Abstract
Biosurfactants are molecules with wide application in several industrial processes. Their production is damaged due to inefficient bioprocessing and expensive substrates. The latest developments of strategies to improve and economize the biosurfactant production process use alternative substrates, optimization techniques, and different scales. This paper presents a study to compare the performances of classical (polynomial models) and modern tools, such as artificial intelligence to aid optimization of the alternative substrate concentration (alternative based on beet peel and glycerol) and process parameters (agitation and aeration). The evaluation was developed in two different scales: Erlenmeyer flask (100 mL) and bioreactor (7 L). The intelligent models were implemented to verify the ability to predict the emulsification index and biosurfactant concentration in smaller scale and the biosurfactant concentration and the superficial tension reduction (STR) in bigger scale, resulting in four different situations. The overall results of the predictions led to artificial neural networks as the best performing modeling tool in all four situations studied, with R2 values ranging from 0.9609 to 0.9974 and error indices close to 0. Also, four different models (Wu, Contois, Megee, and Ghose-Tyagi) were adjusted by particle swarm optimization (PSO) in order to describe the kinetics of biosurfactant production. Contois model was the only one to present R2 ≥ 0.97 for all monitored variables. The findings described in this work present an adjusted model for the prediction of biosurfactant production and also state that the most adjusted kinetic model for further studies on this process is Contois model, leading to the conclusion that biomass growth is limited by a single substrate, considering only glucose.
Similar content being viewed by others
Data availability
All data and materials as well as software application or custom code support this paper’s published claims and comply with field standards.
Abbreviations
- \({EH}_{24h}\) :
-
Emulsification height after 24 h
- \({EH}_{0h}\) :
-
Emulsification height at time zero
- \(E\) :
-
Emulsification index
- \(BC\) :
-
Biosurfactant concentration
- \(STR\) :
-
Superficial tension reduction
- \(v\) :
-
Particle’s velocity
- \(p\) :
-
Particle’s position
- \(iw\) :
-
Inertia weight
- \({c}_{gk}\) :
-
Global learning coefficient
- \({c}_{pk}\) :
-
Personal learning coefficient
- \(K1\) :
-
Kinetic constant for glucose
- \(K1a\) :
-
Kinetic constant for oxygen
- \(Yxg\) :
-
Theoretical yield in terms of biomass
- \(t\) :
-
Time (h)
- \(X\) :
-
Biomass concentration (g L−1)
- \(S\) :
-
Substrate concentration (g L−1)
- \({S}_{c}\) :
-
Sucrose concentration (g L−1)
- \(P\) :
-
Product concentration (g L−1)
- \({P}_{\mathrm{max}}\) :
-
Maximum product concentration (g L−1)
- \({C}_{{\mathrm{O}}_{2}}\) :
-
Oxygen concentration (g L−1)
- \({C}_{{\mathrm{O}}_{{2}_{S}}}\) :
-
Saturated oxygen concentration (g L−1)
- \({K}_{S} e {K}_{S}^{^{\prime}}\) :
-
Saturation constant (g L−1)
- \({K}_{P} e {K}_{P}^{^{\prime}}\) :
-
Inhibition constant per product (g L−1)
- \({K}_{X} e {K}_{X}^{^{\prime}}\) :
-
Inhibition constant by biomass (g L−1)
- \({K}_{{O}_{2}}\) :
-
Oxygen saturation constant (g L−1)
- \({K}_{i}\) :
-
Substrate inhibition constant (g L−1)
- \({k}_{1}\), \({k}_{2}\), \({k}_{3}\) :
-
Kinetic constants (variable units)
- \(N, n, m, k\) :
-
Kinetic parameters (dimensionless)
- \({m}_{S}\) :
-
Maintenance coefficient for the substrate (g L−1 or h−1)
- \({\mu }_{S}\) :
-
Specific substrate consumption speed (h−1)
- \({\mu }_{x}\) :
-
Specific speed of microbial growth (h−1)
- \({\mu }_{m}\) :
-
Specific speed of microbial growth (h−1)
- \(\gamma\) :
-
Specific product formation speed (h−1)
- \({\gamma }_{m}\) :
-
Specific product formation maximum speed (h−1)
- \({\mu }_{{\mathrm{O}}_{2}}\) :
-
Specific breathing speed (h−1)
- \({\mu }_{{m}_{{\mathrm{O}}_{2}}}\) :
-
Specific maximum breathing speed (h−1)
- \({Q}_{{\mathrm{O}}_{2}}\) :
-
Specific respiration rate (\({g}_{{O}_{2}}{g}_{\mathrm{cells}}^{- 1}{h}^{-1}\))
- \({m}_{O}\) :
-
Maintenance coefficient for \({O}_{2} ({g}_{{O}_{2}}{g}_{\mathrm{cells}}^{-1}{h}^{-1}\))
- \({Y}_{O}\) :
-
Conversion factor from \({O}_{2}\) to cells (\({g}_{{O}_{2}}{g}_{\mathrm{cells}}^{- 1}\))
- \({k}_{L}a\) :
-
Volumetric transfer coefficient of \({O}_{2}\) (h−1)
- \({Y}_{X/S}\) :
-
Theoretical biomass yield (dimensionless)
- \({Y}_{P/S}\) :
-
Theoretical product yield (dimensionless)
References
Abiodun OI, Jantan A, Omolara AE, Dada KV, Mohamed NA, Arshad H (2018) State-of-the-art in artificial neural network applications: A survey. Heliyon 23;4(11):e00938. https://doi.org/10.1016/j.heliyon.2018.e00938
Ahmad Z, Crowley D, Marina N, Jha SK (2016) Estimation of biosurfactant yield produced by Klebseilla sp. FKOD36 bacteria using artificial neural network approach. Meas: J Int Meas Confed 81:163–173. https://doi.org/10.1016/j.measurement.2015.12.019
Akbari S, Abdurahman NH, Yunus RM et al (2018) Biosurfactants—a new frontier for social and environmental safety: a mini review. Biotechnol Res Innov 2:81–90
Bezerra MA, Santelli RE, Oliveira EP et al (2008) Response surface methodology (RSM) as a tool for optimization in analytical chemistry. Talanta 76:965–977. https://doi.org/10.1016/j.talanta.2008.05.019
Bharathi Raja S, Baskar N (2011) Particle swarm optimization technique for determining optimal machining parameters of different work piece materials in turning operation. Int J Adv Manuf Technol 54:445–463. https://doi.org/10.1007/s00170-010-2958-y
Boelaert J, Ollion É (2018) The Great Regression: machine learning, econometrics, and the future of quantitative social sciences. Rev Fr Sociol 59:475. https://doi.org/10.3917/rfs.593.0475
Boveiri Shami R, Shojaei V, Khoshdast H (2019) Efficient cadmium removal from aqueous solutions using a sample coal waste activated by rhamnolipid biosurfactant. J Environ Manage 231:1182–1192. https://doi.org/10.1016/j.jenvman.2018.03.126
CONTOIS DE (1959) Kinetics of bacterial growth: relationship between population density and specific growth rate of continuous cultures. J Gen Microbiol 21:40–50. https://doi.org/10.1099/00221287-21-1-40
Derguine-Mecheri L, Kebbouche-Gana S, Khemili-Talbi S, Djenane D (2018) Screening and biosurfactant/bioemulsifier production from a high-salt-tolerant halophilic Cryptococcus strain YLF isolated from crude oil. J Petrol Sci Eng 162:712–724. https://doi.org/10.1016/j.petrol.2017.10.088
Ebadi MJ, Hosseini A, Hosseini MM (2017) A projection type steepest descent neural network for solving a class of nonsmooth optimization problems. Neurocomputing 235:164–181. https://doi.org/10.1016/J.NEUCOM.2017.01.010
Ebrahimzade H, Khayati GR, Schaffie M (2020) PSO–ANN-based prediction of cobalt leaching rate from waste lithium-ion batteries. J Mater Cycles Waste Manage 22:228–239. https://doi.org/10.1007/s10163-019-00933-2
Fouladi S, Ebadi MJ, Safaei AA et al (2021) Efficient deep neural networks for classification of COVID-19 based on CT images: virtualization via software defined radio. Comput Commun 176:234–248. https://doi.org/10.1016/J.COMCOM.2021.06.011
Ghazala I, Bouassida M, Krichen F et al (2017) Anionic lipopeptides from Bacillus mojavensis I4 as effective antihypertensive agents: production, characterization, and identification. Eng Life Sci 17:1244–1253. https://doi.org/10.1002/elsc.201700020
Ghose TK, Tyagi RD (1979) Rapid ethanol fermentation of cellulose hydrolysate. II. Product and substrate inhibition and optimization of fermentor design. Biotechnol Bioeng 21:1401–1420. https://doi.org/10.1002/bit.260210808
Hadia NJ, Ottenheim C, Li S et al (2019) Experimental investigation of biosurfactant mixtures of surfactin produced by Bacillus Subtilis for EOR application. Fuel 251:789–799. https://doi.org/10.1016/j.fuel.2019.03.111
Hema T, Seghal Kiran G, Sajayyan A, et al (2019) Response surface optimization of a glycolipid biosurfactant produced by a sponge associated marine bacterium Planococcus sp. MMD26. Biocatal Agric Biotechnol 18:101071. https://doi.org/10.1016/j.bcab.2019.101071
Hornik K, Stinchcombe M, White H (1989) Multilayer feedforward networks are universal approximators. Neural Netw 2:359–366. https://doi.org/10.1016/0893-6080(89)90020-8
Hornik K, Stinchcombe M, White H (1990) Universal approximation of an unknown mapping and its derivatives using multilayer feedforward networks. Neurul Networks< 3:551
Kennedy J, Eberhart R (1995) Particle swarm optimization, Proceedings of IEEE International Conference on Neural Networks Vol. IV: 1942–1948. In: Neural Networks
MATLAB Statistics and Machine Learning Toolbox (2019a) The Mathworks Inc., Natick, Massachusetts, United States of America
Megee RD, Drake JF, Fredrickson AG, Tsuchiya HM (1972) Studies in intermicrobial symbiosis. Saccharomyces cerevisiae and Lactobacillus casei. Can J Microbiol 18:1733–1742. https://doi.org/10.1139/m72-269
Mouafi FE, Abo Elsoud MM, Moharam ME (2016) Optimization of biosurfactant production by Bacillus brevis using response surface methodology. Biotechnology Reports 9:31–37. https://doi.org/10.1016/j.btre.2015.12.003
Naveen Babu K, Karthikeyan R, Punitha A (2019) An integrated ANN-PSO approach to optimize the material removal rate and surface roughness of wire cut EDM on INCONEL 750. Materials Today: Proceedings 19:501–505. https://doi.org/10.1016/j.matpr.2019.07.643
Neboh HA, Abu GO, Uyigue L (2016) Utilization of agro-industrial wastes as substrates for. IIARD International Journal of Environmental Research 2:40–47
Ni’matuzahroh, Sari SK, Trikurniadewi N, et al (2020) Bioconversion of agricultural waste hydrolysate from lignocellulolytic mold into biosurfactant by Achromobacter sp. BP (1)5. Biocatal Agric Biotechnol 24:101534. https://doi.org/10.1016/j.bcab.2020.101534
Noori R, Khakpour A, Omidvar B, Farokhnia A (2010) Comparison of ANN and principal component analysis-multivariate linear regression models for predicting the river flow based on developed discrepancy ratio statistic. Expert Syst Appl 37:5856–5862. https://doi.org/10.1016/J.ESWA.2010.02.020
Noori R, Karbassi AR, Mehdizadeh H et al (2011) A framework development for predicting the longitudinal dispersion coefficient in natural streams using an artificial neural network. Environ Prog Sustainable Energy 30:439–449. https://doi.org/10.1002/EP.10478
Patel KA, Brahmbhatt PK (2016) A comparative study of the RSM and ANN models for predicting surface roughness in roller burnishing. Procedia Technol 23:391–397. https://doi.org/10.1016/j.protcy.2016.03.042
Pi Y, Bao M, Liu Y et al (2017) The contribution of chemical dispersants and biosurfactants on crude oil biodegradation by Pseudomonas sp. LSH-7′. J Clean Prod 153:74–82. https://doi.org/10.1016/j.jclepro.2017.03.120
Poznyak A, Chairez I, Poznyak T (2019) A survey on artificial neural networks application for identification and control in environmental engineering: Biological and chemical systems with uncertain models. Annu Rev Control 48:250–272. https://doi.org/10.1016/j.arcontrol.2019.07.003
Prado AAOS, Santos BLP, Vieira IMM et al (2019) Evaluation of a new strategy in the elaboration of culture media to produce surfactin from hemicellulosic corncob liquor. Biotechnology Reports 24:e00364. https://doi.org/10.1016/j.btre.2019.e00364
Santos BF, Ponezi AN, Fileti AMF (2014) Strategy of using waste for biosurfactant production through fermentation by bacillus subtilis. Chem Eng Trans 37:727–732. https://doi.org/10.3303/CET1437122
Silva R de CFS, Almeida DG, Rufino RD, et al (2014) Applications of biosurfactants in the petroleum industry and the remediation of oil spills. Int J Mol Sci 15:12523-12542https://doi.org/10.3390/ijms150712523
Sivapathasekaran C, Sen R (2013) Performance evaluation of an ANN-GA aided experimental modeling and optimization procedure for enhanced synthesis of marine biosurfactant in a stirred tank reactor. J Chem Technol Biotechnol 88:794–799. https://doi.org/10.1002/jctb.3900
Valenzuela-Ávila L, Miliar Y, Moya-Ramírez I et al (2020) Effect of emulsification and hydrolysis pretreatments of waste frying oil on surfactin production. J Chem Technol Biotechnol 95:223–231. https://doi.org/10.1002/jctb.6225
Vera ECS, de Azevedo PO de S, Domínguez JM, Oliveira RP de S (2018) Optimization of biosurfactant and bacteriocin-like inhibitory substance (BLIS) production by Lactococcus lactis CECT-4434 from agroindustrial waste. Biochem Eng J 133:168-178https://doi.org/10.1016/j.bej.2018.02.011
Watsuntorn W, Khanongnuch R, Chulalaksananukul W et al (2020) Resilient performance of an anoxic biotrickling filter for hydrogen sulphide removal from a biogas mimic: steady, transient state and neural network evaluation. J Clean Prod 249:119351. https://doi.org/10.1016/j.jclepro.2019.119351
Wu YC, Hao OJ, Ou KC, Scholze RJ (1988) Treatment of leachate from a solid waste landfill site using a two-stage anaerobic filter. Biotechnol Bioeng 31:257–266. https://doi.org/10.1002/bit.260310312
Wu Q, Zhi Y, Xu Y (2019) Systematically engineering the biosynthesis of a green biosurfactant surfactin by Bacillus subtilis 168. Metab Eng 52:87–97. https://doi.org/10.1016/j.ymben.2018.11.004
Funding
The authors received financial support from the CNPq/MCT, CAPES, FAPERJ, and FINEP for the Department of Chemical and Material Engineering (DEQM) at the Pontifical Catholic University of Rio de Janeiro (PUC-Rio).
Author information
Authors and Affiliations
Contributions
All authors contributed to the study conception and design. Material preparation, data collection, and analysis were performed by Rodrigo de A. Bustamante, Juan S. de Oliveira, and Brunno F. Santos. The first draft of the manuscript was written by Rodrigo de A. Bustamante, and all authors commented on previous versions of the manuscript. All authors read and approved the final manuscript.
Corresponding author
Ethics declarations
Ethical approval
Not applicable.
Consent to participate
All authors consent to participate.
Consent for publication
All authors consent to publish.
Competing interests
The authors declare no competing interests.
Additional information
Responsible Editor: Marcus Schulz
Publisher's note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
de Andrade Bustamante, R., de Oliveira, J.S. & dos Santos, B.F. Modeling biosurfactant production from agroindustrial residues by neural networks and polynomial models adjusted by particle swarm optimization. Environ Sci Pollut Res 30, 6466–6491 (2023). https://doi.org/10.1007/s11356-022-22481-3
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11356-022-22481-3