☆ 4.7 Article

A dynamic classification-based long short-term memory network model for daily streamflow forecasting in different climate regions

ECOLOGICAL INDICATORS (2023)

相关参考文献

注意：仅列出部分参考文献，下载原文获取全部文献信息。

Article Environmental Sciences

Assessing spatial connectivity effects on daily streamflow forecasting using Bayesian-based graph neural network

Guanjun Liu et al.

Summary: This paper investigates the impact of basin networks on daily streamflow prediction and proposes a novel graph neural network model. The results show that establishing appropriate connections and identifying connection relationships in the basin network can effectively improve the prediction accuracy and reliability of the graph convolutional model.

SCIENCE OF THE TOTAL ENVIRONMENT (2023)

添加到收藏夹

Article Biodiversity Conservation

Surface water temperature prediction in large-deep reservoirs using a long short-term memory model

Longfan Wang et al.

Summary: This study proposed an LSTM-based method for predicting surface water temperature (SWT) in reservoirs, demonstrating significant improvements in prediction efficiency. The model accurately predicted SWT, with a high correlation to measured data, and sensitivity analysis revealed the impacts of climate change and reservoir operations on SWT. The method offers a computational efficiency that can easily integrate with reservoir management models for optimizing operations and supporting strategies to reduce aquatic ecosystem risks.

ECOLOGICAL INDICATORS (2022)

添加到收藏夹

Article Environmental Sciences

Capabilities of deep learning models on learning physical relationships: Case of rainfall-runoff modeling with LSTM

Kazuki Yokoo et al.

Summary: This study investigates the relationships between input and output data using deep learning methods. A case study of rainfall-runoff modeling in a snow-dominated watershed was conducted using a long short-term memory (LSTM) network. The results indicated that the trained model generated flow discharge but exhibited a strong lack of water mass conservation.

SCIENCE OF THE TOTAL ENVIRONMENT (2022)

添加到收藏夹

Article Environmental Sciences

Multi-Task Deep Learning of Daily Streamflow and Water Temperature

J. M. Sadler et al.

Summary: The study explores the benefits of using multi-task deep learning models to predict both streamflow and water temperature, and finds that it can lead to more accurate predictions for certain sites and model configurations.

WATER RESOURCES RESEARCH (2022)

添加到收藏夹

Article Biodiversity Conservation

Streamflow prediction with large climate indices using several hybrid multilayer perceptrons and copula Bayesian model averaging

Fatemeh Panahi et al.

Summary: The study focuses on predicting streamflow in four rivers of Malaysia using the CBMA as an improved version of the BMA model. The CBMA corrects the assumption of Gaussian distortion in the BMA and uses different distribution and Copula functions for the variables. The study trains the MLP model with the AOA algorithm and benchmarks it against other optimization algorithms, showing a significant improvement in predictive performance.

ECOLOGICAL INDICATORS (2021)

添加到收藏夹

Article Engineering, Civil

A classification-based deep belief networks model framework for daily streamflow forecasting

Haibo Chu et al.

Summary: The paper introduces an integrated framework for daily streamflow forecasting based on different flow regimes, which improves modeling performance through regime identification, input selection, nonlinear relationship mapping, and rigorous validation. Application of the framework to three streamflow stations in the USA shows significant performance improvement compared to single data-driven models.

JOURNAL OF HYDROLOGY (2021)

添加到收藏夹

Article Environmental Sciences

Sequential Data Assimilation for Streamflow Forecasting: Assessing the Sensitivity to Uncertainties and Updated Variables of a Conceptual Hydrological Model at Basin Scale

G. Piazzi et al.

Summary: Skillful streamflow forecasts are crucial for water-related applications, with a growing emphasis on improving initial condition estimates through data assimilation. This study assesses the sensitivity of DA-based IC estimation to various uncertainties and model updates over 232 watersheds in France. The comparison of two ensemble-based techniques shows that accurate routing store estimates benefit the DA-based IC estimation, with the EnKF outperforming the PF in forecasting meteorological uncertainty.

WATER RESOURCES RESEARCH (2021)

添加到收藏夹

Article Engineering, Civil

A novel attention-based LSTM cell post-processor coupled with bayesian optimization for streamflow prediction

Babak Alizadeh et al.

Summary: The study introduces a novel deep learning model SAINA-LSTM, which improves streamflow forecasting performance by incorporating attention mechanism into LSTM cells. SAINA-LSTM outperforms other models in various climatological basins and for 1- to 7-day ahead forecasts in different flow ranges.

JOURNAL OF HYDROLOGY (2021)

添加到收藏夹

Article Environmental Sciences

Developing a Long Short-Term Memory (LSTM)-Based Model for Reconstructing Terrestrial Water Storage Variations from 1982 to 2016 in the Tarim River Basin, Northwest China

Fei Wang et al.

Summary: This study utilizes the LSTM model and GRACE data to effectively analyze the long-term Terrestrial Water Storage Anomalies in the Tarim River Basin, revealing a significant downward trend in TWSA in this region.

REMOTE SENSING (2021)

添加到收藏夹

Article Computer Science, Artificial Intelligence

Daily streamflow forecasting in Sobradinho Reservoir using machine learning models coupled with wavelet transform and bootstrapping

Samuel Vitor Saraiva et al.

Summary: This study conducted a comparative analysis of a set of machine learning models, including an ANN and an SVM coupled with wavelet transform and data resampling. Results showed that the ANN outperformed the SVM in terms of accuracy, with the best performing combination being the BWNN method. The BWNN method yielded lower mean square error and higher R-2 and MAE coefficients for streamflow forecasting 3 to 15 days ahead.

APPLIED SOFT COMPUTING (2021)

添加到收藏夹

Review Environmental Sciences

Generating Ensemble Streamflow Forecasts: A Review of Methods and Approaches Over the Past 40 Years

Magali Troin et al.

Summary: This study reviews over 700 research studies in the past 40 years on ensemble forecasting in hydrology, focusing on model-based approaches and categorizing them into statistics-based, climatology-based, and numerical weather prediction-based systems. The review highlights the performance and uncertainty of ensemble forecasting systems, and identifies future research directions, particularly in hybrid dynamical - statistical learning approaches.

WATER RESOURCES RESEARCH (2021)

添加到收藏夹

Article Environmental Sciences

A Short-Term Wind Speed Forecasting Model Based on a Multi-Variable Long Short-Term Memory Network

Anqi Xie et al.

Summary: This study proposed a method based on a multi-variable long short-term memory network model for short-term wind speed forecasting, which proved to be feasible and superior to other forecasting methods.

ATMOSPHERE (2021)

添加到收藏夹

Article Environmental Sciences

PCA-based multivariate LSTM model for predicting natural groundwater level variations in a time-series record affected by anthropogenic factors

Gyoo-Bum Kim et al.

Summary: This study aimed to develop a universal LSTM model for predicting natural water level variations in a time-series record affected by groundwater abstraction or other anthropogenic factors. It uses past and present groundwater levels, rainfall, and representative principal components of groundwater level time series as input variables. Among 17 cases tested, the model with the highest performance, case 6, achieved average RMSE and MAE values of 0.061 and 0.027, respectively. The model utilized rainfall, groundwater levels of monitoring wells, and four main principal components as input variables, with an optimum window size of 5.

ENVIRONMENTAL EARTH SCIENCES (2021)

添加到收藏夹

Article Computer Science, Interdisciplinary Applications

A rapid flood inundation modelling framework using deep learning with spatial reduction and reconstruction

Yuerong Zhou et al.

Summary: A rapid flood inundation modelling framework is developed in this study, combining a spatial reduction and reconstruction (SRR) approach and deep learning (DL) modelling component. The framework is able to efficiently estimate inundation surfaces in real-world river systems, simulating over 3 million grid cells in 4 seconds.

ENVIRONMENTAL MODELLING & SOFTWARE (2021)

添加到收藏夹

Article Engineering, Civil

Examination and comparison of binary metaheuristic wrapper-based input variable selection for local and global climate information-driven one-step monthly streamflow forecasting

Kun Ren et al.

Summary: The study highlights the importance of selecting appropriate input variable selection methods in practice, as some examined wrappers were found to be inferior to benchmark models. The BMWIVS model combining different methods yielded the best performance across the three cases studied. Additionally, the correlations between global climate indices and streamflow were lower than those between local weather information and streamflow, indicating that both types of information are important for forecasting monthly streamflow.

JOURNAL OF HYDROLOGY (2021)

添加到收藏夹

Article Engineering, Civil

Improving Artificial Neural Network Based Streamflow Forecasting Models through Data Preprocessing

Muhammad Hassan et al.

Summary: Real-time hydrological data can be noisy, contain missing information, and deviate from its original scale due to the complex and nonlinear nature of hydrological processes. This study introduces a simple preprocessing approach, involving power transformations, Box-Cox transformations, and input variable selection through the Gamma Test, to improve the performance of ANN-based streamflow estimation models. The results show that the models developed with transformed data-sets outperform those developed with original data in terms of NSE, R-2, and other statistical errors, indicating that simple preprocessing options can significantly reduce uncertainty in ANN-based hydrological models by enhancing the quality of real-time hydrological data.

KSCE JOURNAL OF CIVIL ENGINEERING (2021)

添加到收藏夹

Article Engineering, Civil

Performance Comparison of an LSTM-based Deep Learning Model versus Conventional Machine Learning Algorithms for Streamflow Forecasting

Maryam Rahimzad et al.

Summary: Streamflow forecasting is crucial for water resource management, flood warning, and mitigation. This study compared the accuracy of four data-driven techniques in daily streamflow forecasting and found that the LSTM network outperformed other models in terms of NRMSE, E-H, E-L, and R values.

WATER RESOURCES MANAGEMENT (2021)

添加到收藏夹

Article Geosciences, Multidisciplinary

AI-based techniques for multi-step streamflow forecasts: application for multi-objective reservoir operation optimization and performance assessment

Yuxue Guo et al.

Summary: This study developed an AI-based management methodology integrating multi-step streamflow forecasts and multi-objective reservoir operation optimization for water resource allocation. The study found that both GRU and LSTM performed equally well on streamflow forecasts, with GRU potentially being the preferred method due to its simpler structure and less modeling time. Higher forecast performance could lead to improved reservoir operation, while uncertain forecasts were more valuable than deterministic forecasts.

HYDROLOGY AND EARTH SYSTEM SCIENCES (2021)

添加到收藏夹

Article Energy & Fuels

Time-series well performance prediction based on Long Short-Term Memory (LSTM) neural network model

Xuanyi Song et al.

JOURNAL OF PETROLEUM SCIENCE AND ENGINEERING (2020)

添加到收藏夹

Article Engineering, Civil

Decomposition ensemble model based on variational mode decomposition and long short-term memory for streamflow forecasting

Ganggang Zuo et al.

JOURNAL OF HYDROLOGY (2020)

添加到收藏夹

Article Mechanics

A data-driven approach based on long short-term memory and hidden Markov model for crack propagation prediction

Duyen H. Nguyen-Le et al.

ENGINEERING FRACTURE MECHANICS (2020)

添加到收藏夹

Article Engineering, Civil

A robust approach for calibrating a daily rainfall-runoff model to monthly streamflow data

Julien Lerat et al.

JOURNAL OF HYDROLOGY (2020)

添加到收藏夹

Article Environmental Sciences

Data Assimilation for Streamflow Forecasting Using Extreme Learning Machines and Multilayer Perceptrons

M-A Boucher et al.

WATER RESOURCES RESEARCH (2020)

添加到收藏夹

Article Engineering, Civil

Long lead-time daily and monthly streamflow forecasting using machine learning methods

M. Cheng et al.

JOURNAL OF HYDROLOGY (2020)

添加到收藏夹

Article Engineering, Civil

An enhanced extreme learning machine model for river flow forecasting: State-of-the-art, practical applications in water resource engineering area and future research direction

Zaher Mundher Yaseen et al.

JOURNAL OF HYDROLOGY (2019)

添加到收藏夹

Article Geochemistry & Geophysics

Long short-term memory (LSTM) recurrent neural network for low-flow hydrological time series forecasting

Bibhuti Bhusan Sahoo et al.

ACTA GEOPHYSICA (2019)

添加到收藏夹

Article Water Resources

Exploring geometrical patterns in streamflow time series: utility for forecasting?

Ramesh S. Teegavarapu

HYDROLOGY RESEARCH (2018)

添加到收藏夹

Article Engineering, Civil

Developing a Long Short-Term Memory (LSTM) based model for predicting water table depth in agricultural areas

Jianfeng Zhang et al.

JOURNAL OF HYDROLOGY (2018)

添加到收藏夹

Article Engineering, Civil

An improved gene expression programming model for streamflow forecasting in intermittent streams

Ali Danandeh Mehr

JOURNAL OF HYDROLOGY (2018)

添加到收藏夹

Article Engineering, Civil

Forecasting Daily Streamflow for Basins with Different Physical Characteristics through Data-Driven Methods

Sinan Jasim Hadi et al.

WATER RESOURCES MANAGEMENT (2018)

添加到收藏夹

Article Water Resources

Exploring geometrical patterns in streamflow time series: utility for forecasting?

Ramesh S. Teegavarapu

HYDROLOGY RESEARCH (2018)

添加到收藏夹

Article Engineering, Environmental

Design and evaluation of SVR, MARS and M5Tree models for 1, 2 and 3-day lead time forecasting of river flow data in a semiarid mountainous catchment

Zhenliang Yin et al.

STOCHASTIC ENVIRONMENTAL RESEARCH AND RISK ASSESSMENT (2018)

添加到收藏夹

Article Geosciences, Multidisciplinary

Rainfall-runoff modelling using Long Short-Term Memory (LSTM) networks

Frederik Kratzert et al.

HYDROLOGY AND EARTH SYSTEM SCIENCES (2018)

添加到收藏夹

Article Engineering, Civil

Improved error modelling for streamflow forecasting at hourly time steps by splitting hydrographs into rising and falling limbs

Ming Li et al.

JOURNAL OF HYDROLOGY (2017)

添加到收藏夹

Article Geosciences, Multidisciplinary

Seasonal streamflow forecasting by conditioning climatology with precipitation indices

Louise Crochemore et al.

HYDROLOGY AND EARTH SYSTEM SCIENCES (2017)

添加到收藏夹

Article Engineering, Civil

Configurational entropy theory for streamflow forecasting

Huijuan Cui et al.

JOURNAL OF HYDROLOGY (2015)

添加到收藏夹

Article Engineering, Civil

Copula-based modeling and stochastic simulation of seasonal intermittent streamflows for arid regions

Changsam Jeong et al.

JOURNAL OF HYDRO-ENVIRONMENT RESEARCH (2015)

添加到收藏夹

Article Engineering, Civil

Hydrological Drought Assessment in Northwestern Iran Based on Streamflow Drought Index (SDI)

Hossein Tabari et al.

WATER RESOURCES MANAGEMENT (2013)

添加到收藏夹

© Peeref 2019-2024. All rights reserved.