Online sensor for monitoring a microalgal bioreactor system using support vector regression

Abstract In this work, Raman spectroscopy and a machine learning technique known as support vector regression (SVR) are used for building an online sensor to monitor the heterotrophic algal culture conditions in a computer-interfaced bench-scale microalgal bioreactor system, for the production of bio-oil. Monitoring of process conditions in algal cultures is required to enable the use of different control strategies to maximize oil productivity. In order to correlate the Raman spectra with culture conditions, three independent experimental datasets are used. The effect of several preprocessing techniques, including Savitzky–Golay filtering, baseline correction, and standard normal variate transformation, on the goodness of fit is evaluated. A multivariate sensor for real time online monitoring of the concentrations of biomass, glucose and percentage oil content is successfully built and validated. The advantages of using the proposed real-time on-line sensor are illustrated in an experimental microalgal bioreactor system.

[1]  Urs von Stockar,et al.  On‐line monitoring of Phaffia rhodozyma fed‐batch process with in situ dispersive raman spectroscopy , 2003, Biotechnology and bioengineering.

[2]  Qingyu Wu,et al.  High-density fermentation of microalga Chlorella protothecoides in bioreactor for microbio-diesel production , 2008, Applied Microbiology and Biotechnology.

[3]  Amos Ben-Zvi,et al.  Robust modeling of a microalgal heterotrophic fed-batch bioreactor , 2010 .

[4]  Mats Josefson,et al.  Characterization and mapping of carotenoids in the algae Dunaliella and Phaeodactylum using Raman and target orthogonal partial least squares , 2011 .

[5]  Jens Petter Wold,et al.  Raman Spectra of Biological Samples: A Study of Preprocessing Methods , 2006, Applied spectroscopy.

[6]  Y. Chisti.  Biodiesel from microalgae. , 2007, Biotechnology advances.

[7]  Michael K Danquah,et al.  Oil extraction from microalgae for biodiesel production. , 2011, Bioresource technology.

[8]  S. Khatibisepehr,et al.  Data-based modeling and prediction of cytotoxicity induced by contaminants in water resources , 2011, Comput. Biol. Chem..

[9]  Lutgarde M. C. Buydens,et al.  Using support vector machines for time series prediction , 2003 .

[10]  S. Wold,et al.  PLS-regression: a basic tool of chemometrics , 2001 .

[11]  H. Hotelling.  The relations of the newer multivariate statistical methods to factor analysis. , 1957 .

[12]  Anthony Randal McIntosh,et al.  Partial least squares analysis of neuroimaging data: applications and advances , 2004, NeuroImage.

[13]  R. Tibshirani,et al.  Generalized additive models for medical research , 1986, Statistical methods in medical research.

[14]  H. Oh,et al.  Rapid method for the determination of lipid from the green alga Botryococcus braunii , 1998 .

[15]  R. Ruoff,et al.  Micro‐Raman spectroscopy of algae: Composition analysis and fluorescence background behavior , 2009, Biotechnology and bioengineering.

[16]  N S Radin,et al.  Lipid extraction of tissues with a low-toxicity solvent. , 1978, Analytical biochemistry.

[17]  L. Buydens,et al.  Comparing support vector machines to PLS for spectral regression applications , 2004 .

[18]  Yanna Liang,et al.  Biomass and lipid productivities of Chlorella vulgaris under autotrophic, heterotrophic and mixotrophic growth conditions , 2009, Biotechnology Letters.

[19]  Vladimir Vapnik,et al.  Statistical learning theory , 1998 .

[20]  J.T. Kwok,et al.  Linear Dependency betweenand the Input Noise in -Support Vector Regression , 2001 .

[21]  Michael S Feld,et al.  Development of robust calibration models using support vector machines for spectroscopic monitoring of blood glucose. , 2010, Analytical chemistry.

[22]  Gerard L. Cot,et al.  Application of a multivariate technique to Raman spectra for quantification of body chemicals , 1995, IEEE Transactions on Biomedical Engineering.

[23]  W. Cleveland,et al.  Locally Weighted Regression: An Approach to Regression Analysis by Local Fitting , 1988 .

[24]  J. Coello,et al.  Kinetic spectrophotometric determination of Ga(III)-Al(III) mixtures by stopped-flow injection analysis using principal component regression. , 1993, Talanta.

[25]  Charles K. Mann,et al.  Raman measurement of glucose in bioreactor materials , 1997, Photonics West - Biomedical Optics.

[26]  Thomas B. Shope,et al.  The Direct Analysis of Fermentation Products by Raman Spectroscopy , 1987 .

[27]  Bhupinder S. Dayal,et al.  Recursive exponentially weighted PLS and its applications to adaptive control and prediction , 1997 .

[28]  M. Zou,et al.  Rapid authentication of olive oil adulteration by Raman spectrometry. , 2009, Journal of agricultural and food chemistry.

[29]  B. Wawrik,et al.  Rapid, colorimetric quantification of lipid from algal cultures. , 2010, Journal of microbiological methods.

[30]  Lu Wencong,et al.  Support vector regression applied to materials optimization of sialon ceramics , 2006 .

[31]  Yue Jiang,et al.  Differential lipid and fatty acid profiles of photoautotrophic and heterotrophic Chlorella zofingiensis: assessment of algal oils for biodiesel production. , 2011, Bioresource technology.

[32]  Anoop Singh,et al.  Renewable fuels from algae: an answer to debatable land based fuels. , 2011, Bioresource technology.

[33]  Massimiliano Pontil,et al.  On the Noise Model of Support Vector Machines Regression , 2000, ALT.

[34]  H. M. Heise,et al.  Calibration modeling by partial least-squares and principal component regression and its optimization using an improved leverage correction for prediction testing , 1990 .

[35]  Wei Chen,et al.  A high throughput Nile red method for quantitative measurement of neutral lipids in microalgae. , 2009, Journal of microbiological methods.

[36]  Bernhard E. Boser,et al.  A training algorithm for optimal margin classifiers , 1992, COLT '92.

[37]  Rajeev J Ram,et al.  In situ bioprocess monitoring of Escherichia coli bioreactions using Raman spectroscopy , 2004 .

[38]  Mohamed Limam,et al.  Support Vector Regression control charts for multivariate nonlinear autocorrelated processes , 2010 .

[39]  Bernhard Schölkopf,et al.  Learning with kernels , 2001 .

[40]  Sirish L. Shah,et al.  Application of support vector regression for developing soft sensors for nonlinear processes , 2010 .

[41]  Weida Tong,et al.  Multi-class cancer classification by total principal component regression (TPCR) using microarray gene expression data , 2005, Nucleic acids research.

[42]  D. Kell,et al.  Noninvasive, On-Line Monitoring of the Biotransformation by Yeast of Glucose to Ethanol Using Dispersive Raman Spectroscopy and Chemometrics , 1999 .

[43]  A. Ben-Zvi,et al.  The dynamics of heterotrophic algal cultures. , 2011, Bioresource technology.

[44]  D. Massart,et al.  Mutlivariate calibration with Raman data using fast principal component regression and partial least squares methods , 2001 .

[45]  M. Kendall.  A course in multivariate analysis , 1958 .

[46]  Harald Martens,et al.  A multivariate calibration problem in analytical chemistry solved by partial least-squares models in latent variables , 1983 .

[47]  T. Næs,et al.  Principal component regression in NIR analysis: Viewpoints, background details and selection of components , 1988 .

[48]  W. Christie.  PREPARATION OF LIPID EXTRACTS FROM TISSUES , 1993 .

[49]  W. Cleveland.  Robust Locally Weighted Regression and Smoothing Scatterplots , 1979 .