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
EfficientRainNet: Leveraging EfficientNetV2 for memory-efficient rainfall nowcasting DOI
Muhammed Sit, Bong‐Chul Seo, Bekir Zahit Demiray

и другие.

Environmental Modelling & Software, Год журнала: 2024, Номер 176, С. 106001 - 106001

Опубликована: Март 6, 2024

Язык: Английский

Процитировано

4
A Systematic Review of Deep Learning Applications in Streamflow Data Augmentation and Forecasting DOI Creative Commons
Muhammed Sit, Bekir Zahit Demiray, İbrahim Demir

и другие.

EarthArXiv (California Digital Library), Год журнала: 2022, Номер unknown

Опубликована: Сен. 26, 2022

The volume and variety of Earth data have increased as a result growing attention to climate change and, subsequently, the availability large-scale sensor networks remote sensing instruments. This has been an important resource for data-driven studies generate practical knowledge services, support environmental modeling forecasting needs, transform earth science research thanks computational resources popularity novel techniques like deep learning. Timely accurate simulation extreme events are critical planning mitigation in hydrology water resources. There is strong need short-term long-term forecasts streamflow, benefiting from recent developments learning methods. In this study, we review literature that employ tackling tasks either improve quality streamflow or forecast streamflow. study aims serve starting point by covering latest approaches those topics well highlighting problems, limitations, open questions with insights future directions.

Язык: Английский

Процитировано

9
EfficientRainNet: Smaller Neural Networks Based on EfficientNetV2 for Rainfall Nowcasting DOI Creative Commons
Muhammed Sit, Bong‐Chul Seo, Bekir Zahit Demiray

и другие.

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

Опубликована: Апрель 5, 2023

Rainfall nowcasting provides short-term, high-resolution information on the location, intensity, and timing of rainfall, which is crucial for weather forecasting, flood warning, emergency response. This can help people organizations make informed decisions to mitigate impact severe events reduce risk damage loss life. There are many attempts at tackling problem hand, whether it be numerical models or statistical that also comprise deep neural networks. Even though nowcast quite accurate nowadays has a saturated literature, current approaches mostly focus improving performance while computational burden keeps increasing. In this study, we propose EfficientRainNet, convolutional network architecture based mobile inverted residual linear bottleneck blocks with few alterations. We show EfficientRainNet able produce comparable results those encoder-decoder GRUs only fraction trainable parameters over radar rainfall dataset State Iowa. Also, most part, performs better than baselines using persistence- optical flow-based nowcasting, along another efficiency-focused architecture, Small Attention UNet.

Язык: Английский

Процитировано

4
TempNet – Temporal Super Resolution of Radar Rainfall Products with Residual CNNs DOI Creative Commons
Muhammed Sit, Bong‐Chul Seo, İbrahim Demir

и другие.

EarthArXiv (California Digital Library), Год журнала: 2022, Номер unknown

Опубликована: Сен. 22, 2022

The temporal and spatial resolution of rainfall data is crucial for environmental modeling studies in which its variability space time considered as a primary factor. Rainfall products from different remote sensing instruments (e.g., radar, satellite) have space-time resolutions because the differences their capabilities post-processing methods. In this study, we developed deep learning approach that augments with increased to complement relatively lower products. We propose neural network architecture based on Convolutional Neural Networks (CNNs) improve radar-based compare proposed model an optical flow-based interpolation method CNN-baseline model. methodology presented study could be used enhancing maps better imputation missing frames sequences 2D support hydrological flood forecasting studies.

Язык: Английский

Процитировано

5
Efficientrainnet: Memory Resilient Neural Networks Based on Efficientnetv2 for Rainfall Nowcasting DOI
Muhammed Sit, Bong‐Chul Seo, Bekir Zahit Demiray

и другие.

Опубликована: Янв. 1, 2023

Rainfall nowcasting provides short-term, high-resolution information on the location, intensity, and timing of rainfall, which is crucial for flood warning emergency response. This can help people make informed decisions to mitigate impact severe weather events reduce risk damage loss life. There are many attempts at tackling problem, whether it be numerical models or statistical models. Even though nowcast quite accurate nowadays problem has a saturated literature, current approaches mostly focus improving performance while computational burden keeps increasing. In this study, we propose EfficientRainNet, convolutional neural network architecture that based mobile inverted residual linear bottleneck blocks with few alterations. We show EfficientRainNet able produce comparable results those encoder-decoder GRUs only fraction trainable parameters over State Iowa.

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