Enhanced multi-step streamflow series forecasting using hybrid signal decomposition and optimized reservoir computing models

Expert Systems with Applications, Год журнала: 2024, Номер 255, С. 124856 - 124856

Опубликована: Июль 24, 2024

Язык: Английский

---

A Ship Energy Consumption Prediction Method Based on TGMA Model and Feature Selection

Journal of Marine Science and Engineering, Год журнала: 2024, Номер 12(7), С. 1098 - 1098

Опубликована: Июнь 28, 2024

Optimizing ship energy efficiency is a crucial measure for reducing fuel use and emissions in the shipping industry. Accurate prediction models of consumption are essential achieving this optimization. However, external factors affecting have not been comprehensively investigated, many existing studies still face accuracy challenges. In study, we propose neural network model called TCN-GRU-MHSA (TGMA), which incorporates temporal convolutional (TCN), gated recurrent unit (GRU), multi-head self-attention mechanisms to predict consumption. Firstly, characteristics operation data analyzed, appropriate input features selected. Then, established validated through application analysis. Using proposed model, can reach up 96.04%. Comparative analysis results show that TGMA outperforms models, including those based on LSTM, GRU, SVR, TCN-GRU, BP networks, terms accuracy. Therefore, developed effectively usage under various conditions, making it optimizing improving efficiency.

Язык: Английский

---

Enhanced Streamflow Forecasting for Crisis Management Based on Hybrid Extreme Gradient Boosting Model

Iranian Journal of Science and Technology Transactions of Civil Engineering, Год журнала: 2025, Номер unknown

Опубликована: Янв. 13, 2025

Язык: Английский

---

Performance enhancement of models through discrete wavelet transform for streamflow forecasting in Çarşamba River, Türkiye

Journal of Water and Climate Change, Год журнала: 2025, Номер unknown

Опубликована: Янв. 31, 2025

ABSTRACT Streamflow forecasts play an active role in hydrological planning and taking precautions against natural disasters. prediction models are frequently used by scientists, especially dam management, sustainable agriculture, flood control, mitigation. Hence, streamflow modeling was performed this study, six were employed through four different machine learning (ML) algorithms, namely, the artificial neural network (ANN), random forest (RF), support vector (SVM), decision tree (DT) that well known literature, order to predict monthly of Çarşamba River, Türkiye. To further enhance model performance, wavelet transform (WT) applied ML algorithms. In average precipitation data between 1974 2015 used, minimum redundancy maximum relevance method (MRMR) cross-correlation determine input data. Results study revealed RF had superiority over other before WT, followed SVM model. The after WT (W-SVM), M04 (r: 0.9846, NSE: 0.9695, RMSE: 0.3536) gave most effective performance results, while W-ANN 0.9797, 0.9588, 0.4108) showed second best performance.

Язык: 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, Год журнала: 2024, Номер 636, С. 131230 - 131230

Опубликована: Апрель 24, 2024

Язык: Английский

---

Enhancing seasonal streamflow prediction using multistage hybrid stochastic data-driven deep learning methodology with deep feature selection

Environmental and Ecological Statistics, Год журнала: 2025, Номер unknown

Опубликована: Фев. 23, 2025

Язык: Английский

---

Enhancing hydrological time series forecasting with a hybrid Bayesian-ConvLSTM model optimized by particle swarm optimization

Acta Geophysica, Год журнала: 2025, Номер unknown

Опубликована: Март 24, 2025

Язык: Английский

---

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

Hydrological Sciences Journal, Год журнала: 2024, Номер 69(11), С. 1501 - 1522

Опубликована: Июль 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

Язык: Английский

---

Daily Runoff Forecasting Using Novel Optimized Machine Learning Methods

Results in Engineering, Год журнала: 2024, Номер 24, С. 103319 - 103319

Опубликована: Ноя. 5, 2024

Язык: Английский

---

Dynamic optimization can effectively improve the accuracy of reference evapotranspiration in southern China

Computers and Electronics in Agriculture, Год журнала: 2024, Номер 230, С. 109881 - 109881

Опубликована: Дек. 31, 2024

Язык: Английский

---