Xiaojiang Song
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Xiaojiang Song has a total of 22 co-authors. Here are the top co-authors by number of shared publications:
- Junyu Dong
Ocean University of China
3 shared publications - Wei Zhang
State Key Laboratory of Physical Oceanography, Ocean University of China, Qingdao 266100, China
3 shared publications - Anboyu Guo
National Marine Environment Forecasting Center, Beijing 100082, China
2 shared publications Boyu Guoan
2 shared publicationsRenbo Pang
2 shared publications- Renbo Pang
National Marine Environment Forecasting Center, Beijing 100082, China
2 shared publications
Latest Publications
- Open Access
- 31 October 2025
- Published by MDPI AG in Remote Sensing
- Vol. 17 (21) , 3609
Robust Synthesis Weather Radar from Satellite Imagery: A Light/Dark Classification and Dual-Path Processing Approach
Weather radar reflectivity plays a critical role in precipitation estimation and convective storm identification. However, due to terrain limitations and the uneven spatial distribution of radar stations, oceanic regions have long suffered from a lack of radar observations, resulting in extensive monitoring gaps. Geostationary meteorological satellites have wide-area coverage and near-real-time observation capability, offering a viable solution for synthesizing radar reflectivity in these regions. Most previous synthesis studies have adopted fixed time-window data partitioning, which introduces significant noise into visible-light observations under large-scale, low-illumination conditions, thereby degrading synthesis quality. To address this issue, we propose an integrated deep-learning method that combines illumination-based classification and reflectivity synthesis to enhance the accuracy of radar reflectivity synthesis from geostationary meteorological satellites. This approach integrates a classification network with a synthesis network. First, visible-light observations from the Himawari-8 satellite are classified based on illumination conditions to separate valid signals from noise; then, noise-free infrared observations and multimodal fused data are fed into dedicated synthesis networks to generate composite reflectivity products. In experiments, the proposed method outperformed the baseline approach in regions with strong convection (≥35 dBZ), with a 9.5% improvement in the critical success index, a 7.5% increase in the probability of detection, and a 6.1% reduction in the false alarm rate. Additional experiments confirmed the applicability and robustness of the method across various complex scenarios.
- 31 October 2025
- Published by MDPI AG in Remote Sensing
- Vol. 17 (21) , 3609
Open AccessRobust Synthesis Weather Radar from Satellite Imagery: A Light/Dark Classification and Dual-Path Processing Approach
Weather radar reflectivity plays a critical role in precipitation estimation and convective storm identification. However, due to terrain limitations and the uneven spatial distribution of radar stations, oceanic regions have long suffered from a lack of radar observations, resulting in extensive monitoring gaps. Geostationary meteorological satellites have wide-area coverage and near-real-time observation capability, offering a viable solution for synthesizing radar reflectivity in these regions. Most previous synthesis studies have adopted fixed time-window data partitioning, which introduces significant noise into visible-light observations under large-scale, low-illumination conditions, thereby degrading synthesis quality. To address this issue, we propose an integrated deep-learning method that combines illumination-based classification and reflectivity synthesis to enhance the accuracy of radar reflectivity synthesis from geostationary meteorological satellites. This approach integrates a classification network with a synthesis network. First, visible-light observations from the Himawari-8 satellite are classified based on illumination conditions to separate valid signals from noise; then, noise-free infrared observations and multimodal fused data are fed into dedicated synthesis networks to generate composite reflectivity products. In experiments, the proposed method outperformed the baseline approach in regions with strong convection (≥35 dBZ), with a 9.5% improvement in the critical success index, a 7.5% increase in the probability of detection, and a 6.1% reduction in the false alarm rate. Additional experiments confirmed the applicability and robustness of the method across various complex scenarios.
- Open Access
- 11 February 2025
- Published by MDPI AG in Remote Sensing
- Vol. 17 (4) , 610
A Multi-Scale Fusion Deep Learning Approach for Wind Field Retrieval Based on Geostationary Satellite Imagery
Wind field retrieval, a crucial component of weather forecasting, has been significantly enhanced by recent advances in deep learning. However, existing approaches that are primarily focused on wind speed retrieval are limited by their inability to achieve real-time, full-coverage retrievals at large scales. To address this problem, we propose a novel multi-scale fusion retrieval (MFR) method, leveraging geostationary observation satellites. At the mesoscale, MFR incorporates a cloud-to-wind transformer model, which employs local self-attention mechanisms to extract detailed wind field features. At large scales, MFR incorporates a multi-encoder coordinate U-net model, which incorporates multiple encoders and utilises coordinate information to fuse meso- to large-scale features, enabling accurate and regionally complete wind field retrievals, while reducing the computational resources required. The MFR method was validated using Level 1 data from the Himawari-8 satellite, covering a geographic range of 0–60°N and 100–160°E, at a resolution of 0.25°. Wind field retrieval was accomplished within seconds using a single graphics processing unit. The mean absolute error of wind speed obtained by the MFR was 0.97 m/s, surpassing the accuracy of the CFOSAT and HY-2B Level 2B wind field products. The mean absolute error for wind direction achieved by the MFR was 23.31°, outperforming CFOSAT Level 2B products and aligning closely with HY-2B Level 2B products. The MFR represents a pioneering approach for generating initial fields for large-scale grid forecasting models.
- 11 February 2025
- Published by MDPI AG in Remote Sensing
- Vol. 17 (4) , 610
Open AccessA Multi-Scale Fusion Deep Learning Approach for Wind Field Retrieval Based on Geostationary Satellite Imagery
Wind field retrieval, a crucial component of weather forecasting, has been significantly enhanced by recent advances in deep learning. However, existing approaches that are primarily focused on wind speed retrieval are limited by their inability to achieve real-time, full-coverage retrievals at large scales. To address this problem, we propose a novel multi-scale fusion retrieval (MFR) method, leveraging geostationary observation satellites. At the mesoscale, MFR incorporates a cloud-to-wind transformer model, which employs local self-attention mechanisms to extract detailed wind field features. At large scales, MFR incorporates a multi-encoder coordinate U-net model, which incorporates multiple encoders and utilises coordinate information to fuse meso- to large-scale features, enabling accurate and regionally complete wind field retrievals, while reducing the computational resources required. The MFR method was validated using Level 1 data from the Himawari-8 satellite, covering a geographic range of 0–60°N and 100–160°E, at a resolution of 0.25°. Wind field retrieval was accomplished within seconds using a single graphics processing unit. The mean absolute error of wind speed obtained by the MFR was 0.97 m/s, surpassing the accuracy of the CFOSAT and HY-2B Level 2B wind field products. The mean absolute error for wind direction achieved by the MFR was 23.31°, outperforming CFOSAT Level 2B products and aligning closely with HY-2B Level 2B products. The MFR represents a pioneering approach for generating initial fields for large-scale grid forecasting models.
- Open Access
- 6 August 2024
- Published by MDPI AG in Remote Sensing
- Vol. 16 (16) , 2871
Oceanic Precipitation Nowcasting Using a UNet-Based Residual and Attention Network and Real-Time Himawari-8 Images
Qualitative precipitation forecasting plays a vital role in marine operational services. However, predicting heavy precipitation over the open ocean presents a significant challenge due to the limited availability of ground-based radar observations far from coastal regions. Recent advancements in deep learning models offer potential for oceanic precipitation nowcasting using satellite images. This study implemented an enhanced UNet model with an attention mechanism and a residual architecture (RA-UNet) to predict the precipitation rate within a 90 min time frame. A comparative analysis with the standard UNet and UNet with an attention algorithm revealed that the RA-UNet method exhibited superior accuracy metrics, such as the critical ratio index and probability of detection, with fewer false alarms. Two typical cases demonstrated that RA-UNet had a better ability to forecast monsoon precipitation as well as intense precipitation in a tropical cyclone. These findings indicate the greater potential of the RA-UNet approach for nowcasting heavy precipitation over the ocean using satellite imagery.
- 6 August 2024
- Published by MDPI AG in Remote Sensing
- Vol. 16 (16) , 2871
Open AccessOceanic Precipitation Nowcasting Using a UNet-Based Residual and Attention Network and Real-Time Himawari-8 Images
Qualitative precipitation forecasting plays a vital role in marine operational services. However, predicting heavy precipitation over the open ocean presents a significant challenge due to the limited availability of ground-based radar observations far from coastal regions. Recent advancements in deep learning models offer potential for oceanic precipitation nowcasting using satellite images. This study implemented an enhanced UNet model with an attention mechanism and a residual architecture (RA-UNet) to predict the precipitation rate within a 90 min time frame. A comparative analysis with the standard UNet and UNet with an attention algorithm revealed that the RA-UNet method exhibited superior accuracy metrics, such as the critical ratio index and probability of detection, with fewer false alarms. Two typical cases demonstrated that RA-UNet had a better ability to forecast monsoon precipitation as well as intense precipitation in a tropical cyclone. These findings indicate the greater potential of the RA-UNet approach for nowcasting heavy precipitation over the ocean using satellite imagery.
- Open Access
A Deep-learning Real-time Bias Correction Method for Significant Wave Height Forecasts in the Western North Pacific
Significant wave height is one of the most important parameters characterizing ocean waves, and accurate numerical ocean wave forecasting is crucial for coastal protection and shipping. However, due to the randomness and nonlinearity of the wind fields that generate ocean waves and the complex interaction between wave and wind fields, current forecasts of numerical ocean waves have biases. In this study, a spatiotemporal deep-learning method was employed to correct gridded SWH forecasts from the ECMWF-IFS. This method was built on the trajectory gated recurrent unit deep neural network,and it conducts real-time rolling correction for the 0-240h SWH forecasts from ECMWF-IFS. The correction model is co-driven by wave and wind fields, providing better results than those based on wave fields alone. A novel pixel-switch loss function was developed. The pixel-switch loss function can dynamically fine-tune the pre-trained correction model, focusing on pixels with large biases in SWH forecasts. According to the seasonal characteristics of SWH, four correction models were constructed separately, for spring, summer, autumn, and winter. The experimental results show that, compared with the original ECMWF SWH predictions, the correction was most effective in spring, when the mean absolute error decreased by 12.972~46.237%. Although winter had the worst performance, the mean absolute error decreased by 13.794~38.953%. The corrected results improved the original ECMWF SWH forecasts under both normal and extreme weather conditions, indicating that our SWH correction model is robust and generalizable.
Open AccessA Deep-learning Real-time Bias Correction Method for Significant Wave Height Forecasts in the Western North Pacific
Significant wave height is one of the most important parameters characterizing ocean waves, and accurate numerical ocean wave forecasting is crucial for coastal protection and shipping. However, due to the randomness and nonlinearity of the wind fields that generate ocean waves and the complex interaction between wave and wind fields, current forecasts of numerical ocean waves have biases. In this study, a spatiotemporal deep-learning method was employed to correct gridded SWH forecasts from the ECMWF-IFS. This method was built on the trajectory gated recurrent unit deep neural network,and it conducts real-time rolling correction for the 0-240h SWH forecasts from ECMWF-IFS. The correction model is co-driven by wave and wind fields, providing better results than those based on wave fields alone. A novel pixel-switch loss function was developed. The pixel-switch loss function can dynamically fine-tune the pre-trained correction model, focusing on pixels with large biases in SWH forecasts. According to the seasonal characteristics of SWH, four correction models were constructed separately, for spring, summer, autumn, and winter. The experimental results show that, compared with the original ECMWF SWH predictions, the correction was most effective in spring, when the mean absolute error decreased by 12.972~46.237%. Although winter had the worst performance, the mean absolute error decreased by 13.794~38.953%. The corrected results improved the original ECMWF SWH forecasts under both normal and extreme weather conditions, indicating that our SWH correction model is robust and generalizable.
- Open Access
A Deep Learning Method for Real-time Bias Correction of Wind Field Forecasts in the Western North Pacific
Forecasts by the European Centre for Medium-Range Weather Forecasts (ECMWF; EC for short) can provide a basis for the establishment of maritime-disaster warning systems, but they contain some systematic biases.The fifth-generation EC atmospheric reanalysis (ERA5) data have high accuracy, but are delayed by about 5 days. To overcome this issue, a spatiotemporal deep-learning method could be used for nonlinear mapping between EC and ERA5 data, which would improve the quality of EC wind forecast data in real time. In this study, we developed the Multi-Task-Double Encoder Trajectory Gated Recurrent Unit (MT-DETrajGRU) model, which uses an improved double-encoder forecaster architecture to model the spatiotemporal sequence of the U and V components of the wind field; we designed a multi-task learning loss function to correct wind speed and wind direction simultaneously using only one model. The study area was the western North Pacific (WNP), and real-time rolling bias corrections were made for 10-day wind-field forecasts released by the EC between December 2020 and November 2021, divided into four seasons. Compared with the original EC forecasts, after correction using the MT-DETrajGRU model the wind speed and wind direction biases in the four seasons were reduced by 8-11% and 9-14%, respectively. In addition, the proposed method modelled the data uniformly under different weather conditions. The correction performance under normal and typhoon conditions was comparable, indicating that the data-driven mode constructed here is robust and generalizable.
Open AccessA Deep Learning Method for Real-time Bias Correction of Wind Field Forecasts in the Western North Pacific
Forecasts by the European Centre for Medium-Range Weather Forecasts (ECMWF; EC for short) can provide a basis for the establishment of maritime-disaster warning systems, but they contain some systematic biases.The fifth-generation EC atmospheric reanalysis (ERA5) data have high accuracy, but are delayed by about 5 days. To overcome this issue, a spatiotemporal deep-learning method could be used for nonlinear mapping between EC and ERA5 data, which would improve the quality of EC wind forecast data in real time. In this study, we developed the Multi-Task-Double Encoder Trajectory Gated Recurrent Unit (MT-DETrajGRU) model, which uses an improved double-encoder forecaster architecture to model the spatiotemporal sequence of the U and V components of the wind field; we designed a multi-task learning loss function to correct wind speed and wind direction simultaneously using only one model. The study area was the western North Pacific (WNP), and real-time rolling bias corrections were made for 10-day wind-field forecasts released by the EC between December 2020 and November 2021, divided into four seasons. Compared with the original EC forecasts, after correction using the MT-DETrajGRU model the wind speed and wind direction biases in the four seasons were reduced by 8-11% and 9-14%, respectively. In addition, the proposed method modelled the data uniformly under different weather conditions. The correction performance under normal and typhoon conditions was comparable, indicating that the data-driven mode constructed here is robust and generalizable.