Enhancing Hydrological Modeling with Transformers: A Case Study for 24-Hour Streamflow Prediction DOI Creative Commons
Bekir Zahit Demiray, Muhammed Sit, Omer Mermer

и другие.

EarthArXiv (California Digital Library), Год журнала: 2023, Номер unknown

Опубликована: Сен. 12, 2023

In this paper, we address the critical task of 24-hour streamflow forecasting using advanced deep-learning models, with a primary focus on Transformer architecture which has seen limited application in specific task. We compare performance five different including Persistence, LSTM, Seq2Seq, GRU, and Transformer, across four distinct regions. The evaluation is based three metrics: Nash-Sutcliffe Efficiency (NSE), Pearson’s r, Normalized Root Mean Square Error (NRMSE). Additionally, investigate impact two data extension methods: zero-padding persistence, model's predictive capabilities. Our findings highlight Transformer's superiority capturing complex temporal dependencies patterns data, outperforming all other models terms both accuracy reliability. study's insights emphasize significance leveraging deep learning techniques, such as hydrological modeling for effective water resource management flood prediction.

Язык: Английский

Enhancing hydrological modeling with transformers: a case study for 24-h streamflow prediction DOI Creative Commons
Bekir Zahit Demiray, Muhammed Sit, Omer Mermer

и другие.

Water Science & Technology, Год журнала: 2024, Номер 89(9), С. 2326 - 2341

Опубликована: Апрель 4, 2024

ABSTRACT In this paper, we address the critical task of 24-h streamflow forecasting using advanced deep-learning models, with a primary focus on transformer architecture which has seen limited application in specific task. We compare performance five different including persistence, long short-term memory (LSTM), Seq2Seq, GRU, and transformer, across four distinct regions. The evaluation is based three metrics: Nash–Sutcliffe Efficiency (NSE), Pearson's r, normalized root mean square error (NRMSE). Additionally, investigate impact two data extension methods: zero-padding model's predictive capabilities. Our findings highlight transformer's superiority capturing complex temporal dependencies patterns data, outperforming all other models terms both accuracy reliability. Specifically, model demonstrated substantial improvement NSE scores by up to 20% compared models. study's insights emphasize significance leveraging deep learning techniques, such as hydrological modeling for effective water resource management flood prediction.

Язык: Английский

Процитировано

6
DiffREE: feature-conditioned diffusion model for radar echo extrapolation DOI

Wu Qi-liang,

Xing Wang, Tong Zhang

и другие.

The Journal of Supercomputing, Год журнала: 2024, Номер 81(1)

Опубликована: Окт. 18, 2024

Язык: Английский

Процитировано

1
Spatial Downscaling of Streamflow Data with Attention Based Spatio-Temporal Graph Convolutional Networks DOI Creative Commons
Muhammed Sit, Bekir Zahit Demiray, İbrahim Demir

и другие.

EarthArXiv (California Digital Library), Год журнала: 2023, Номер unknown

Опубликована: Март 31, 2023

Accurate streamflow data is vital for various climate modeling applications, including flood forecasting. However, many streams lack sufficient monitoring due to the high operational costs involved. To address this issue and promote enhanced disaster preparedness, management, response, our study introduces a neural network-based method estimating historical hourly in two spatial downscaling scenarios. The targets types of ungauged locations: (1) those without sensors sparsely gauged river networks, (2) that previously had sensor, but gauge no longer available. For both cases, we propose ScaleGNN, graph network based on Attention-Based Spatio-Temporal Graph Convolutional Networks (ASTGCN). We evaluate performance ScaleGNN against Long Short-Term Memory (LSTM) baseline persistence discharge values over 36-hour period. Our findings indicate surpasses first scenario, while approaches demonstrate their effectiveness compared second scenario.

Язык: Английский

Процитировано

2
DiffREE: Feature-Conditioned Diffusion Model for Radar Echo Extrapolation DOI Creative Commons

Wu Qi-liang,

Xing Wang, Tong Zhang

и другие.

Research Square (Research Square), Год журнала: 2024, Номер unknown

Опубликована: Апрель 19, 2024

Abstract Deep learning techniques for radar echo extrapolation and prediction have become crucial short-term precipitation forecasts in recent years. As the leading time extends, intensity attenuates increasingly, forecast performance on strong echoes declines rapidly. These are two typical characteristics contributing to current inaccurate results of extrapolation. To this end, we propose a novel diffusion (DiffREE) algorithm driven by frames study. This deeply integrates spatio-temporal information through conditional encoding module, then it utilizes Transformer encoder automatically extract features echoes. serve as inputs model, driving model reconstruct frame. Moreover, validation experiment demonstrates that proposed method can generate high-precision high-quality images further substantiate performance, DiffREE is compared with other four models using public datasets. In task, remarkable improvement evaluation metrics critical success index, equitable threat score, Heidke skill score probability detection 21.5%, 27.6%, 25.8%, 21.8%, respectively, displaying notable superiority.

Язык: Английский

Процитировано

0
Enhancing Hydrological Modeling with Transformers: A Case Study for 24-Hour Streamflow Prediction DOI Creative Commons
Bekir Zahit Demiray, Muhammed Sit, Omer Mermer

и другие.

EarthArXiv (California Digital Library), Год журнала: 2023, Номер unknown

Опубликована: Сен. 12, 2023

In this paper, we address the critical task of 24-hour streamflow forecasting using advanced deep-learning models, with a primary focus on Transformer architecture which has seen limited application in specific task. We compare performance five different including Persistence, LSTM, Seq2Seq, GRU, and Transformer, across four distinct regions. The evaluation is based three metrics: Nash-Sutcliffe Efficiency (NSE), Pearson’s r, Normalized Root Mean Square Error (NRMSE). Additionally, investigate impact two data extension methods: zero-padding persistence, model's predictive capabilities. Our findings highlight Transformer's superiority capturing complex temporal dependencies patterns data, outperforming all other models terms both accuracy reliability. study's insights emphasize significance leveraging deep learning techniques, such as hydrological modeling for effective water resource management flood prediction.

Язык: Английский

Процитировано

0