Saltwater Intrusion Forecast System for Thachin River using Multilayer Perceptron Neural Network

Abstract

Saltwater intrusion is the movement of saline water into freshwater, which can lead to contamination of drinking water sources and other consequences. Currently, saltwater intrusion into the Thachin River is still ongoing, severely affecting in agricultural area and aquaculture. This research aims to develop a model to forecast of saltwater intrusion for Thachin River using Multilayer Perceptron Neural Network, developed to forecast saltwater intrusion 7 days in advance at Nakhon Chaisri and Sam Phran Station. The model to forecast saltwater intrusion was assessed using Mean Square Error (MSE) and Root Mean Square Error (RMSE). The results showed that MSE for Nakhon Chaisri and Sam Phran Station were 0.0020 and 0.0049, RMSE were 0.0048 and 0.0317. This indicated that the Multilayer Perceptron Neural Network was the suitable model for this data set.