Register Now

EUBCE 2026 - Laura Catalina GONZÁLEZ - Interpretable Classification Model for Identifying Potential Syngas Applications Based on Feedstock Properties And Process Parameters

Interpretable Classification Model for Identifying Potential Syngas Applications Based on Feedstock Properties And Process Parameters

 Print
Gasification for power, CHP and polygeneration

Gasification processes for polygeneration and including biochar and classification model

Interpretable Classification Model for Identifying Potential Syngas Applications Based on Feedstock Properties And Process Parameters

Short Introductive summary

Residual biomass gasification is a promising pathway for sustainable energy and chemicals’ production. However, biomass feedstock variability and complex operational interactions limit the large-scale application of the process. This study presents a data-driven model to predict syngas composition and end-use application based on biomass’ properties and operational conditions, covering a wide range of residual biomass feedstocks, gasification conditions and reactor configurations. A CatBoost-based Decision Tree Regressor was trained on 133 experimental samples compiled from peer-reviewed studies. The dataset was augmented using the Synthetic Minority Over-sampling Technique (SMOTE) to mitigate class imbalance and enhance generalization across diverse gasification outcomes. Model performance was rigorously evaluated through nested cross-validation, yielding mean average errors of 4.2 ± 0.3 %vol for H2, 2.9 ± 0.4 %vol for CO, and 1.4 ± 0.3 %vol for CH4. Beyond composition predictions, the model accurately classified the most suitable syngas applications, achieving over 90% identification for heat/power generation, methanol and biofuel synthesis, and SNG production.

Presenter

Moderator portrait

Laura Catalina GONZÁLEZ

University EAFIT, Applied Science and Engineering Dpt., COLOMBIA

Presenter's biography

PhD candidate with four years of research experience in alternative fuels and thermochemical conversion. Research focused on bioSNG production from residual biomass, integrating data-driven and mechanistic modeling with laboratory-scale experimental and pilot system development.

Biographies and Short introductive summaries are supplied directly by presenters and are published here unedited


Co-authors:

L.C. González, University EAFIT, Medellin, COLOMBIA
S. García-Freites, Promigas, Barranquilla, COLOMBIA
M. Sanjuan, Promigas, Barranquilla, COLOMBIA
D. Acosta, Promigas, Barranquilla, COLOMBIA
A. Aristizabal, University EAFIT, Medellin, COLOMBIA
M.L. Botero, University EAFIT, Medellin, COLOMBIA
S. Builes, University EAFIT, Medellin, COLOMBIA

Session reference: 4AO.5.4