21 Jun 2018

New Scientific Paper on Sewer Failure Prediction Featured in Top Journal

We are pleased to announce that our most recent paper, "Analyzing the Importance of Variables for Sewer Failure Prediction", was selected to appear in the Urban Water Journal, a top international peer-reviewed publication.

When defining the variables to predict sewer failure and therefore optimize sewer systems maintenance, it is important to identify the ones that most significantly influence the quality of the predictions or to define the smallest number of variables that is sufficient to obtain accurate prediction. In our study, three statistical variable selection algorithms were tested: the mutual information indicator, the out-of-bag samples concept (based on the random forest algorithm), and the stepwise search approach.

To find out the results of our study and review our paper in its entirety, please visit our publications page.