Improving LSTM hydrological modeling with spatiotemporal deep learning and multi-task learning: A case study of three mountainous areas on the Tibetan Plateau

Li, Bu; Li, Ruidong; Sun, Ting; Gong, Aofan; Khan, Mohd Yawar Ali; Ni, Guangheng

doi:10.1016/j.jhydrol.2023.129401

Cited by 27 publications

(16 citation statements)

References 59 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…To establish a fair comparison of model performance between the THREW model and the proposed hybrid models, the THREW model in this study is subjected to the same spatial discretization utilized by the hybrid models. LSTM models have recently shown excellent capabilities in hydrological simulation all over the world (Lees et al, 2021;Li et al, 2023a;Kratzert et al, 2019;Hochreiter and Schmidhuber, 1997). To benchmark against our proposed hybrid models, we have sourced the LSTM and CNN-LSTM model results from Li et al (2023a).…”

Section: Comparison Modelsmentioning

confidence: 99%

“…Most of these studies disregard the effect of spatial information from meteorological data on hydrological modeling. Li et al (2023a) introduced an innovative spatiotemporal DL hydrological model, demonstrating that integrating spatial information can significantly improve the performance of DL models in hydrological modeling. Nonetheless, despite their remarkable capabilities, DL hydrological models still face scrutiny within the hydrological modeling community, primarily due to their "black-box" nature.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Hybrid Hydrological Modeling for Large Alpine Basins: A Distributed Approach

Li,

Sun,

Tian

et al. 2024

Preprint

View full text Add to dashboard Cite

Abstract. Large alpine basins provide abundant water resources crucial for hydropower generation, irrigation, and daily life. It is thus crucial to develop high-performance hydrological models for water resources management in large alpine basins. Recently, hybrid hydrological models have come to the forefront, synergizing the exceptional learning capacity of deep learning with the interpretability and physical consistency of process-based models. These models exhibit considerable promise in achieving precision in hydrological simulations. However, a notable limitation of existing hybrid models lies in their failure to incorporate spatial information within the basin and describe alpine hydrological processes, which restricts their applicability in hydrological modeling in large alpine basins. To address this issue, we develop a set of hybrid distributed hydrological models by employing a distributed process-based model as the backbone, and utilizing embedded neural networks (ENNs) to parameterize and replace different internal modules. The proposed models are tested on three large alpine basins on the Tibetan Plateau. Results are compared to those obtained from hybrid lumped models, state-of-the-art distributed hydrological model, and purely deep learning models. A climate perturbation method is further used to test the applicability of the hybrid models to analyze the hydrological sensitivities to climate change in large alpine basins. Results indicate that proposed hybrid hydrological models can perform well in predicting runoff processes and simulating runoff component contributions in large alpine basins. The optimal hybrid model with Nash-Sutcliffe efficiency coefficients (NSEs) higher than 0.87 shows comparable performance to state-of-the-art DL models. The hybrid distributed model also exhibits remarkable capability in simulating hydrological processes at ungauged sites within the basin, markedly surpassing traditional distributed models. Besides, the results also show reasonable patterns in the analysis of the hydrological sensitivities to climate change. Runoff exhibits an amplification effect in response to precipitation changes, with a 10 % precipitation change resulting in a 15–20 % runoff change in large alpine basins. An increase in temperature enhances evaporation capacity and changes the redistribution of rainfall and snowfall and the timing of snowmelt. It further leads to a decrease in the total runoff, the contributions of snowmelt runoff, and the intra-annual variability of runoff. Overall, this study provides a high-performance tool enriched with explicit hydrological knowledge for hydrological prediction and improves our understanding about the hydrological sensitivities to climate change in large alpine basins.

show abstract

Section: Comparison Modelsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Hybrid Hydrological Modeling for Large Alpine Basins: A Distributed Approach

Li,

Sun,

Tian

et al. 2024

Preprint

View full text Add to dashboard Cite

show abstract

“…Como resultado, a aplicação de redes LSTM à hidrologia ganhou atenção considerável em pesquisas recentes (Descovi et al, 2023;Kratzert et al, 2018;Li et al, 2023;S. Mohammadizadeh et al, 2021;S.…”

Section: Redes De Memória Longa E De Curto Prazo (Lstm)unclassified

Utilizing Long Short-Term Memory (Lstm) Networks for River Flow Prediction in the Brazilian Pantanal Basin

Sampaio Descovi,

Carlos Zuffo,

Mohammadizadeh

et al. 2023

HOLOS

View full text Add to dashboard Cite

This article demonstrates the successful application of Long Short-Term Memory (LSTM) recurrent neural networks to simulate streamflow in the Aquidauana River basin, located in the Brazilian Pantanal. The LSTM network used daily precipitation data as input to predict future streamflow in the region. The results obtained from this research show a coefficient of determination (R2) of 0.82, indicating a strong fit of the model to the observed data. Additionally, the Root Mean Squared Error (RMSE) was found to be 0.53, indicating the model's accuracy in predicting streamflow compared to actual data. These findings highlight the effectiveness of LSTM networks in hydrological modeling for the Pantanal region, which is crucial for water resource planning and sustainable management in this ecologically significant area. This study is expected to serve as a catalyst for further research and make a substantial contribution to the advancement of streamflow prediction techniques in complex watersheds such as the Aquidauana River basin.

show abstract

“…In recent years, deep learning (DL) has made rapid progress and has been successfully applied in various fields. Deep learning methods have shown prominent advantages over traditional methods in hydrological and meteorological applications, including runoff forecasting [20], precipitation nowcasting [21][22][23], quantitative precipitation estimation [24,25], cloud-type classification [26], tropical cyclone tracking [27], etc. Several researchers have made attempts to apply deep learning models in radar missing data completion.…”

Section: Introductionmentioning

confidence: 99%

Improving the Completion of Weather Radar Missing Data with Deep Learning

Gong,

Chen,

2023

Remote Sensing

Self Cite

View full text Add to dashboard Cite

Weather radars commonly suffer from the data-missing problem that limits their data quality and applications. Traditional methods for the completion of weather radar missing data, which are based on radar physics and statistics, have shown defects in various aspects. Several deep learning (DL) models have been designed and applied to weather radar completion tasks but have been limited by low accuracy. This study proposes a dilated and self-attentional UNet (DSA-UNet) model to improve the completion of weather radar missing data. The model is trained and evaluated on a radar dataset built with random sector masking from the Yizhuang radar observations during the warm seasons from 2017 to 2019, which is further analyzed with two cases from the dataset. The performance of the DSA-UNet model is compared to two traditional statistical methods and a DL model. The evaluation methods consist of three quantitative metrics and three diagrams. The results show that the DL models can produce less biased and more accurate radar reflectivity values for data-missing areas than traditional statistical methods. Compared to the other DL model, the DSA-UNet model can not only produce a completion closer to the observation, especially for extreme values, but also improve the detection and reconstruction of local-scale radar echo patterns. Our study provides an effective solution for improving the completion of weather radar missing data, which is indispensable in radar quantitative applications.

show abstract

Improving LSTM hydrological modeling with spatiotemporal deep learning and multi-task learning: A case study of three mountainous areas on the Tibetan Plateau

Cited by 27 publications

References 59 publications

Hybrid Hydrological Modeling for Large Alpine Basins: A Distributed Approach

Hybrid Hydrological Modeling for Large Alpine Basins: A Distributed Approach

Utilizing Long Short-Term Memory (Lstm) Networks for River Flow Prediction in the Brazilian Pantanal Basin

Improving the Completion of Weather Radar Missing Data with Deep Learning

Contact Info

Product

Resources

About