Deep learning‐based precipitation bias correction approach for <scp>Yin–He</scp> global spectral model

Hu, Yifan; Yin, Fukang; Zhang, Weimin

doi:10.1002/met.2032

Cited by 16 publications

(17 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Considering the normalcy, integrity, and accessibility of the data, the study uses the reanalysis dataset as the ground truth which is common in previous studies (e.g., Larraondo et al, 2019;Han et al, 2021;Hu et al, 2021). Given that there are still discrepancies between the reanalyzed precipitation data and observations, we will employ the observed data for additional testing and modeling in the future.…”

Section: Discussionmentioning

confidence: 99%

“…The encoder uses convolution and max-pooling layers to extract features at different levels, while the decoder is a reverse process using the same layers besides up-sampling layers to decode the features into correction fields. Recently, U-Net has been utilized in atmospheric science and proved to be effective and promising in weather prediction (Larraondo et al, 2019;Han et al, 2021;Hu et al, 2021).…”

Section: Modelsmentioning

confidence: 99%

“…CNN-based architectures, together with other DL approaches, are also utilized in the post-processing of NWP (Rasp and Lerch, 2018;Han et al, 2021;Hu et al, 2021). U-Net is a CNN-based architecture first proposed for biomedical segmentation, and has acquired some achievements in the estimate of weather factors (Ronneberger et al, 2015;Larraondo et al, 2019).…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Improving the heavy rainfall forecasting using a weighted deep learning model

Chen

Huang²,

Wang³

et al. 2023

Front. Environ. Sci.

View full text Add to dashboard Cite

Weather forecasting has been playing an important role in socio-economics. However, operational numerical weather prediction (NWP) is insufficiently accurate in terms of precipitation forecasting, especially for heavy rainfalls. Previous works on NWP bias correction utilizing deep learning (DL) methods mostly focused on a local region, and the China-wide precipitation forecast correction had not been attempted. Meanwhile, earlier studies imposed no particular focus on strong rainfalls despite their severe catastrophic impacts. In this study, we propose a DL model called weighted U-Net (WU-Net) that incorporates sample weights for various precipitation events to improve the forecasts of intensive precipitation in China. It is found that WU-Net can further improve the forecasting skill of heaviest rainfall comparing with the ordinary U-Net and ECMWF-IFS. Further analysis shows that this improvement increases with growing lead time, and distributes mainly in the eastern parts of China. This study suggests that a DL model considering the imbalance of the meteorological data could further improve the precipitation forecasting generated by numerical weather prediction.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Modelsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Improving the heavy rainfall forecasting using a weighted deep learning model

Chen

Huang²,

Wang³

et al. 2023

Front. Environ. Sci.

View full text Add to dashboard Cite

show abstract

“…They evaluated their approach by comparing it to another bias correction method based on the standard deviation method they introduced. Hu et al (2021b) proposed a CNN based on Unet to correct biases over Yin-He global spectral model (YHGSM) by inputting the geopotential, specific humidity, and vertical velocity on three pressure levels.…”

Section: Data Augmentation and Synthesismentioning

confidence: 99%

A Systematic Review of Deep Learning Applications in Interpolation and Extrapolation of Precipitation Data

Sit¹,

Demiray²,

Demir³

2022

Preprint

View full text Add to dashboard Cite

With technological enhancements, the volume, velocity, and variety (3Vs) of the raw digital Earth data have increased in recent years. Due to the increased availability of computer resources and the growing popularity of deep learning applications, this data has been a crucial source for data-driven studies that have transformed the fields of climate and earth science. One of the critical data sources is precipitation supporting climate and earth science studies on modeling, forecasting, and preparedness for extreme events (i.e., floods, droughts, pollution transport). In this study, we worked on an extensive review of manuscripts focusing on use of deep learning methods to tackle challenges either to improve the quality or extrapolate (forecast) rainfall datasets. The purpose of this study is to summarize the most recent developments in deep learning approaches for forecasting rainfall or improving rainfall datasets, as well as highlighting issues, shortcomings, and open questions with insightful recommendations for future directions.

show abstract

“…Peter Grönquist et al [19] adopted U-Net and multi-level residual networks with several ensemble members of global numerical model, and the results showed significant improvements in temperature and precipitation at 850 hPa. Yi-Fan Hu et al [20] used the U-Net with attention mechanism to correct the bias of precipitation for global numerical model, and their model showed good performance in reducing RMSE and improving the threat scores while utilizing multiple auxiliary factors. In fact, most of current MME forecast methods did not focus on the special structure of numeric forecast results, and showed limitations in improving multiple dimensions of the original forecast simultaneously.…”

Section: Related Workmentioning

confidence: 99%

SWAR: A Deep Multi-Model Ensemble Forecast Method with Spatial Grid and 2-D Time Structure Adaptability for Sea Level Pressure

Zhang

Jin

2022

Information

View full text Add to dashboard Cite

The multi-model ensemble (MME) forecast for meteorological elements has been proved many times to be more skillful than the single model. It improves the forecast quality by integrating multiple sets of numerical forecast results with different spatial-temporal characteristics. Currently, the main numerical forecast results present a grid structure formed by longitude and latitude lines in space and a special two-dimensional time structure in time, namely the initial time and the lead time, compared with the traditional one-dimensional time. These characteristics mean that many MME methods have limitations in further improving forecast quality. Focusing on this problem, we propose a deep MME forecast method that suits the special structure. At spatial level, our model uses window self-attention and shifted window attention to aggregate information. At temporal level, we propose a recurrent like neural network with rolling structure (Roll-RLNN) which is more suitable for two-dimensional time structure that widely exists in the institutions of numerical weather prediction (NWP) with running service. In this paper, we test the MME forecast for sea level pressure as the forecast characteristics of the essential meteorological element vary clearly across institutions, and the results show that our model structure is effective and can make significant forecast improvements.

show abstract

Deep learning‐based precipitation bias correction approach for Yin–He global spectral model

Cited by 16 publications

References 27 publications

Improving the heavy rainfall forecasting using a weighted deep learning model

Improving the heavy rainfall forecasting using a weighted deep learning model

A Systematic Review of Deep Learning Applications in Interpolation and Extrapolation of Precipitation Data

SWAR: A Deep Multi-Model Ensemble Forecast Method with Spatial Grid and 2-D Time Structure Adaptability for Sea Level Pressure

Contact Info

Product

Resources

About