Infilling missing data and outliers for a conventional sewage treatment plant using a self-organizing map: a case study of Kauma Sewage Treatment Plant in Lilongwe, Malawi

Abstract Data availability is key for modeling of wastewater treatment processes. However, process data are characterized by missing values and outliers. This study applied a self-organizing map (SOM) to fill in replace outliers from Kauma Sewage Treatment Plant Lilongwe, Malawi. We used primary secondary executed the SOM algorithm effluent pH, biochemical oxygen demand, dissolved oxygen. The results suggest that reliable filling gaps time series with less than 50% correlation coefficient (R) >0.90. failed reliably >50% values. For instance, high mean square error (MSE) 3,655.57, 10.62, 2,153.34 DO, BOD, respectively, were registered datasets more values, while very small MSE (MSE ≈ 0) associated DO >50%. Practitioners can use this approach improve planning management facilities where available records riddled observations.