Sustainability assessment of biomethanol production via hydrothermal gasification supported by artificial neural network

Global warming and climate change urge the deployment of close carbon-neutral technologies via synthesis low-carbon emission fuels materials. An efficient intermediate product such is biomethanol produced from biomass. Microalgae based offer scalable solutions for biofixation CO2, where biomass can be transformed into value-added fuel gas mixtures by applying thermochemical processes. In this study, environmental economic performances production are examined using artificial neural networks (ANNs) modelling catalytic noncatalytic hydrothermal gasification (HTG). Levenberg-Marquardt Bayesian Regularisation algorithms applied to describe thermocatalytic transformation involving various types feedstocks (biomass wastes) in training process. The relationship between elemental composition feedstock, HTG reaction conditions (380 °C–717 °C, 22.5 MPa–34.4 MPa, 1–30 wt% biomass-to-water ratio, 0.3 min–60.0 min residence time, up 5.5 NaOH catalyst load) yield & determined Chlorella vulgaris strain. ideal ANN topology characterised high performance (MSE = 5.680E-01) accuracies (R2 ? 0.965) 2 hidden layers with 17-17 neurons. process flowsheeting biomass-to-methanol valorisation performed ASPEN Plus software ANN-based profiles. Cradle-to-gate life cycle assessment (LCA) carried out evaluate potential alternatives. It obtained that greenhouse (GHG) reduction (?725 kg CO2,eq (t CH3OH)?1) achieved enriching syngas H2 variable renewable electricity sources. utilisation found a favourable alternative due (i) composition, (ii) heat integration, (iii) GHG mitigation possibilities.