Comparison of machine learning methodologies for predicting kinetics of hydrothermal carbonization of selective biomass

Author(s):  
Mohammadreza Aghaaminiha ◽  
Ramin Mehrani ◽  
Toufiq Reza ◽  
Sumit Sharma
Energies ◽  
2019 ◽  
Vol 12 (3) ◽  
pp. 516 ◽  
Author(s):  
Michela Lucian ◽  
Maurizio Volpe ◽  
Luca Fiori

Olive trimmings (OT) were used as feedstock for an in-depth experimental study on the reaction kinetics controlling hydrothermal carbonization (HTC). OT were hydrothermally carbonized for a residence time τ of up to 8 h at temperatures between 180 and 250 °C to systematically investigate the chemical and energy properties changes of hydrochars during HTC. Additional experiments at 120 and 150 °C at τ = 0 h were carried out to analyze the heat-up transient phase required to reach the HTC set-point temperature. Furthermore, an original HTC reaction kinetics model was developed. The HTC reaction pathway was described through a lumped model, in which biomass is converted into solid (distinguished between primary and secondary char), liquid, and gaseous products. The kinetics model, written in MATLABTM, was used in best fitting routines with HTC experimental data obtained using OT and two other agro-wastes previously tested: grape marc and Opuntia Ficus Indica. The HTC kinetics model effectively predicts carbon distribution among HTC products versus time with the thermal transient phase included; it represents an effective tool for R&D in the HTC field. Importantly, both modeling and experimental data suggest that already during the heat-up phase, biomass greatly carbonizes, in particular at the highest temperature tested of 250 °C.


2013 ◽  
Vol 372 (1-2) ◽  
pp. 375-387 ◽  
Author(s):  
Mo Bai ◽  
Burkhard Wilske ◽  
Franz Buegger ◽  
Jürgen Esperschütz ◽  
Claudia Irene Kammann ◽  
...  

2013 ◽  
Vol 139 ◽  
pp. 161-169 ◽  
Author(s):  
M. Toufiq Reza ◽  
Wei Yan ◽  
M. Helal Uddin ◽  
Joan G. Lynam ◽  
S. Kent Hoekman ◽  
...  

2016 ◽  
Vol 205 ◽  
pp. 199-204 ◽  
Author(s):  
Wei Yang ◽  
Hui Wang ◽  
Meng Zhang ◽  
Jiayu Zhu ◽  
Jie Zhou ◽  
...  

2021 ◽  
Author(s):  
Yvonne M Mueller ◽  
Thijs J Schrama ◽  
Rik Ruijten ◽  
Marco W.J. Schreurs ◽  
Dwin G.B. Grashof ◽  
...  

Quantitative or qualitative differences in immunity may drive and predict clinical severity in COVID-19. We therefore measured modules of serum pro-inflammatory, anti-inflammatory and anti-viral cytokines in combination with the anti-SARS-CoV-2 antibody response in COVID-19 patients admitted to tertiary care. Using machine learning and employing unsupervised hierarchical clustering, agnostic to severity, we identified three distinct immunotypes that were shown post-clustering to predict very different clinical courses such as clinical improvement or clinical deterioration. Immunotypes did not associate chronologically with disease duration but rather reflect variations in the nature and kinetics of individual patient's immune response. Here we demonstrate that immunophenotyping can stratify patients to high and low risk clinical subtypes, with distinct cytokine and antibody profiles, that can predict severity progression and guide personalized therapy.


Sign in / Sign up

Export Citation Format

Share Document