Daily River flow Simulation Using Ensemble Disjoint Aggregating M5-Prime Model

Heliyon, Journal Year: 2024, Volume and Issue: 10(20), P. e37965 - e37965

Published: Sept. 30, 2024

Accurate prediction of daily river flow (Q t ) remains a challenging yet essential task in hydrological modeling, particularly crucial for flood mitigation and water resource management. This study introduces an advanced M5 Prime (M5P) predictive model designed to estimate Q as well one- two-day-ahead forecasts (i.e. t+1 t+2 ). The performance M5P ensembles incorporating Bootstrap Aggregation (BA), Disjoint Aggregating (DA), Additive Regression (AR), Vote (V), Iterative classifier optimizer (ICO), Random Subspace (RS), Rotation Forest (ROF) were comprehensively evaluated. proposed models applied case data Tuolumne County, US, using dataset comprising measured precipitation (P ), evaporation (E t), . A wide range input scenarios explored predicting , t+1, t+2. Results indicate that P significantly influence accuracy. Notably, relying solely on the most correlated variable (e.g., t-1) does not guarantee robust However, extending forecast horizon mitigates low-correlation variables Performance metrics DA-M5P achieves superior results, with Nash-Sutcliff Efficiency 0.916 root mean square error 23 m3/s, followed by ROF-M5P, BA-M5P, AR-M5P, RS-M5P, V-M5P, ICO-M5P, standalone model. ensemble modeling framework enhanced capability stand-alone algorithm 1.2 %-22.6 %, underscoring its efficacy potential advancing forecasting.

Language: Английский

---

Improving the explainability of CNN-LSTM-based flood prediction with integrating SHAP technique

Ecological Informatics, Journal Year: 2024, Volume and Issue: 84, P. 102904 - 102904

Published: Nov. 17, 2024

Language: Английский

---

Daily Streamflow Forecasting Using Networks of Real-Time Monitoring Stations and Hybrid Machine Learning Methods

Water, Journal Year: 2024, Volume and Issue: 16(9), P. 1284 - 1284

Published: April 30, 2024

Considering the increased risk of urban flooding and drought due to global climate change rapid urbanization, imperative for more accurate methods streamflow forecasting has intensified. This study introduces a pioneering approach leveraging available network real-time monitoring stations advanced machine learning algorithms that can accurately simulate spatial–temporal problems. The Spatio-Temporal Attention Gated Recurrent Unit (STA-GRU) model is renowned its computational efficacy in events with forecast horizon 7 days. novel integration groundwater level, precipitation, river discharge as predictive variables offers holistic view hydrological cycle, enhancing model’s accuracy. Our findings reveal 7-day period, STA-GRU demonstrates superior performance, notable improvement mean absolute percentage error (MAPE) values R-square (R2) alongside reductions root squared (RMSE) (MAE) metrics, underscoring generalizability reliability. Comparative analysis seven conventional deep models, including Long Short-Term Memory (LSTM), Convolutional Neural Network LSTM (CNNLSTM), (ConvLSTM), (STA-LSTM), (GRU), GRU (CNNGRU), STA-GRU, confirms power STA-LSTM models when faced long-term prediction. research marks significant shift towards an integrated deep-learning forecasting, emphasizing importance spatially temporally encompassing variability within watershed’s stream network.

Language: Английский

---

Streamflow prediction using Long Short-Term Memory networks: a case study at the Kratie Hydrological Station, Mekong River Basin

Journal of Hydroinformatics, Journal Year: 2025, Volume and Issue: unknown

Published: Jan. 20, 2025

ABSTRACT Accurate streamflow prediction is vital for hydropower operations, agricultural planning, and water resource management. This study assesses the effectiveness of Long Short-Term Memory (LSTM) networks in daily at Kratie station, investigate different network structures hyperparameters to optimize predictive accuracy while considering computational efficiency. Our findings underscore significance LSTM models addressing challenges. Training on historical data reveals training dataset size; spanning 2013–2022 yields optimal results. Incorporating a hidden layer with nonlinear activation function, adding fully connected improve ability. However, increasing number neurons layers introduces complexity overhead. Careful parameter tuning, including epochs, dropout, units, crucial performance without sacrificing The stacked sigmoid demonstrates exceptional performance, boasting high Nash–Sutcliffe Efficiency 0.95 low relative root mean square error (rRMSE) approximately 0.002%. Moreover, model excels forecasting 5–15 antecedent days, 5 days exhibiting particularly accuracy. These offer valuable insights into management Vietnam Mekong Delta.

Language: Английский

---

An improved graph neural network integrating indicator attention and spatio-temporal correlation for dissolved oxygen prediction

Ecological Informatics, Journal Year: 2025, Volume and Issue: unknown, P. 103126 - 103126

Published: April 1, 2025

Language: Английский

---

Investigating the potential of EMA-embedded feature selection method for ESVR and LSTM to enhance the robustness of monthly streamflow forecasting from local meteorological information

Journal of Hydrology, Journal Year: 2024, Volume and Issue: 636, P. 131230 - 131230

Published: April 24, 2024

Language: Английский

---

Predicting rainfall using machine learning, deep learning, and time series models across an altitudinal gradient in the North-Western Himalayas

Scientific Reports, Journal Year: 2024, Volume and Issue: 14(1)

Published: Nov. 13, 2024

Predicting rainfall is a challenging and critical task due to its significant impact on society. Timely accurate predictions are essential for minimizing human financial losses. The dependence of approximately 60% agricultural land in India monsoon implies the crucial nature prediction. Precise forecasts can facilitate early preparedness disasters associated with heavy rains, enabling public government take necessary precautions. In North-Western Himalayas, where meteorological data limited, need improved accuracy traditional modeling methods forecasting pressing. To address this, our study proposes application advanced machine learning (ML) algorithms, including random forest (RF), support vector regression (SVR), artificial neural network (ANN), k-nearest neighbour (KNN) along various deep (DL) algorithms such as long short-term memory (LSTM), bi-directional LSTM, gated recurrent unit (GRU), simple (RNN). These techniques hold potential significantly improve prediction, offering hope more reliable forecasts. Additionally, time series techniques, autoregressive integrated moving average (ARIMA) trigonometric, Box-Cox transform, arma errors, trend, seasonal components (TBATS), proposed predicting across altitudinal gradients India's Himalayas. This approach potentially revolutionise how we forecasting, ushering new era reliability. effectiveness were assessed using obtained from six weather stations at different elevations spanning 1980 2021. results indicate that DL exhibit highest rainfall, measured by root mean squared error (RMSE) absolute (MAE), followed ML techniques. Among order was RNN, GRU. For ANN, KNN, SVR, RF. findings suggest altitude affects models, highlighting additional this mountainous region enhance precision

Language: Английский

---

Ensemble learning of decomposition-based machine learning models for multistep-ahead daily streamflow forecasting in northwest China

Hydrological Sciences Journal, Journal Year: 2024, Volume and Issue: 69(11), P. 1501 - 1522

Published: July 1, 2024

Accurate daily streamflow forecasts remain challenging in arid regions. A Bayesian Model Averaging (BMA) ensemble learning strategy was proposed to forecast 1-, 2-, and 3-day ahead Dunhuang Oasis, northwest China. The efficiency of BMA compared with four decomposition-based machine deep models. Satisfactory were achieved all models at lead times; however, based on NSE values 0.976, 0.967, 0.957, the greatest accuracy for forecasts, respectively. Uncertainty analysis confirmed reliability yielding consistently accurate forecasts. Thus, could provide an efficient alternative approach multistep-ahead forecasting. incorporation data decomposition techniques (e.g. Variational mode decomposition) algorithms Deep belief network) into BMA, may serve as worthy technical references supervised systems scare

Language: Английский

---

Development of a novel modeling framework based on weighted kernel extreme learning machine and ridge regression for streamflow forecasting

Scientific Reports, Journal Year: 2024, Volume and Issue: 14(1)

Published: Dec. 28, 2024

A precise streamflow forecast is crucial in hydrology for flood alerts, water quantity and quality management, disaster preparedness. Machine learning (ML) techniques are commonly employed hydrological prediction; however, they still face certain drawbacks, such as the need to optimize appropriate predictors, ability of models generalize across different time horizons, analysis high-dimensional series. This research aims address these specific drawbacks by developing a novel framework forecasting. Specifically, hybrid ML model, WKELM-R, developed predict based on daily discharge precipitation. The model combines ridge regression (RR), locally weighted linear (LWLR), kernel extreme machine (KELM) enhance multi-step-ahead predictions accounting both nonlinear characteristics. In data preprocessing, this study applies multivariate variational mode decomposition (MVMD) handle non-stationarity complexity, Boruta-XGBoost feature selection select optimal inputs decrease dimension, gradient-based optimizer (GBO) adjustment parameters overcome predictors. To demonstrate real-world conditions WKELM-R was applied watershed North Dakota, USA three horizons. results were compared with those from existing standalone multi-criteria decision-making (MCDM), demonstrating efficacy unique capabilities new forecasting (for testing level at t + 3: R = 0.992, RMSE 0.426, NSE 0.983; 7: 0.997, 0.249, 0.994; 14: 0.996, 0.304, 0.991).

Language: Английский

---

Improved random vector functional link network with an enhanced remora optimization algorithm for predicting monthly streamflow

Journal of Hydrology, Journal Year: 2024, Volume and Issue: 650, P. 132496 - 132496

Published: Dec. 16, 2024

Language: Английский

---