Quantitative Estimation of Rainfall Rate Intensity Based on Deep Convolutional Neural Network and Radar Reflectivity Factor

Yang, Haitao; Tieqiao, Wang; Zhou, Xuesong; Dong, Jiwen; Gao, Xizhan; Niu, Sijie

doi:10.1145/3358528.3358582

Cited by 2 publications

(2 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Recent advancements in machine learning have facilitated the development of more sophisticated downscaling techniques. Convolutional Neural Networks (CNNs) and Long Short-Term Memory (LSTM) networks have been applied to downscaling tasks, showing improved performance over traditional statistical methods [24][25][26][27]. However, these machine learning-based techniques still face challenges in capturing intrinsic temporal dynamics and spatial relationships simultaneously [28].…”

Section: Introductionmentioning

confidence: 99%

A Temporal Downscaling Model for Gridded Geophysical Data with Enhanced Residual U-Net

Wang,

Li,

Peng

et al. 2024

Remote Sensing

View full text Add to dashboard Cite

Temporal downscaling of gridded geophysical data is essential for improving climate models, weather forecasting, and environmental assessments. However, existing methods often cannot accurately capture multi-scale temporal features, affecting their accuracy and reliability. To address this issue, we introduce an Enhanced Residual U-Net architecture for temporal downscaling. The architecture, which incorporates residual blocks, allows for deeper network structures without the risk of overfitting or vanishing gradients, thus capturing more complex temporal dependencies. The U-Net design inherently can capture multi-scale features, making it ideal for simulating various temporal dynamics. Moreover, we implement a flow regularization technique with advection loss to ensure that the model adheres to physical laws governing geophysical fields. Our experimental results across various variables within the ERA5 dataset demonstrate an improvement in downscaling accuracy, outperforming other methods.

show abstract

Section: Introductionmentioning

confidence: 99%

A Temporal Downscaling Model for Gridded Geophysical Data with Enhanced Residual U-Net

Wang,

Li,

Peng

et al. 2024

Remote Sensing

View full text Add to dashboard Cite

show abstract

“…2 Recent advancements in machine learning have facilitated the development of more sophisticated downscaling techniques. Convolutional Neural Networks (CNNs) and Long Short-Term Memory (LSTM) networks have been applied to downscaling tasks, showing improved performance over traditional statistical methods [14,15]. However, these machine learning-based techniques still face challenges in capturing intrinsic temporal dynamics and spatial relationships simultaneously [16].…”

Section: Introductionmentioning

confidence: 99%

A Temporal Downscaling Model for Gridded Geophysical Data with Enhanced Residual U-Net

Wang,

Li,

Peng

et al. 2023

Preprint

View full text Add to dashboard Cite

Temporal downscaling of gridded geophysical data is essential for improving climate models, weather forecasting, and environmental assessments. However, existing methods often could not accurately capture multi-scale temporal features, affecting their accuracy and reliability. To address this issue, we introduce an Enhanced Residual U-Net architecture for temporal downscaling. The architecture, which incorporates residual blocks, allows for deeper network structures without the risk of overfitting or vanishing gradients, thus capturing more complex temporal dependencies. The U-Net design inherently could capture multi-scale features, making it ideal for simulating various temporal dynamics. Moreover, we implement a flow regularization technique with advection loss to ensure that the model adheres to physical laws governing geophysical fields. Our experimental results across various variables within the ERA5 dataset demonstrate an improvement in downscaling accuracy, outperforming other methods.

show abstract

Quantitative Estimation of Rainfall Rate Intensity Based on Deep Convolutional Neural Network and Radar Reflectivity Factor

Cited by 2 publications

References 6 publications

A Temporal Downscaling Model for Gridded Geophysical Data with Enhanced Residual U-Net

A Temporal Downscaling Model for Gridded Geophysical Data with Enhanced Residual U-Net

A Temporal Downscaling Model for Gridded Geophysical Data with Enhanced Residual U-Net

Contact Info

Product

Resources

About