A Modelagem Preditiva por Aprendizado de Máquina para Otimização do Tratamento Terciário de Efluente Lácteo por Consórcio Microalga-Fungo
Palabras clave:
machine learning, tratamento biológico, modelagem cinética, consorcio microbiano, Tetradesmus obliquus, Cunninghamella echinulataResumen
Este estudo avaliou o tratamento terciário do soro de leite utilizando um consórcio microalga-fungo em batelada. Foram analisadas relações DQO:NT (20, 30, 40 e 50), com monitoramento de biomassa, DQO, NT e FT residuais e o lodo de tratamento formado. Adicionalmente, técnicas de aprendizado de máquina foram aplicadas para prever as variáveis de saída (DQOresidual, NTresidual, FTresidual e biomassa) a partir de variáveis de entrada (relação DQO:NT e tempo de tratamento). Os resultados indicaram que a Regressão Linear Múltipla apresentou robustez para aplicação imediata, enquanto o Random Forest demonstrou maior capacidade de ajuste com R2 de teste de até 0.9839. Modelos lineares como Multiple, Ridge, and LASSO mostraram-se mais limitados (R2 de teste entre 0,50-0,74) confirmando a natureza não linear do processo. A integração entre modelagem matemática clássica e Machine Learning mostrou-se promissora para o controle de biorreatores.
Citas
American Public Health Association (APHA), American Water Works Association (AWWA), & Water Environment Federation (WEF). (1999). Standard Methods for the Examination of Water and Wastewater (20th ed.). Washington, D.C.: APHA.
AOAC. (2002). Official Methods of Analysis (16th ed.). Washington, DC: Association of Official Agricultural Chemists.
Arshad, U., Hassan, A., Ahmad, T., Naeem, M., Chaudhary, M. T., Abbas, S. Q., Randhawa, M. A., Pimentel, T. C., Da Cruz, A. G., & Aadil, R. M. (2022). A recent glance on the valorisation of cheese whey for industrial prerogative: high-value-added products development and integrated reutilising strategies. International Journal of Food Science and Technology, 58, 2001–2013.
Bella, K., & Rao, P. V. (2021). Anaerobic digestion of dairy wastewater: Effect of different parameters and co-digestion options – a review. Biomass Conversion and Biorefinery, 13, 2527–2552.
Bentahar, J., Doyen, A., Beaulieu, L., & Deschênes, J. (2019). Acid whey permeate: An alternative growth medium for microalgae Tetradesmus obliquus and production of β-galactosidase. Algal Research, 41, 101559. https://doi.org/10.1016/j.algal.2019.101559
Borzani, W., Schmidell Netto, W., Lima, U. A., & Aquarone, E. (2001). Biotecnologia Industrial: Engenharia Bioquímica (Vol. 2). São Paulo: Edgard Blücher.
Catelan, T. C., Pinotti, L. M., & Soares, V. B. (2021). Use of non-linear empirical models to predict the substrate degradation, enzymatic activity and cell growth in a bioreactor with Aspergillus niger and sugarcane bagasse. Waste and Biomass Valorization. https://doi.org/10.1007/s12649-020-01337-2
Fisher, O. J., et al. (2022). Data-driven modelling for resource recovery: Data volume, variability, and visualisation for an industrial bioprocess. Biochemical Engineering Journal, 185, 108499.
Fu, L., et al. (2019). Hormesis effects of phosphorus on the viability of Chlorella regularis cells under nitrogen limitation. Biotechnology for Biofuels, 12(1), 121. https://doi.org/10.1186/s13068-019-1450-3
Gaden, E. L. Jr. (1955). Fermentation kinetics and productivity. Chemistry and Industry, 12, 1955.
Hossain, S. M. Z., et al. (2022). Hybrid support vector regression and crow search algorithm for modeling and multiobjective optimization of microalgae-based wastewater treatment. Journal of Environmental Management, 301, 113783.
Medeiros, A. J., Silva, C. E. F., Santos, G. K. S., Nascimento, M. A. A., Andrade, F. P., Sá Filho, M. L. F., & Garcia Almeida, R. M. R. (2024). Tertiary treatment of dairy wastewater applying a microalga-fungus consortium. Environmental Technology, 1–17. https://doi.org/10.1080/09593330.2024.2357695
Melkumova, L. E., & Shatskikh, S. Y. (2017). Comparing Ridge and LASSO estimators for data analysis. Procedia Engineering, 201, 746–755.
Monod, J. (1949). The growth of bacterial cultures. Annual Review of Microbiology, 3, 371–394.
Pedregosa, F., et al. (2011). Scikit-learn: Machine Learning in Python. Journal of Machine Learning Research, 12(85), 2825–2830.
Price, G. A. V., et al. (2023). Development and validation of multiple linear regression models for predicting chronic zinc toxicity to freshwater microalgae. Environmental Toxicology and Chemistry, 42(12), 2630–2641.
Wang, M., Kuo-Dahab, W. C., Dalan, S., & Park, C. (2014). Nutrient removal kinetics and extracellular polymeric substances expression of microalgae Chlorella sp. and Microctinium sp. in wastewater treatment. Bioresource Technology, 154, 131–137.
Zhou, Q., Sun, H., Jia, L., Wu, W., & Wang, J. (2022). Simultaneous biological removal of nitrogen and phosphorus from secondary effluent of wastewater treatment plants by advanced treatment: A review. Chemosphere, 296, 134054.
Lokman, A., Ismail, W. Z. W., & Aziz, N. A. A. (2025). A Review of Water Quality Forecasting and Classification Using Machine Learning Models and Statistical Analysis. Water, 17(15), 2243. https://doi.org/10.3390/w17152243
Saleem, M. A., Harrou, F., & Sun, Y. (2024). Explainable machine learning methods for predicting water treatment plant features under varying weather conditions. Results in Engineering, 21, 101930. https://doi.org/10.1016/j.rineng.2024.101930
Wang, Y., Cheng, Y., Liu, H., Guo, Q., Dai, C., Zhao, M., & Liu, D. (2023). A Review on Applications of Artificial Intelligence in Wastewater Treatment. Sustainability, 15(18), 13557. https://doi.org/10.3390/su151813557
Jin, X., Guo, W., Shi, T., & Wang, Z. (2025). Machine learning-based prediction and optimization of biomass pellet strength for sustainable bioenergy production. Industrial Crops and Products, 234, 121498. https://doi.org/10.1016/j.indcrop.2025.121498
Devi, P., Kanwal, S., Ahmed, Z., Rizwan, M., & Khan, S. (2025). Arsenic removal from water using marble powder waste: A comprehensive study on adsorption dynamics and machine learning predictions. Desalination and Water Treatment, 321, 100912. https://doi.org/10.1016/j.dwt.2024.100912
K.N., R., Y., R. R., Kumar G, S., & Hk, R. (2025). Predictive modelling of mechanical properties of concrete using machine learning with secondary treated waste water and fly ash. Cleaner Waste Systems, 11, 100296. https://doi.org/10.1016/j.clwas.2025.100296
Yavari, K., Karami, C., Bijari, S., Adami, D., & Shahavi, M. H. (2025). Removal of amoxicillin from hospital waste using fe2o3-ag adsorbent and optimization by response surface methodology and machine learning prediction. Current Research in Green and Sustainable Chemistry, 100483. https://doi.org/10.1016/j.crgsc.2025.100483
Descargas
Publicado
Número
Sección
Licencia
Derechos de autor 2026 Micaela Almeida Nascimento, João Victor Ferro, Wanderson dos Santos Carneiro, Carlos Eduardo de Farias Silva, João Victor Oliveira Nascimento Da Silva
Esta obra está bajo una licencia internacional Creative Commons Atribución-NoComercial-SinDerivadas 4.0.
Authors who publish in the Annals of Data Analysis retain
the copyright of their work and agree to license it under a Creative Commons Attribution-
NonCommercial-NoDerivatives 4.0 International (CC BY-NC-ND 4.0) license.
