Comparative Study of Coupling Models of Feature Selection Methods and Machine Learning Techniques for Predicting Monthly Reservoir Inflow DOI Open Access
Jakkarin Weekaew, Pakorn Ditthakit, Quoc Bao Pham

и другие.

Water, Год журнала: 2022, Номер 14(24), С. 4029 - 4029

Опубликована: Дек. 9, 2022

Effective reservoir operation under the effects of climate change is immensely challenging. The accuracy inflow forecasting one essential factors supporting operations. This study aimed to investigate coupling models feature selection (FS) and machine learning (ML) algorithms predict monthly inflow. was carried out using data from Huai Nam Sai in southern Thailand. Eighteen years recorded (i.e., inflow, storage, rainfall, regional indices) with up a 12-month time lag were utilized. Three ML techniques, i.e., multiple linear regression (MLR), support vector (SVR), artificial neural network (ANN)were compared their capabilities. In addition, two FS genetic algorithm (GA) backward elimination (BE) methods, studied four predictable intervals, consisting 3, 6, 9, 12 months advance. Ten-fold cross-validation used for model evaluation. Study results revealed that methods GA BE) Could improve performance SVR ANN predicting forecasting, but they have no on MLR. Different developed suitable different time-step-ahead. BE-ANN provided best three-time-ahead (T + 3) nine-time-ahead 9) by giving an OI 0.9885 0.8818, NSE 0.9546 0.9815, RMSE 1.3155 1.2172 MCM/month, MAE 0.9568 0.9644 r 0.9796 0.9804, respectively. GA-ANN showed highest prediction six-time-ahead 6), 0.8997, 0.9407, 2.1699 1.7549 0.9759. twelve-time-ahead 12), 0.9515, 0.9835, 1.1613 0.9273 0.9835.

Язык: Английский

A Review of the Application of Artificial Intelligence in Watershed Management DOI

S. Satheeshkumar,

R. Ravi

Water science and technology library, Год журнала: 2024, Номер unknown, С. 371 - 377

Опубликована: Янв. 1, 2024

Язык: Английский

Процитировано

1
Quartile Regression and Ensemble Models for Extreme Events of Multi-Time Step-Ahead Monthly Reservoir Inflow Forecasting DOI Open Access
Jakkarin Weekaew, Pakorn Ditthakit, Nichnan Kittiphattanabawon

и другие.

Water, Год журнала: 2024, Номер 16(23), С. 3388 - 3388

Опубликована: Ноя. 25, 2024

Amidst changing climatic conditions, accurately predicting reservoir inflows in an extreme event is challenging and inevitable for management. This study proposed innovative strategy under such circumstances through rigorous experimentation investigations using 18 years of monthly data collected from the Huai Nam Sai southern region Thailand. The employed a two-step approach: (1) isolating normal events quantile regression (QR) at 75th, 80th, 90th quantiles (2) comparing forecasting performance individual machine learning models their combinations, including Random Forest (RF), eXtreme Gradient Boosting (XGBoost), Long Short-Term Memory (LSTM), Multiple Linear Regression (MLR). Forecasting accuracy was assessed four lead times—3, 6, 9, 12 months—using ten-fold cross-validation, resulting 16 model configurations each forecast period. results show that combining to distinguish between with hybrid significantly improves inflow forecasting, except 9-month time, where XG continues deliver best performance. top-performing models, based on normalized scores 3-, 6-, 9-, 12-month-ahead forecasts, are XG-MLR-75, RF-XG-80, XG-75, XG-RF-75, respectively. Another crucial finding this research uneven decline prediction as time increases. Notably, performed t + followed by 3, 12, pattern influenced characteristics, error propagation, temporal variability, dynamics, seasonal effects. Improving efficiency can greatly enhance hydrological operational planning

Язык: Английский

Процитировано

1
Utilizing Machine Learning to Estimate Monthly Streamflow in Ungauged Basins of Thailand's Southern Basin DOI

Nureehan Salaeh,

Pakorn Ditthakit,

Sirimon Pinthong

и другие.

Physics and Chemistry of the Earth Parts A/B/C, Год журнала: 2024, Номер unknown, С. 103840 - 103840

Опубликована: Дек. 1, 2024

Язык: Английский

Процитировано

1
Comparison of Multilayer Perceptron with an Optimal Activation Function and Long Short-Term Memory for Rainfall-Runoff Simulations and Ungauged Catchment Runoff Prediction DOI
Mun-Ju Shin, Yong Jung

Water Resources Management, Год журнала: 2024, Номер unknown

Опубликована: Дек. 30, 2024

Язык: Английский

Процитировано

1
Comparative Study of Coupling Models of Feature Selection Methods and Machine Learning Techniques for Predicting Monthly Reservoir Inflow DOI Open Access
Jakkarin Weekaew, Pakorn Ditthakit, Quoc Bao Pham

и другие.

Water, Год журнала: 2022, Номер 14(24), С. 4029 - 4029

Опубликована: Дек. 9, 2022

Effective reservoir operation under the effects of climate change is immensely challenging. The accuracy inflow forecasting one essential factors supporting operations. This study aimed to investigate coupling models feature selection (FS) and machine learning (ML) algorithms predict monthly inflow. was carried out using data from Huai Nam Sai in southern Thailand. Eighteen years recorded (i.e., inflow, storage, rainfall, regional indices) with up a 12-month time lag were utilized. Three ML techniques, i.e., multiple linear regression (MLR), support vector (SVR), artificial neural network (ANN)were compared their capabilities. In addition, two FS genetic algorithm (GA) backward elimination (BE) methods, studied four predictable intervals, consisting 3, 6, 9, 12 months advance. Ten-fold cross-validation used for model evaluation. Study results revealed that methods GA BE) Could improve performance SVR ANN predicting forecasting, but they have no on MLR. Different developed suitable different time-step-ahead. BE-ANN provided best three-time-ahead (T + 3) nine-time-ahead 9) by giving an OI 0.9885 0.8818, NSE 0.9546 0.9815, RMSE 1.3155 1.2172 MCM/month, MAE 0.9568 0.9644 r 0.9796 0.9804, respectively. GA-ANN showed highest prediction six-time-ahead 6), 0.8997, 0.9407, 2.1699 1.7549 0.9759. twelve-time-ahead 12), 0.9515, 0.9835, 1.1613 0.9273 0.9835.

Язык: Английский

Процитировано

5