Lei She
Research Subjects
Lei She has a total of 7 co-authors. Here are the top co-authors by number of shared publications:
- Jie Shao
School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China
3 shared publications - Farah Naz
School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China
2 shared publications - Chenghong Zhang
Institute of Plateau Meteorology, China Meteorological Administration, Chengdu 610299, China
1 shared publication - Chenghong Zhang
Institute of Plateau Meteorology, China Meteorological Administration, Chengdu, China
1 shared publication - Muhammad Sinan
School of Mathematical Sciences, University of Electronic Science and Technology of China, Chengdu 611731, China
1 shared publication - Xin Man
Shenzhen Institute for Advanced Study, University of Electronic Science and Technology of China, Shenzhen, China
1 shared publication
Latest Publications
- 8 September 2026
- Published by Springer Nature in Applied Intelligence
- Vol. 56 (14) , 408
Enhancing NWP precipitation forecasting with Rain-PostEFNet: A multi-scale deep learning approach
- 8 September 2026
- Published by Springer Nature in Applied Intelligence
- Vol. 56 (14) , 408
Enhancing NWP precipitation forecasting with Rain-PostEFNet: A multi-scale deep learning approach
- Open Access
LLMDiff: Diffusion Model Using Frozen LLM Transformers for Precipitation Nowcasting
Precipitation nowcasting, which involves the short-term, high-resolution prediction of rainfall, plays a crucial role in various real-world applications. In recent years, researchers have increasingly utilized deep learning-based methods in precipitation nowcasting. The exponential growth of spatiotemporal observation data has heightened interest in recent advancements such as denoising diffusion models, which offer appealing prospects due to their inherent probabilistic nature that aligns well with the complexities of weather forecasting. Successful application of diffusion models in rainfall prediction tasks requires relevant conditions and effective utilization to direct the forecasting process of the diffusion model. In this paper, we propose a probabilistic spatiotemporal model for precipitation nowcasting, named LLMDiff. The architecture of LLMDiff includes two networks: a conditional encoder–decoder network and a denoising network. The conditional network provides conditional information to guide the denoising network for high-quality predictions related to real-world earth systems. Additionally, we utilize a frozen transformer block from pre-trained large language models (LLMs) in the denoising network as a universal visual encoder layer, which enables the accurate estimation of motion trend by considering long-term temporal context information and capturing temporal dependencies within the frame sequence. Our experimental results demonstrate that LLMDiff outperforms state-of-the-art models on the SEVIR dataset.
Open AccessLLMDiff: Diffusion Model Using Frozen LLM Transformers for Precipitation Nowcasting
Precipitation nowcasting, which involves the short-term, high-resolution prediction of rainfall, plays a crucial role in various real-world applications. In recent years, researchers have increasingly utilized deep learning-based methods in precipitation nowcasting. The exponential growth of spatiotemporal observation data has heightened interest in recent advancements such as denoising diffusion models, which offer appealing prospects due to their inherent probabilistic nature that aligns well with the complexities of weather forecasting. Successful application of diffusion models in rainfall prediction tasks requires relevant conditions and effective utilization to direct the forecasting process of the diffusion model. In this paper, we propose a probabilistic spatiotemporal model for precipitation nowcasting, named LLMDiff. The architecture of LLMDiff includes two networks: a conditional encoder–decoder network and a denoising network. The conditional network provides conditional information to guide the denoising network for high-quality predictions related to real-world earth systems. Additionally, we utilize a frozen transformer block from pre-trained large language models (LLMs) in the denoising network as a universal visual encoder layer, which enables the accurate estimation of motion trend by considering long-term temporal context information and capturing temporal dependencies within the frame sequence. Our experimental results demonstrate that LLMDiff outperforms state-of-the-art models on the SEVIR dataset.
- Open Access
Enhancing Radar Echo Extrapolation by ConvLSTM2D for Precipitation Nowcasting
Precipitation nowcasting in real-time is a challenging task that demands accurate and current data from multiple sources. Despite various approaches proposed by researchers to address this challenge, models such as the interaction-based dual attention LSTM (IDA-LSTM) face limitations, particularly in radar echo extrapolation. These limitations include higher computational costs and resource requirements. Moreover, the fixed kernel size across layers in these models restricts their ability to extract global features, focusing more on local representations. To address these issues, this study introduces an enhanced convolutional long short-term 2D (ConvLSTM2D) based architecture for precipitation nowcasting. The proposed approach includes time-distributed layers that enable parallel Conv2D operations on each image input, enabling effective analysis of spatial patterns. Following this, ConvLSTM2D is applied to capture spatiotemporal features, which improves the model’s forecasting skills and computational efficacy. The performance evaluation employs a real-world weather dataset benchmarked against established techniques, with metrics including the Heidke skill score (HSS), critical success index (CSI), mean absolute error (MAE), and structural similarity index (SSIM). ConvLSTM2D demonstrates superior performance, achieving an HSS of 0.5493, a CSI of 0.5035, and an SSIM of 0.3847. Notably, a lower MAE of 11.16 further indicates the model’s precision in predicting precipitation.
Open AccessEnhancing Radar Echo Extrapolation by ConvLSTM2D for Precipitation Nowcasting
Precipitation nowcasting in real-time is a challenging task that demands accurate and current data from multiple sources. Despite various approaches proposed by researchers to address this challenge, models such as the interaction-based dual attention LSTM (IDA-LSTM) face limitations, particularly in radar echo extrapolation. These limitations include higher computational costs and resource requirements. Moreover, the fixed kernel size across layers in these models restricts their ability to extract global features, focusing more on local representations. To address these issues, this study introduces an enhanced convolutional long short-term 2D (ConvLSTM2D) based architecture for precipitation nowcasting. The proposed approach includes time-distributed layers that enable parallel Conv2D operations on each image input, enabling effective analysis of spatial patterns. Following this, ConvLSTM2D is applied to capture spatiotemporal features, which improves the model’s forecasting skills and computational efficacy. The performance evaluation employs a real-world weather dataset benchmarked against established techniques, with metrics including the Heidke skill score (HSS), critical success index (CSI), mean absolute error (MAE), and structural similarity index (SSIM). ConvLSTM2D demonstrates superior performance, achieving an HSS of 0.5493, a CSI of 0.5035, and an SSIM of 0.3847. Notably, a lower MAE of 11.16 further indicates the model’s precision in predicting precipitation.