Bài viết Áp dụng thuật toán học máy để dự báo độ mặn trên sông Hàm Luông, tỉnh Bến Tre đánh giá khả năng áp dụng một số thuật toán học máy, bao gồm hồi quy đa biến (Multiple Linear Regression, MLR), rừng ngẫu nhiên (Random Forest Regression, RFR), mạng nơ-ron nhân tạo (Artificial Neural Networks, ANN) trong dự báo độ mặn trên sông Hàm Luông, tỉnh Bến Tre. | VNU Journal of Science Earth and Environmental Sciences Vol. 38 No. 3 2022 79-92 Original Article Apply Machine Learning to Predict Saltwater Intrusion in the Ham Luong River Ben Tre Province Pham Ngoc Hoai1 Pham Bao Quoc1 Tran Thanh Thai2 1 Institute of Applied Technology Thu Dau Mot University 6 Tran Van On Phu Hoa Thu Dau Mot City Binh Duong Vietnam 2 Institute of Tropical Biology Vietnam Academy of Science and Technology 85 Tran Quoc Toan Vo Thi Sau District 3 Ho Chi Minh City Vietnam Received 08 October 2021 Revised 15 December 2021 Accepted 14 February 2022 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 RMSE MAE for training period NSE RMSE MAE for testing period. The findings of this study suggest that the ANN algorithm is a promising tool to forecast salinity in Ham Luong River. Keywords Artificial intelligence climate change Mekong Delta saltwater intrusion. _ Corresponding author. E-mail address https 2588-1094 79 80 P. N. Hoai et al. VNU Journal of Science Earth and Environmental Sciences .
