Predicting the total suspended solids in wastewater: A data-mining approach

Total suspended solids (TSS) are a major pollutant that affects waterways all over the world. Predicting the values of TSS is of interest to quality control of wastewater processing. Due to infrequent measurements, time series data for TSS are constructed using influent flow rate and influent carbonaceous bio-chemical oxygen demand (CBOD). We investigated different scenarios of daily average influent CBOD and influent flow rate measured at 15 min intervals. Then, we used five data-mining algorithms, i.e., multi-layered perceptron, k-nearest neighbor, multi-variate adaptive regression spline, support vector machine, and random forest, to construct day-ahead, time-series prediction models for TSS. Historical TSS values were used as input parameters to predict current and future values of TSS. A sliding-window approach was used to improve the results of the predictions.