Data Driven Models as A Powerful Tool to Simulate Emerging Bioprocesses: An Artificial Neural Network Model to Describe Methanotrophic Microbial Activity

The vision for sewage treatment plants is being revised and they are no longer considered as pollutant removing facilities but rather water resources recovery (WRRFs). However, the newly adopted bioprocesses in WRRFs not fully understood from microbiological kinetic perspectives. Thus, large variations outputs of kinetics-based numerical models evident. In this research, data driven (DDM) proposed a robust alternative towards modelling emerging bioprocesses. Methano- trophs multi-use bacterium that can play key role revalorizing biogas WRRFs, thus, Multi-Layer Perceptron Artificial Neural Network (ANN) model was developed optimized to simulate cultivation mixed methanotrophic culture considering multiple environmental conditions. influence input variables on assessed through developing analyzing several different ANN configurations. constructed demonstrate indirect complex relationships between inputs be accurately prior full understanding physical or mathematical processes. Furthermore, it found used better understand rank (i.e., parameters methanotrophs) microbial activity. Methanotrophic-based due interactions gaseous, liquid solid phases. Yet, first time, study successfully utilized DDM methanotrophic-based findings research suggest powerful, modeling tool their implementation WRRFs.