An Artificial Neural Network Surrogate Model for Predicting Equilibrium Gas Yields During Supercritical Water Gasification of Açaí Residual Biomass

Authors:
Open Access
Publisher website
Google Scholar
Abstract
Thermodynamic equilibrium modeling is a useful approach for predicting gas production during supercritical water gasification (SCWG) of wet biomass; however, Gibbs energy minimization can be computationally demanding for repeated process simulations. This study developed an artificial neural network (ANN) surrogate model to predict the equilibrium yields of H2, CO, CO2, and CH4 during SCWG of açaí residual biomass from Maranhão, Brazil. Four biomass samples collected under different geographical and seasonal conditions were characterized by ultimate analysis and used to generate a thermodynamic database with 1000 simulations per sample using the TeS-Thermo PyPI Python library (0.1.11). The ANN comprised 10 input variables, two hidden layers with 12 and 6 neurons, and 4 output neurons, and was trained using the Levenberg–Marquardt algorithm. The selected ANN achieved R2 values of 0.99995, 0.99563, 0.99960, and 0.99971 for H2, CO, CO2, and CH4, respectively. External validation using an independent biomass composition provided evidence of the ANN’s generalization capability within the investigated compositional domain, with R2 values above 0.99244 for all four species. Sensitivity analyses further demonstrated that the ANN reproduced the effects of temperature (700–1100 K), water-to-biomass molar ratio (3–6 mol mol−1), and pressure (230–260 bar), with low deviations from TeS-Thermo predictions. These results demonstrate that the ANN provides an accurate and computationally efficient surrogate model for rapid thermodynamic screening, sensitivity analysis and process optimization of SCWG biomass processes.
Funding Information
  • National Agency of Petroleum, Natural Gas and Biofuels (2025/02550-5)
  • National Agency of Petroleum, Natural Gas and Biofuels (2025/17586-5)

This publication has 61 references indexed in Scilit: