(190f) Improved Soft Sensors for Mixed Culture System Monitoring

Mixed cultures are biological systems with more than one type of organism sharing or competing for available nutrients. Due to many advantages associated with mixed cultures, their applications in biotechnology has expanded rapidly in recent years with newer applications for producing solvents, acids, plastics, hydrogen, antibiotics, and other valued commodities. At the same time, many challenges remain for effective mixed culture applications. One of them is how to efficiently and accurately monitor the individual cell populations in a mixed culture. The traditional approaches on individual cell mass quantification are suitable for off-line, in frequent characterization of mixed cultures.

To address this challenge, spectra-based soft sensor was proposed [1] to estimate individual biomass concentration in a mixed culture. Although this approach is quick and sufficiently accurate, models are built from data with large number of variable compared to the number of samples, which makes models less accurate and less robust. This work is intended to address this issue.

In this work, models were developed to predict individual biomass concentration for co-culture mixtures of Scheffersomyces Stipitis & Methylomicrobium buryatense, and Escherichia coli & Saccharomyces cerevisiae using partial least squares (PLS). For outlier detection, principal component analysis (PCA) was applied. The main goal of this work was to investigate the effect of variable selection and experimental design on the performance of the PLS soft sensor. Variable selection methods studied in this work are variable importance in projection (VIP), synergy-iPLS, genetic algorithm, and recursive-VIP or R-VIP. Performances of soft sensors with different variable selection methods and different model training scenarios are compared and discussed.

References:

[1] Stone K & Shah D., â??A novel soft sensor approach for estimating individual biomass in mixed culturesâ?. Annual AIChE Meeting, Salt lake city, UT(2015)