Comparing a long short-term memory (LSTM) neural network with a physically-based hydrological model for streamflow forecasting over a Canadian catchment

Sabzipour, Behmard; Arsenault, Richard; Troin, Magali; Martel, Jean-Luc; Brissette, François; Brunet, Frédéric; Mai, Juliane

doi:10.1016/j.jhydrol.2023.130380

Cited by 18 publications

(3 citation statements)

References 51 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Long short-term memory (LSTM) network is developed from recurrent neural network (RNN) as a solution to the common problem of gradient vanishing in RNNs. LSTM is suitable for problems that are highly correlated with time series [48]. LSTM contains three gate structures: input gate, forget gate, and output gate.…”

Section: Lstmmentioning

confidence: 99%

A Time Series Forecasting Approach Based on Meta-Learning for Petroleum Production under Few-Shot Samples

Xu,

2024

Energies

View full text Add to dashboard Cite

Accurate prediction of crude petroleum production in oil fields plays a crucial role in analyzing reservoir dynamics, formulating measures to increase production, and selecting ways to improve recovery factors. Current prediction methods mainly include reservoir engineering methods, numerical simulation methods, and deep learning methods, and the required prerequisite is a large amount of historical data. However, when the data used to train the model are insufficient, the prediction effect will be reduced dramatically. In this paper, a time series-related meta-learning (TsrML) method is proposed that can be applied to the prediction of petroleum time series containing small samples and can address the limitations of traditional deep learning methods for the few-shot problem, thereby supporting the development of production measures. The approach involves an architecture divided into meta-learner and base-learner, which learns initialization parameters from 89 time series datasets. It can be quickly adapted to achieve excellent and accurate predictions with small samples in the oil field. Three case studies were performed using time series from two actual oil fields. For objective evaluation, the proposed method is compared with several traditional methods. Compared to traditional deep learning methods, RMSE is decreased by 0.1766 on average, and MAPE is decreased by 4.8013 on average. The empirical results show that the proposed method outperforms the traditional deep learning methods.

show abstract

Section: Lstmmentioning

confidence: 99%

A Time Series Forecasting Approach Based on Meta-Learning for Petroleum Production under Few-Shot Samples

Xu,

2024

Energies

View full text Add to dashboard Cite

show abstract

“…Extensive research has shown that commonly used deep learning models for hydrological forecasting, such as LSTM (Hu et al, 2018;Sushanth et al, 2023;Sabzipour et al, 2023), TCN Qiao et al, 2023), andTransformer (Yin et al, 2022;Xu et al, 2023), have a more advanced theoretical foundation and model structure compared to traditional artificial neural networks. These models achieve better forecasting accuracy in multi-period flood forecasting.…”

Section: Literature Reviewmentioning

confidence: 99%

Research on a hybrid model for flood probability prediction based on time convolutional network and particle swarm optimization algorithm

Yu,

Liu,

et al. 2024

Preprint

View full text Add to dashboard Cite

Accurate advance flood forecasting is beneficial for planning watershed flood prevention measures in advance. In this study, the PSO-TCN-Bootstrap flood forecasting model for the Tailan River Basin in Xinjiang was constructed by coupling particle swarm optimization algorithm (PSO), temporal convolutional neural network algorithm (TCN), and Bootstrap probability sampling algorithm. The model was tested based on 50 historical flood events from 1960 to 2014 using measured rainfall-runoff data in the Tailan River Basin. The results showed that under the same lead time conditions, the PSO-TCN-Bootstrap model had higher Nash efficiency coefficient, lower root mean square error and relative peak error in flood process forecasting. The PSO-TCN-Bootstrap flood forecasting model has better applicability and robustness in the Tailan River Basin. However, when the lead time exceeds 5h, the relative peak error in the PSO-TCN-Bootstrap model's flood forecasting will still exceed 20%. In the future, it is expected to integrate the mechanism of flood process occurrence and further improve the generalization ability of machine learning models in flood forecasting applications. The research results can provide a scientific basis for flood management in the Tailan River Basin.

show abstract

“…Over the past decades, many scholars have attempted to predict soil moisture using control equations based on complex hydrological processes [10], involving a range of methods from integrating weather forecast models into land surface data assimilation systems to independently calculating soil moisture with land surface models driven by specific factors [11,12]. However, these physically based models face challenges in key application areas, such as the uncertainty of driving factors, incompleteness of land surface process models, and substantial computational resource demands [13]. Consequently, some studies have evaluated the performance of these physical models, highlighting their limitations, and explored machine learning (ML) models as alternatives [14,15].…”

Section: Introductionmentioning

confidence: 99%

Enhancing Soil Moisture Forecasting Accuracy with REDF-LSTM: Integrating Residual En-Decoding and Feature Attention Mechanisms

Li,

Zhang,

et al. 2024

Water

View full text Add to dashboard Cite

This study introduces an innovative deep learning model, Residual-EnDecode-Feedforward Attention Mechanism-Long Short-Term Memory (REDF-LSTM), designed to overcome the high uncertainty challenges faced by traditional soil moisture prediction methods. The REDF-LSTM model, by integrating a residual learning encoder–decoder LSTM layer, enhanced LSTM layers, and feedforward attention, not only captures the deep features of time series data but also optimizes the model’s ability to identify key influencing factors, including land surface features, atmospheric conditions, and other static environmental variables. Unlike existing methods, the innovation of this model lies in its first-time combination of the residual learning encoder–decoder and feedforward attention mechanisms in the soil moisture prediction field. It delves into the complex patterns of time series through the encoder–decoder structure and accurately locates key influencing factors through the feedforward attention mechanism, significantly improving predictive performance. The choice to combine the feedforward attention mechanism and encoder–decoder with the LSTM model is to fully leverage their advantages in processing complex data sequences and enhancing the model’s focus on important features, aiming for more accurate soil moisture prediction. After comparison with current advanced models such as EDLSTM, FAMLSTM, and GANBiLSTM, our REDF-LSTM demonstrated the best performance. Compared to traditional LSTM models, it achieved an average improvement of 13.07% in R2, 20.98% in RMSE, 24.86% in BIAS, and 11.1% in KGE key performance indicators, fully proving its superior predictive capability and potential application value in precision agriculture and ecosystem management.

show abstract

Comparing a long short-term memory (LSTM) neural network with a physically-based hydrological model for streamflow forecasting over a Canadian catchment

Cited by 18 publications

References 51 publications

A Time Series Forecasting Approach Based on Meta-Learning for Petroleum Production under Few-Shot Samples

A Time Series Forecasting Approach Based on Meta-Learning for Petroleum Production under Few-Shot Samples

Research on a hybrid model for flood probability prediction based on time convolutional network and particle swarm optimization algorithm

Enhancing Soil Moisture Forecasting Accuracy with REDF-LSTM: Integrating Residual En-Decoding and Feature Attention Mechanisms

Contact Info

Product

Resources

About