Machine Learning Strategies for Forecasting Mannosylerythritol Lipid Production Through Fermentation: A Proof-of-Concept
Fermentations are complex and often unpredictable processes. However, fermentation-based bioprocesses generate large volumes of data that are currently underexplored. These data can be used to develop data-driven models, such as machine learning (ML) models, to improve process predictability. Among...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-03-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/15/7/3709 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849730847488344064 |
|---|---|
| author | Carolina A. Vares Sofia P. Agostinho Ana L. N. Fred Nuno T. Faria Carlos A. V. Rodrigues |
| author_facet | Carolina A. Vares Sofia P. Agostinho Ana L. N. Fred Nuno T. Faria Carlos A. V. Rodrigues |
| author_sort | Carolina A. Vares |
| collection | DOAJ |
| description | Fermentations are complex and often unpredictable processes. However, fermentation-based bioprocesses generate large volumes of data that are currently underexplored. These data can be used to develop data-driven models, such as machine learning (ML) models, to improve process predictability. Among various fermentation products, biosurfactants have emerged as promising candidates for several industrial applications. Nevertheless, the large-scale production of biosurfactants is not yet cost-effective. This study aims to develop forecasting methods for the concentration of mannosylerythritol lipids (MELs), a type of biosurfactant, produced in <i>Moesziomyces</i> spp. cultivation. Three ML models, neural networks (NNs), support vector machines (SVMs), and random forests (RFs), were used. An NN provided predictions with a mean squared error (MSE) of 0.69 for day 4 and 1.63 for day 7 and a mean absolute error (MAE) of 0.58 g/L and 1.1 g/L, respectively. These results indicate that the model’s predictions are sufficiently accurate for practical use, with the MAE showing only minor deviations from the actual concentrations. Both results are promising, as they demonstrate the possibility of obtaining reliable predictions of the MEL production on days 4 and 7 of fermentation. This, in turn, could help reduce process-related costs, enhancing its economic viability. |
| format | Article |
| id | doaj-art-b0db309ca6b341d8a06d177499566e3c |
| institution | DOAJ |
| issn | 2076-3417 |
| language | English |
| publishDate | 2025-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj-art-b0db309ca6b341d8a06d177499566e3c2025-08-20T03:08:44ZengMDPI AGApplied Sciences2076-34172025-03-01157370910.3390/app15073709Machine Learning Strategies for Forecasting Mannosylerythritol Lipid Production Through Fermentation: A Proof-of-ConceptCarolina A. Vares0Sofia P. Agostinho1Ana L. N. Fred2Nuno T. Faria3Carlos A. V. Rodrigues4Department of Bioengineering, Instituto Superior Técnico, Universidade de Lisboa, Av. Rovisco Pais, 1049-001 Lisbon, PortugalDepartment of Bioengineering, Instituto Superior Técnico, Universidade de Lisboa, Av. Rovisco Pais, 1049-001 Lisbon, PortugalDepartment of Bioengineering, Instituto Superior Técnico, Universidade de Lisboa, Av. Rovisco Pais, 1049-001 Lisbon, PortugalDepartment of Bioengineering, Instituto Superior Técnico, Universidade de Lisboa, Av. Rovisco Pais, 1049-001 Lisbon, PortugalDepartment of Bioengineering, Instituto Superior Técnico, Universidade de Lisboa, Av. Rovisco Pais, 1049-001 Lisbon, PortugalFermentations are complex and often unpredictable processes. However, fermentation-based bioprocesses generate large volumes of data that are currently underexplored. These data can be used to develop data-driven models, such as machine learning (ML) models, to improve process predictability. Among various fermentation products, biosurfactants have emerged as promising candidates for several industrial applications. Nevertheless, the large-scale production of biosurfactants is not yet cost-effective. This study aims to develop forecasting methods for the concentration of mannosylerythritol lipids (MELs), a type of biosurfactant, produced in <i>Moesziomyces</i> spp. cultivation. Three ML models, neural networks (NNs), support vector machines (SVMs), and random forests (RFs), were used. An NN provided predictions with a mean squared error (MSE) of 0.69 for day 4 and 1.63 for day 7 and a mean absolute error (MAE) of 0.58 g/L and 1.1 g/L, respectively. These results indicate that the model’s predictions are sufficiently accurate for practical use, with the MAE showing only minor deviations from the actual concentrations. Both results are promising, as they demonstrate the possibility of obtaining reliable predictions of the MEL production on days 4 and 7 of fermentation. This, in turn, could help reduce process-related costs, enhancing its economic viability.https://www.mdpi.com/2076-3417/15/7/3709biosurfactantsupervised learningpredictionfeature engineeringneural networkrecursive feature elimination |
| spellingShingle | Carolina A. Vares Sofia P. Agostinho Ana L. N. Fred Nuno T. Faria Carlos A. V. Rodrigues Machine Learning Strategies for Forecasting Mannosylerythritol Lipid Production Through Fermentation: A Proof-of-Concept Applied Sciences biosurfactant supervised learning prediction feature engineering neural network recursive feature elimination |
| title | Machine Learning Strategies for Forecasting Mannosylerythritol Lipid Production Through Fermentation: A Proof-of-Concept |
| title_full | Machine Learning Strategies for Forecasting Mannosylerythritol Lipid Production Through Fermentation: A Proof-of-Concept |
| title_fullStr | Machine Learning Strategies for Forecasting Mannosylerythritol Lipid Production Through Fermentation: A Proof-of-Concept |
| title_full_unstemmed | Machine Learning Strategies for Forecasting Mannosylerythritol Lipid Production Through Fermentation: A Proof-of-Concept |
| title_short | Machine Learning Strategies for Forecasting Mannosylerythritol Lipid Production Through Fermentation: A Proof-of-Concept |
| title_sort | machine learning strategies for forecasting mannosylerythritol lipid production through fermentation a proof of concept |
| topic | biosurfactant supervised learning prediction feature engineering neural network recursive feature elimination |
| url | https://www.mdpi.com/2076-3417/15/7/3709 |
| work_keys_str_mv | AT carolinaavares machinelearningstrategiesforforecastingmannosylerythritollipidproductionthroughfermentationaproofofconcept AT sofiapagostinho machinelearningstrategiesforforecastingmannosylerythritollipidproductionthroughfermentationaproofofconcept AT analnfred machinelearningstrategiesforforecastingmannosylerythritollipidproductionthroughfermentationaproofofconcept AT nunotfaria machinelearningstrategiesforforecastingmannosylerythritollipidproductionthroughfermentationaproofofconcept AT carlosavrodrigues machinelearningstrategiesforforecastingmannosylerythritollipidproductionthroughfermentationaproofofconcept |