Đánh giá khả năng dự báo mặn trên sông Hàm Luông của thuật toán K-Nearest Neighbors

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 create a K-Nearest Neighbors (KNN) model for predicting the saltwater intrusion in Ham Luong River, Ben Tre Province. The input data 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 performances of KNN model. The research results indicated that the KNN model achieved a high performance for salinity forecasting. with NSE = 0,960, RMSE = 0,842, MAE = 0,541 for training period, NSE = 0,904, RMSE = 1,448, MAE = 0,914 for testing period. The findings of this study suggest that the KNN model has promised as a potential tool in salinity forecasting with salinity data characteristics in Ham Luong River