Danyi Sun

Danyi Sun

Auto-generated profile, based on publicly available information

Danyi Sun

Ministry of Education Key Laboratory for Earth System Modeling Department of Earth System Science (DESS) Tsinghua University Beijing China

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
26 July 2023 in Geophysical Research Letters
Verified
Journal Article
Open access
DSDanyi Sun
Danyi Sun
WHWenyu Huang
Wenyu Huang
ZYZifan Yang
Zifan Yang
YLYong Luo
Yong Luo
JLJing-Jia Luo
Jing-Jia Luo
Bin WangBin Wang
Bin Wang
Wintertime precipitation, especially snowstorms, significantly impacts people's lives. However, the current forecast skill of wintertime precipitation is still low. Based on data augmentation (DA) and deep learning, we propose a DABU‐Net which improves the Global Forecast System wintertime precipitation forecast over southeastern China. We build three independent models for the forecast lead times of 24, 48, and 72 hr, respectively. After using DABU‐Net, the mean Root Mean Squared Errors (RMSEs) of the wintertime precipitation at the three lead times are reduced by 19.08%, 25.00%, and 22.37%, respectively. The threat scores (TS) are all significantly increased at the thresholds of 1, 5, 10, 15, and 20 mm day−1 for the three lead times. During heavy precipitation days, the RMSEs are decreased by 14% and TS are increased by 7% at the lead times within 48 hr. Therefore, combining DA and deep learning has great prospects in precipitation forecasting.

26 June 2024 in Journal of Geophysical Research: Atmospheres
Verified
Journal Article
Closed access
SFShu Fu
Shu Fu
WHWenyu Huang
Wenyu Huang
JLJing-Jia Luo
Jing-Jia Luo
DLDongqing Liu
Dongqing Liu
DSDanyi Sun
Danyi Sun
BWBin Wang
Bin Wang

15 May 2023
Verified
Conference Paper
Open access
DSDanyi Sun
Danyi Sun
WHWenyu Huang
Wenyu Huang
YLYong Luo
Yong Luo
JLJingjia Luo
Jingjia Luo
JWJonathon Wright
Jonathon Wright
BWBin Wang
Bin Wang
Ocean waves, especially extreme waves, are vital for air-sea interaction and shipping. However, current wave models still have significant biases, especially under extreme wind conditions. Based on a numerical wave model and a deep learning model, we accurately predict the significant wave height (SWH) of the Northwest Pacific Ocean. For each day in 2017-2021, we conducted a 3-day hindcast experiment using WAVEWATCH3 (WW3) to obtain the SWH forecasts at lead times of 24, 48, and 72hr, forced by GFS real-time forecast surface winds. The deep learning-based bias correction method is BU-Net by adding batch normalization layers to a U-Net, which could improve the accuracy. Due to the use of BU-Net, the mean Root Mean Squared Errors (RMSEs) of the SWH forecast from WW3 at lead times of 24, 48, and 72hr are reduced from 0.35m to 0.21m, 0.39m to 0.24m, and 0.43m to 0.30m, corresponding to drop percentages of 40%, 38%, and 30%, respectively. During typhoon passages, the drop percentages of RMSEs reach 45%, 42%, and 35% for three lead times. Therefore, combining numerical models and deep learning algorithms is very promising in ocean wave forecasting.

15 May 2023
Verified
Conference Paper
Open access
SFShu Fu
Shu Fu
WHWenyu Huang
Wenyu Huang
RLRunqing Lv
Runqing Lv
ZYZifan Yang
Zifan Yang
TQTianpei Qiu
Tianpei Qiu
BWBin Wang
Bin Wang
A new ocean-atmosphere-wave regional coupled model named Windwave version 1.0 for simulating and predicting winds and waves has been developed for the Northwest Pacific Ocean. In particular, the global-to-regional nesting technique is adopted for the ocean component to alleviate the bias due to the inconsistency in the lateral boundary. This paper is devoted to describing the coupling details of Windwave and the initialization scheme and assessing its basic performance, especially in predicting surface winds and significant wave heights (SWH) on the weather timescale. The control experiment set contains 31 experiments for August 2020, with seven typhoons passing through the Northwest Pacific. Each experiment starts at 0:00 am UTC of each day and runs for three days. Experiment results show that the new coupled model performs well in predicting surface winds, SWH, surface air temperature, and sea surface temperature on the weather timescale. In particular, the Root Mean Square Errors (RMSEs) of surface winds at 10 m height over the Northwest Pacific of the control experiment are 1.82 m s-1, 2.22 m s-1, and 2.59 m s-1, respectively, at lead times of 24 h, 48 h, and 72 h. Meanwhile, the RMSEs of SWH at lead times of 24 h, 48 h, and 72 h are 0.39 m, 0.43 m, and 0.51 m. In addition, we have explored the impacts of the different sea surface aerodynamic roughness parameterization schemes on predicting surface winds and SWH. In total, five different sea surface aerodynamic roughness parameterization schemes are adopted, corresponding to one control set and four sensitivity sets of experiments. Under normal conditions, the sea surface aerodynamic roughness parameterization scheme considering the effects of wind-wave direction tends to perform better for winds and waves, while that depending on wave age and SWH tends to perform worse. Under extreme wind and wave conditions, the schemes considering the effects of wind-wave direction and that considering wave age and peak wave length have better performance. These findings can provide new insights for developing a more advanced sea surface aerodynamic roughness parameterization scheme.

25 August 2026 in Journal of Geophysical Research: Atmospheres
Verified
Journal Article
Open access
PDF file
DLDianhewen Liu
Dianhewen Liu
WHWenyu Huang
Wenyu Huang
YLYongqian Liu
Yongqian Liu
DCDeliang Chen
Deliang Chen
DSDanyi Sun
Danyi Sun
HFHaohuan Fu
Haohuan Fu
Reliable subseasonal maritime wind forecasts are essential for navigation safety and disaster prevention, yet current forecasting systems show noticeable biases over China's coastal waters. Here, we introduce TDSwin‐UnetSS (Time‐embedded Downscaling Swin‐Transformer U‐Net for SubSeasonal forecasting), an asymmetric hybrid model that integrates the Swin Transformer with a U‐Net architecture. The model incorporates: (a) Weibull distribution constraints to preserve the wind‐speed probability density, (b) spatial downscaling from 1.5 to 0.25 resolution, (c) time embedding for simultaneous 3–6 week lead‐time corrections, and (d) spatially adaptive learning focused on extreme wind‐prone regions. Applied to ECMWF S2S forecasts, TDSwin‐UnetSS reduces root mean squared error (RMSE) by 13.41%–16.67%, mean absolute error (MAE) by 10.69%–13.67%, and the absolute value of the bias by 80.00%–90.00%, while increasing anomaly correlation coefficient (ACC) by 18.18%–76.19% and structural similarity index measure (SSIM) by 5.71%–10.77% across different lead times, with RMSE reductions exceeding 19.76% during extreme wind events. This study demonstrates the application of the Swin Transformer to subseasonal wind bias correction, highlighting its potential for extended‐range forecasting through effective multi‐scale feature learning and physics‐informed hybrid modeling.