Detecting Industrial Chemicals in Water With Microbial Fuel Cells and Artificial Neural Networks

Water quality monitoring is critically important in efforts to both limit human exposure to toxic chemicals and to protect ecosystems. This study integrates artificial neural network (ANN) processing with MFC-based biosensing in the detection of three organic pollutants that have relevance to DoD operations: aldicarb, dimethyl-methylphosphonate (DMMP), and bisphenol-A (BPA). Overall, the use of the ANN proved to be more reliable than direct correlations with raw data in the prediction of both chemical concentration and type. The ANN made no errors in the identification and quantification of all chemicals in three concentration ranges. Additionally, chemical mixtures and chemicals dissolved in the standard feed medium were accurately identified by the ANN. Finally, the newly-tested metrics of 10-hour Subsidence Rate (10SR) and First Moment (FrM) proved to be useful in ANN development. This study is the first to incorporate ANN modeling with MFC-based biosensing for the detection and quantification of organic pollutants that are not readily biodegradable. It is also the first to evaluate the utility of 10-hr SR and FM as metrics. Furthermore, this work provides insight into MFC-based biosensing as it pertains to limits of detection and its applicability to scenarios where mixtures of pollutants and unique solvents are involved