Apply Machine Learning to Predict Saltwater Intrusion in the Ham Luong River, Ben Tre Province
Phạm Ngọc Hoài, Pham Bao Quoc, Trần Thành Thái
Abstract
Saltwater intrusion is a major problem particularly in the Mekong Delta, Việt Nam. In order to better manage the salinity problem, it is important to be able to predict the saltwater intrusion in rivers. The objective of this research is to apply several machine learning algorithms, including Multiple Linear Regression (MLR), Random Forest Regression (RFR), Artificial Neural Networks (ANN) for predicting the saltwater intrusion in Ham Luong River, Ben Tre Province. The input data is is composed of 207 weekly saltwater intrusion data points from 2012 to 2020. Yearly salinity was measured during the 23 weeks of the dry season, from January to June. The Nash - Sutcliffe efficiency coefficient (NSE), Root Mean Squared Error (RMSE), and Mean Absolute Error (MAE) are used to evaluate the performances of machine learning algorithms. The research results indicated that the ANN model achieved a high performance for salinity forecasting with NSE = 0.907, RMSE = 0.11, MAE = 0.08 for training period, NSE = 0.842, RMSE = 1.16, MAE = 0.11 for testing period. The findings of this study suggest that the ANN algorithm is a promising tool to forecast salinity in Ham Luong River.