick, Seonah Kim†, Combustion & Flame, 225, 377-387 (2021)
Prediction of gas-phase homolytic bond dissociation energies at near chemical accuracy with sub-second computational cost, Peter C. St. John†, Yanfei Guan, Yeonjoon Kim, Seonah Kim†, Robert S. Paton†, Nature Comm., 11, 2328 (2020).
A quantitative model for the prediction of sooting tendency from molecular structure, Peter C. St John, Paul Kairys, Dhrubajyoti D. Das, Charles S. McEnally, Lisa D. Pfefferle, David J. Robichaud, Mark R. Nimlos, Bradley T. Zigler, Robert L. McCormick, Thomas D. Foust, Yannick J. Bomble, and Seonah Kim†, Energy & Fuels, 31 (9), 9983-9990 (2017).
