Comparison of adaptive neuro-fuzzy inference systems (ANFIS) and support vector regression (SVR) for data-driven modelling of aerobic granular sludge reactors

Abstract Maintaining stable operation of aerobic granular sludge (AGS) reactors is a challenge due to the high sensitivity of the biomass to a wide array of parameters, and the frequent changes in influent characteristics. The application of artificial intelligence in AGS modelling has shown promising results but is still at its early stages. This work investigated, for the first time, the capabilities of two artificial intelligence algorithms for the development of predictive models for AGS reactors based on influent characteristics and operational conditions: adaptive neuro-fuzzy inference system (ANFIS), and support vector regression (SVR). The model structure adopted a two-stage modular approach. The models predicted the performance of the reactors for the unseen data with an average R2, nRMSE, sMAPE, and MASE of 91 %, 0.21, 0.06, and 0.22 for ANFIS, and 99 %, 0.07, 0.006, and 0.01 for SVR. The results showed that SVR provides more accurate predictions than ANFIS, in terms of prediction errors, and correctly predicting different types of failures. However, ANFIS provided better generalization ability than SVR. The results of this study showed the potential of artificial intelligence for the development of predictive models for the AGS process and provided insight into the selection of the appropriate algorithms for these models.

[1]  Shahidan M. Abdullah,et al.  Advantage and drawback of support vector machine functionality , 2014, 2014 International Conference on Computer, Communications, and Control Technology (I4CT).

[2]  J. Tay,et al.  Aerobic granulation for future wastewater treatment technology: challenges ahead , 2018 .

[3]  Xiupeng Wei,et al.  Modeling and optimization of wastewater treatment process with a data-driven approach , 2013 .

[4]  N. Wahab,et al.  Dynamic modelling of aerobic granular sludge artificial neural networks , 2017 .

[5]  Cristian Picioreanu,et al.  Multi-scale individual-based model of microbial and bioconversion dynamics in aerobic granular sludge. , 2007, Environmental science & technology.

[6]  Oliver Terna Iorhemen,et al.  Performance prediction of an aerobic granular SBR using modular multilayer artificial neural networks. , 2018, The Science of the total environment.

[7]  Jianxu Luo,et al.  Prediction of Effluent Parameters of Wastewater Treatment Plant Based on Improved Least Square Support Vector Machine with PSO , 2009, 2009 First International Conference on Information Science and Engineering.

[8]  Vladimir N. Vapnik,et al.  The Nature of Statistical Learning Theory , 2000, Statistics for Engineering and Information Science.

[9]  Wen-hong Pu,et al.  Rapid cultivation of aerobic granular sludge in a pilot scale sequencing batch reactor. , 2014, Bioresource technology.

[10]  Rob J Hyndman,et al.  Another look at measures of forecast accuracy , 2006 .

[11]  Rui Zhang,et al.  Simulation and optimization of a full-scale Carrousel oxidation ditch plant for municipal wastewater treatment , 2011 .

[12]  Hare Krishna Mohanta,et al.  Soft sensing of particle size in a grinding process: Application of support vector regression, fuzzy inference and adaptive neuro fuzzy inference techniques for online monitoring of cement fineness , 2014 .

[13]  S. Okabe,et al.  Effects of dissolved oxygen and pH on nitrous oxide production rates in autotrophic partial nitrification granules. , 2015, Bioresource technology.

[14]  Karim Djouani,et al.  Fuzzy dynamic modelling and predictive control of a coagulation chemical dosing unit for water treatment plants , 2014 .

[15]  Ji-Hoon Kim,et al.  Real-time remote monitoring of small-scaled biological wastewater treatment plants by a multivariate statistical process control and neural network-based software sensors , 2008 .

[16]  J. Tay,et al.  Effects of hydraulic retention time on aerobic granulation and granule growth kinetics at steady state with a fast start-up strategy , 2015, Applied Microbiology and Biotechnology.

[17]  J. Tay,et al.  Artificial neural network modelling for organic and total nitrogen removal of aerobic granulation under steady-state condition , 2019, Environmental technology.

[18]  Maged M. Hamed,et al.  Prediction of wastewater treatment plant performance using artificial neural networks , 2004, Environ. Model. Softw..

[19]  Lluís Corominas,et al.  Transforming data into knowledge for improved wastewater treatment operation: A critical review of techniques , 2017, Environ. Model. Softw..

[20]  Liang Zhu,et al.  Optimization of F/M ratio for stability of aerobic granular process via quantitative sludge discharge. , 2018, Bioresource technology.

[21]  N. Wahab,et al.  Aerobic sludge granulation at high temperatures for domestic wastewater treatment. , 2015, Bioresource technology.

[22]  M. Hermansson,et al.  The mechanisms of granulation of activated sludge in wastewater treatment, its optimization, and impact on effluent quality , 2018, Applied Microbiology and Biotechnology.

[23]  Hanqing Yu,et al.  Modeling and optimization of granulation process of activated sludge in sequencing batch reactors , 2013, Biotechnology and bioengineering.

[24]  A. E. Greenberg,et al.  Standard methods for the examination of water and wastewater : supplement to the sixteenth edition , 1988 .

[25]  F. Rogalla,et al.  Influence of dissolved oxygen concentration on the start-up of the anammox-based process: ELAN®. , 2015, Water science and technology : a journal of the International Association on Water Pollution Research.

[26]  Jyh-Shing Roger Jang,et al.  ANFIS: adaptive-network-based fuzzy inference system , 1993, IEEE Trans. Syst. Man Cybern..

[27]  J. Tay,et al.  Aerobic granular sludge: recent advances. , 2008, Biotechnology advances.

[28]  Hanqing Yu,et al.  Mathematical modeling of aerobic granular sludge: a review. , 2010, Biotechnology advances.

[29]  Oscar Castillo,et al.  A new approach for time series prediction using ensembles of ANFIS models with interval type-2 and type-1 fuzzy integrators , 2013, 2013 IEEE Conference on Computational Intelligence for Financial Engineering & Economics (CIFEr).

[30]  Samarjit Kar,et al.  Applications of neuro fuzzy systems: A brief review and future outline , 2014, Appl. Soft Comput..

[31]  M. V. van Loosdrecht,et al.  Stability of aerobic granules during long-term bioreactor operation. , 2017, Biotechnology advances.

[32]  H. Horn,et al.  Aerobic Sludge Granulation in a Full-Scale Sequencing Batch Reactor , 2014, BioMed research international.

[33]  O. T. Iorhemen,et al.  Rapid formation and characterization of aerobic granules in pilot-scale sequential batch reactor for high-strength organic wastewater treatment , 2018 .

[34]  Chandra Shekhar P. Ojha,et al.  Estimation of Scour Downstream of a Ski-Jump Bucket Using Support Vector and M5 Model Tree , 2011 .

[35]  Y. Nancharaiah,et al.  Aerobic granular sludge technology: Mechanisms of granulation and biotechnological applications. , 2018, Bioresource technology.

[36]  J. Tay,et al.  Fast formation of aerobic granules by combining strong hydraulic selection pressure with overstressed organic loading rate. , 2015, Water research.

[37]  Zhong-lin Chen,et al.  Performance of aerobic granular sludge in different bioreactors , 2014, Environmental technology.

[38]  P. Mondal,et al.  Aerobic granulation for wastewater bioremediation: A review , 2013 .

[39]  Munir Ahmed,et al.  Sequential treatment of paper and pulp industrial wastewater: Prediction of water quality parameters by Mamdani Fuzzy Logic model and phytotoxicity assessment. , 2019, Chemosphere.

[40]  Mohamed Gamal El-Din,et al.  Application of artificial neural networks in wastewater treatment , 2004 .

[41]  J. Shayegan,et al.  Effect of pH on Aerobic Granulation and Treatment Performance in Sequencing Batch Reactors , 2015 .

[42]  Bernhard Schölkopf,et al.  A tutorial on support vector regression , 2004, Stat. Comput..

[43]  Rajib Maity,et al.  Potential of support vector regression for prediction of monthly streamflow using endogenous property , 2010 .

[44]  Joo-Hwa Tay,et al.  Neural fuzzy modeling of anaerobic biological wastewater treatment systems , 1999 .

[45]  G. Viviani,et al.  Aerobic granular sludge treating high strength citrus wastewater: Analysis of pH and organic loading rate effect on kinetics, performance and stability. , 2018, Journal of environmental management.

[46]  D. T. Lee,et al.  Travel-time prediction with support vector regression , 2004, IEEE Transactions on Intelligent Transportation Systems.

[47]  F. Tsai,et al.  Prediction of effluent quality parameters of a wastewater treatment plant using a supervised committee fuzzy logic model , 2018 .

[48]  Spyros Makridakis,et al.  Accuracy measures: theoretical and practical concerns☆ , 1993 .

[49]  J. Tay,et al.  Characteristics of Aerobic Granules Grown on Glucose and Acetate in Sequential Aerobic Sludge Blanket Reactors , 2002, Environmental technology.

[50]  S. Wuertz,et al.  Support vector regression model of wastewater bioreactor performance using microbial community diversity indices: effect of stress and bioaugmentation. , 2014, Water research.

[51]  Mohd Alauddin Mohd Ali,et al.  Comparison of adaptive neuro-fuzzy inference system and artificial neutral networks model to categorize patients in the emergency department , 2013, SpringerPlus.

[52]  J. Garibaldi,et al.  A new accuracy measure based on bounded relative error for time series forecasting , 2017, PloS one.

[53]  R. Méndez,et al.  Effects of Inoculum Type and Aeration Flowrate on the Performance of Aerobic Granular SBRs , 2017 .

[54]  Oskar Modin,et al.  Microbial Population Dynamics and Ecosystem Functions of Anoxic/Aerobic Granular Sludge in Sequencing Batch Reactors Operated at Different Organic Loading Rates , 2017, Front. Microbiol..

[55]  Dawei Han,et al.  Flood forecasting using support vector machines , 2007 .

[56]  Jan Adamowski,et al.  Modeling of daily pan evaporation in sub tropical climates using ANN, LS-SVR, Fuzzy Logic, and ANFIS , 2014, Expert Syst. Appl..

[57]  J. Tay,et al.  Finding Knowledge Gaps in Aerobic Granulation Technology. , 2017, Trends in biotechnology.