MACHINE LEARNING TECHNIQUES APPLIED TO LIGNOCELLULOSIC ETHANOL IN SIMULTANEOUS HYDROLYSIS AND FERMENTATION
Abstract This paper investigates the use of machine learning (ML) techniques to study the effect of different process conditions on ethanol production from lignocellulosic sugarcane bagasse biomass using S. cerevisiae in a simultaneous hydrolysis and fermentation (SHF) process. The effects of temper...
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Brazilian Society of Chemical Engineering
|
Series: | Brazilian Journal of Chemical Engineering |
Subjects: | |
Online Access: | http://www.scielo.br/scielo.php?script=sci_arttext&pid=S0104-66322017000100053&lng=en&tlng=en |
id |
doaj-5a61627f4c474434a733633629519fa3 |
---|---|
record_format |
Article |
spelling |
doaj-5a61627f4c474434a733633629519fa32020-11-24T22:34:50ZengBrazilian Society of Chemical EngineeringBrazilian Journal of Chemical Engineering1678-4383341536310.1590/0104-6632.20170341s20150475S0104-66322017000100053MACHINE LEARNING TECHNIQUES APPLIED TO LIGNOCELLULOSIC ETHANOL IN SIMULTANEOUS HYDROLYSIS AND FERMENTATIONJ. FischerV. S. LopesS. L. CardosoU. Coutinho FilhoV. L. CardosoAbstract This paper investigates the use of machine learning (ML) techniques to study the effect of different process conditions on ethanol production from lignocellulosic sugarcane bagasse biomass using S. cerevisiae in a simultaneous hydrolysis and fermentation (SHF) process. The effects of temperature, enzyme concentration, biomass load, inoculum size and time were investigated using artificial neural networks, a C5.0 classification tree and random forest algorithms. The optimization of ethanol production was also evaluated. The results clearly depict that ML techniques can be used to evaluate the SHF (R2 between actual and model predictions higher than 0.90, absolute average deviation lower than 8.1% and RMSE lower than 0.80) and predict optimized conditions which are in close agreement with those found experimentally. Optimal conditions were found to be a temperature of 35 ºC, an SHF time of 36 h, enzymatic load of 99.8%, inoculum size of 29.5 g/L and bagasse concentration of 24.9%. The ethanol concentration and volumetric productivity for these conditions were 12.1 g/L and 0.336 g/L.h, respectively.http://www.scielo.br/scielo.php?script=sci_arttext&pid=S0104-66322017000100053&lng=en&tlng=enLignocellulosic ethanolMachine learningSimultaneous hydrolysis and fermentationCrude enzyme complex |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
J. Fischer V. S. Lopes S. L. Cardoso U. Coutinho Filho V. L. Cardoso |
spellingShingle |
J. Fischer V. S. Lopes S. L. Cardoso U. Coutinho Filho V. L. Cardoso MACHINE LEARNING TECHNIQUES APPLIED TO LIGNOCELLULOSIC ETHANOL IN SIMULTANEOUS HYDROLYSIS AND FERMENTATION Brazilian Journal of Chemical Engineering Lignocellulosic ethanol Machine learning Simultaneous hydrolysis and fermentation Crude enzyme complex |
author_facet |
J. Fischer V. S. Lopes S. L. Cardoso U. Coutinho Filho V. L. Cardoso |
author_sort |
J. Fischer |
title |
MACHINE LEARNING TECHNIQUES APPLIED TO LIGNOCELLULOSIC ETHANOL IN SIMULTANEOUS HYDROLYSIS AND FERMENTATION |
title_short |
MACHINE LEARNING TECHNIQUES APPLIED TO LIGNOCELLULOSIC ETHANOL IN SIMULTANEOUS HYDROLYSIS AND FERMENTATION |
title_full |
MACHINE LEARNING TECHNIQUES APPLIED TO LIGNOCELLULOSIC ETHANOL IN SIMULTANEOUS HYDROLYSIS AND FERMENTATION |
title_fullStr |
MACHINE LEARNING TECHNIQUES APPLIED TO LIGNOCELLULOSIC ETHANOL IN SIMULTANEOUS HYDROLYSIS AND FERMENTATION |
title_full_unstemmed |
MACHINE LEARNING TECHNIQUES APPLIED TO LIGNOCELLULOSIC ETHANOL IN SIMULTANEOUS HYDROLYSIS AND FERMENTATION |
title_sort |
machine learning techniques applied to lignocellulosic ethanol in simultaneous hydrolysis and fermentation |
publisher |
Brazilian Society of Chemical Engineering |
series |
Brazilian Journal of Chemical Engineering |
issn |
1678-4383 |
description |
Abstract This paper investigates the use of machine learning (ML) techniques to study the effect of different process conditions on ethanol production from lignocellulosic sugarcane bagasse biomass using S. cerevisiae in a simultaneous hydrolysis and fermentation (SHF) process. The effects of temperature, enzyme concentration, biomass load, inoculum size and time were investigated using artificial neural networks, a C5.0 classification tree and random forest algorithms. The optimization of ethanol production was also evaluated. The results clearly depict that ML techniques can be used to evaluate the SHF (R2 between actual and model predictions higher than 0.90, absolute average deviation lower than 8.1% and RMSE lower than 0.80) and predict optimized conditions which are in close agreement with those found experimentally. Optimal conditions were found to be a temperature of 35 ºC, an SHF time of 36 h, enzymatic load of 99.8%, inoculum size of 29.5 g/L and bagasse concentration of 24.9%. The ethanol concentration and volumetric productivity for these conditions were 12.1 g/L and 0.336 g/L.h, respectively. |
topic |
Lignocellulosic ethanol Machine learning Simultaneous hydrolysis and fermentation Crude enzyme complex |
url |
http://www.scielo.br/scielo.php?script=sci_arttext&pid=S0104-66322017000100053&lng=en&tlng=en |
work_keys_str_mv |
AT jfischer machinelearningtechniquesappliedtolignocellulosicethanolinsimultaneoushydrolysisandfermentation AT vslopes machinelearningtechniquesappliedtolignocellulosicethanolinsimultaneoushydrolysisandfermentation AT slcardoso machinelearningtechniquesappliedtolignocellulosicethanolinsimultaneoushydrolysisandfermentation AT ucoutinhofilho machinelearningtechniquesappliedtolignocellulosicethanolinsimultaneoushydrolysisandfermentation AT vlcardoso machinelearningtechniquesappliedtolignocellulosicethanolinsimultaneoushydrolysisandfermentation |
_version_ |
1725725915847065600 |