Liang Sun
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Liang Sun has a total of 51 co-authors. Here are the top co-authors by number of shared publications:
- Linxiao Yang
DAMO Academy, Alibaba Group, Hangzhou, Zhejiang, China
7 shared publications - Tian Zhou
Alibaba Group, Hangzhou, China
7 shared publications - Xinyue Gu
DAMO Academy, Alibaba Group, Hangzhou, Zhejiang, China
5 shared publications - Ziqing Ma
DAMO Academy, Alibaba Group, Hangzhou, China
5 shared publications - Peisong Niu
DAMO Academy, Alibaba Group, Hangzhou, China
4 shared publications - Qingsong Wen
Alibaba Group
4 shared publications
Latest Publications
- Open Access
- 6 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 8204-8211
eForecaster-MultiRegion: A Deployed Day-Ahead Load Forecasting System for Provincial Grid Operations
- 6 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 8204-8211
Open AccesseForecaster-MultiRegion: A Deployed Day-Ahead Load Forecasting System for Provincial Grid Operations
- 5 October 2026
- Published by Springer Nature
- p. 135-152
Pushing the Limits of High-Resolution Weather Forecasting Through Data Scaling
- 5 October 2026
- Published by Springer Nature
- p. 135-152
Pushing the Limits of High-Resolution Weather Forecasting Through Data Scaling
- Open Access
- 8 August 2026
- Published by Association for Computing Machinery (ACM)
- p. 12303-12314
Skillful Kilometer-Scale Regional Weather Forecasting via Global and Regional Coupling
Data-driven weather models have advanced global medium-range forecasting, yet high-resolution regional prediction remains challenging due to unresolved multiscale interactions between large-scale dynamics and small-scale processes such as terrain-induced circulations and coastal effects. This paper presents a global-regional coupling framework for kilometer-scale regional weather forecasting that synergistically couples a pretrained Transformer-based global model with a high-resolution regional network via a novel bidirectional coupling module, Baguan-Regional. Baguan-Regional dynamically identifies meteorologically critical regions through adaptive key-position sampling and enables cross-scale feature interaction through dedicated attention mechanisms. The framework produces forecasts at 0.05° (~5km) and 1-hour resolution over China, significantly outperforming operational NWP and AI baselines on both gridded reanalysis data and real-time weather station observations. It exhibits exceptional skill in capturing fine-grained phenomena, such as orographic wind patterns and Foehn warming, demonstrating effective global-scale coherence with high-resolution fidelity. The code is available at https://github.com/DAMO-DI-ML/Baguan-Regional.
- 8 August 2026
- Published by Association for Computing Machinery (ACM)
- p. 12303-12314
Open AccessSkillful Kilometer-Scale Regional Weather Forecasting via Global and Regional Coupling
Data-driven weather models have advanced global medium-range forecasting, yet high-resolution regional prediction remains challenging due to unresolved multiscale interactions between large-scale dynamics and small-scale processes such as terrain-induced circulations and coastal effects. This paper presents a global-regional coupling framework for kilometer-scale regional weather forecasting that synergistically couples a pretrained Transformer-based global model with a high-resolution regional network via a novel bidirectional coupling module, Baguan-Regional. Baguan-Regional dynamically identifies meteorologically critical regions through adaptive key-position sampling and enables cross-scale feature interaction through dedicated attention mechanisms. The framework produces forecasts at 0.05° (~5km) and 1-hour resolution over China, significantly outperforming operational NWP and AI baselines on both gridded reanalysis data and real-time weather station observations. It exhibits exceptional skill in capturing fine-grained phenomena, such as orographic wind patterns and Foehn warming, demonstrating effective global-scale coherence with high-resolution fidelity. The code is available at https://github.com/DAMO-DI-ML/Baguan-Regional.
- Open Access
- 8 August 2026
- Published by Association for Computing Machinery (ACM)
- p. 11621-11632
RainCast: A High-Resolution 72-Hour Short-Term Precipitation Forecasting Model
Accurate short-term precipitation forecasting, which targets predictions up to 3 days ahead, has long been challenging, mainly due to extreme sample imbalance and complex multiscale physical processes. Existing regression- or classification-based deep learning methods often produce over-smoothed precipitation fields, lack physical guidance, and provide limited capability for uncertainty quantification, while radar-based nowcasting methods are unsuitable for multi-day forecasting. To address these limitations, we propose RainCast, a high-resolution framework for hourly precipitation forecasting over China up to 72 hours ahead at 0.05° resolution. RainCast incorporates two key designs: (1) a physics-guided feature extractor, which emulates continuity-equation-based diagnostics to extract vorticity, divergence, and vertical-motion-related signals from circulation fields; and (2) a multi-head output design that supports both deterministic forecasts with a regression head and probabilistic multi-member forecasts with an ensemble head, thereby reducing over-smoothing. Experiments show that RainCast consistently outperforms baselines. For heavy rainfall events (50 mm/24 h), RainCast improves CSI by up to 62.82% over GFS, improves CRPS by 19.35% over GEFS. And interpretability analysis further identifies 600-hPa temperature as a key signal for East Asian precipitation forecasting, likely related to hydrometeor phase transitions near the freezing–melting layer.
- 8 August 2026
- Published by Association for Computing Machinery (ACM)
- p. 11621-11632
Open AccessRainCast: A High-Resolution 72-Hour Short-Term Precipitation Forecasting Model
Accurate short-term precipitation forecasting, which targets predictions up to 3 days ahead, has long been challenging, mainly due to extreme sample imbalance and complex multiscale physical processes. Existing regression- or classification-based deep learning methods often produce over-smoothed precipitation fields, lack physical guidance, and provide limited capability for uncertainty quantification, while radar-based nowcasting methods are unsuitable for multi-day forecasting. To address these limitations, we propose RainCast, a high-resolution framework for hourly precipitation forecasting over China up to 72 hours ahead at 0.05° resolution. RainCast incorporates two key designs: (1) a physics-guided feature extractor, which emulates continuity-equation-based diagnostics to extract vorticity, divergence, and vertical-motion-related signals from circulation fields; and (2) a multi-head output design that supports both deterministic forecasts with a regression head and probabilistic multi-member forecasts with an ensemble head, thereby reducing over-smoothing. Experiments show that RainCast consistently outperforms baselines. For heavy rainfall events (50 mm/24 h), RainCast improves CSI by up to 62.82% over GFS, improves CRPS by 19.35% over GEFS. And interpretability analysis further identifies 600-hPa temperature as a key signal for East Asian precipitation forecasting, likely related to hydrometeor phase transitions near the freezing–melting layer.
- Open Access
- 8 August 2026
- Published by Association for Computing Machinery (ACM)
- p. 7785-7796
Integrating Weather Foundation Model and Satellite to Enable Fine-Grained Solar Irradiance Forecasting
Accurate day-ahead solar irradiance forecasting is essential for integrating solar energy into the power grid. However, it remains challenging due to the pronounced diurnal cycle and inherently complex cloud dynamics. Current methods either lack fine-scale resolution (e.g., numerical weather prediction, weather foundation models) or degrade at longer lead times (e.g., satellite extrapolation). We propose Baguan-solar, a two-stage multimodal framework that fuses forecasts from Baguan, a global weather foundation model, with high-resolution geostationary satellite imagery to produce 24-hour irradiance forecasts at kilometer scale. Its decoupled two-stage design first forecasts day-night continuous intermediates (e.g., cloud cover) and then infers irradiance, while its modality fusion jointly preserves fine-scale cloud structures from satellite and large-scale constraints from Baguan forecasts. Evaluated over East Asia using CLDAS as ground truth, Baguan-solar outperforms strong baselines (including ECMWF IFS, vanilla Baguan, and SolarSeer), reducing RMSE by 16.08% and better resolving cloud-induced transients. An operational deployment of Baguan-solar has supported solar power forecasting in an eastern province in China, since July 2025. Our code is accessible at https://github.com/DAMO-DI-ML/Baguansolar.git.
- 8 August 2026
- Published by Association for Computing Machinery (ACM)
- p. 7785-7796
Open AccessIntegrating Weather Foundation Model and Satellite to Enable Fine-Grained Solar Irradiance Forecasting
Accurate day-ahead solar irradiance forecasting is essential for integrating solar energy into the power grid. However, it remains challenging due to the pronounced diurnal cycle and inherently complex cloud dynamics. Current methods either lack fine-scale resolution (e.g., numerical weather prediction, weather foundation models) or degrade at longer lead times (e.g., satellite extrapolation). We propose Baguan-solar, a two-stage multimodal framework that fuses forecasts from Baguan, a global weather foundation model, with high-resolution geostationary satellite imagery to produce 24-hour irradiance forecasts at kilometer scale. Its decoupled two-stage design first forecasts day-night continuous intermediates (e.g., cloud cover) and then infers irradiance, while its modality fusion jointly preserves fine-scale cloud structures from satellite and large-scale constraints from Baguan forecasts. Evaluated over East Asia using CLDAS as ground truth, Baguan-solar outperforms strong baselines (including ECMWF IFS, vanilla Baguan, and SolarSeer), reducing RMSE by 16.08% and better resolving cloud-induced transients. An operational deployment of Baguan-solar has supported solar power forecasting in an eastern province in China, since July 2025. Our code is accessible at https://github.com/DAMO-DI-ML/Baguansolar.git.
- Open Access
- 10 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 6093-6101
SolarMAE: A Unified framework for Regional Centralized and Distributed Solar Power Forecasting with Weather Pre-training
- 10 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 6093-6101
Open AccessSolarMAE: A Unified framework for Regional Centralized and Distributed Solar Power Forecasting with Weather Pre-training
- Open Access
- 3 August 2025
- Published by Association for Computing Machinery (ACM)
- p. 4330-4340
EMD-Period: Detecting Multi-periodicity in Industrial Cloud Clusters via Time-Frequency Decomposition
- 3 August 2025
- Published by Association for Computing Machinery (ACM)
- p. 4330-4340
Open AccessEMD-Period: Detecting Multi-periodicity in Industrial Cloud Clusters via Time-Frequency Decomposition
- Open Access
- 3 August 2025
- Published by Association for Computing Machinery (ACM)
- p. 3507-3517
When Interpretability Meets Generalization: Delta-GAM for Robust Extrapolation in Out-of-Distribution Settings
- 3 August 2025
- Published by Association for Computing Machinery (ACM)
- p. 3507-3517
Open AccessWhen Interpretability Meets Generalization: Delta-GAM for Robust Extrapolation in Out-of-Distribution Settings
- Open Access
- 3 August 2025
- Published by Association for Computing Machinery (ACM)
- p. 2186-2197
Utilizing Strategic Pre-training to Reduce Overfitting: Baguan - A Pre-trained Weather Forecasting Model
- 3 August 2025
- Published by Association for Computing Machinery (ACM)
- p. 2186-2197
Open AccessUtilizing Strategic Pre-training to Reduce Overfitting: Baguan - A Pre-trained Weather Forecasting Model
- Open Access
- 3 August 2025
- Published by Association for Computing Machinery (ACM)
- p. 2010-2020
Physics-Guided Learning of Meteorological Dynamics for Weather Downscaling and Forecasting
- 3 August 2025
- Published by Association for Computing Machinery (ACM)
- p. 2010-2020
Open AccessPhysics-Guided Learning of Meteorological Dynamics for Weather Downscaling and Forecasting