BioChem - DOS

Hybrid modeling of microbial exopolysaccharide (EPS) production: The case of Enterobacter A47

Journal of biotechnology

Marques, Rodolfo; von Stosch, Moritz; Portela, Rui M.C.; Torres, Cristiana A.V.; Antunes, Sí lvia; Freitas, Filomena; Reis, Maria A.M.; Oliveira, Rui

<P><B>Abstract</B></P> <P> <I>Enterobacter</I> A47 is a bacterium that produces high amounts of a fucose-rich exopolysaccharide (EPS) from glycerol residue of the biodiesel industry. The fed-batch process is characterized by complex non-linear dynamics with highly viscous pseudo-plastic rheology due to the accumulation of EPS in the culture medium. In this paper, we study hybrid modeling as a methodology to increase the predictive power of models for EPS production optimization. We compare six hybrid structures that explore different levels of knowledge-based and machine-learning model components. Knowledge-based components consist of macroscopic material balances, Monod type kinetics, cardinal temperature and pH (CTP) dependency and power-law viscosity models. Unknown dependencies are set to be identified by a feedforward artificial neural network (ANN). A semiparametric identification schema is applied resorting to a data set of 13 independent fed-batch experiments. A parsimonious hybrid model was identified that describes the dynamics of the 13 experiments with the same parameterization. The final model is specific to <I>Enterobacter</I> A47 but can be easily extended to other microbial EPS processes.</P> <P><B>Highlights</B></P> <P> <UL> <LI> Hybrid dynamic models were developed for microbial EPS production. </LI> <LI> Six hybrid structures exploring different degrees of knowledge were compared. </LI> <LI> A parsimonious model was discriminated describing 13 fed-batch experiments. </LI> <LI> Hybrid modeling improves generalization in the context of data sparsity. </LI> </UL> </P>

2017

Elsevier

0168-1656

1873-4863

246

pp.61-70

10.1016/j.jbiotec.2017.01.017

http://click.ndsl.kr/servlet/OpenAPIDetailView?keyValue=05787966&target=NART&cn=NART77471242

Microbial exopolysaccharides (EPS); Enterobacter A47; Hybrid modeling; Knowledge-based modeling; Machine learning; Semiparametric identification