Liwen Wang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Liwen Wang has a total of 5 co-authors. Here are the top co-authors by number of shared publications:
- Qian Li
College of Meteorology and Oceanography, National University of Defense Technology, Changsha, China
7 shared publications - Qi Lv
College of Meteorology and Oceanography National University of Defense Technology Changsha China
6 shared publications - Xuan Peng
College of Meteorology and Oceanography National University of Defense Technology Changsha China
4 shared publications Tianying Wang
Institute of Meteorological Sciences of Hunan Province Changsha China
1 shared publicationZeming Zhou
College of Meteorology and Oceanography National University of Defense Technology Changsha China
1 shared publication
Latest Publications
- 15 September 2025
- Published by American Geophysical Union (AGU) in Journal of Geophysical Research: Atmospheres
- Vol. 130 (18)
A Diffusion Framework for Temperature Fields Reconstruction With Embedded Vertical Dynamics
High‐resolution meteorological data are crucial for accurate climate research and weather forecasting. However, climate change and global warming are altering the patterns in meteorological data, leading to gradual shifts in the statistical characteristics of climate variables. Existing statistical downscaling approaches primarily focus on fitting historical data while neglecting the integration of essential physical laws governing atmospheric dynamics. Although these models may perform well on past data, they risk losing accuracy when applied to future climate scenarios, particularly when faced with climate shifts or changing conditions. To address this challenge, we introduce a physics‐informed framework to downscale continuous temperature fields. Our framework is designed to decompose the temperature fields into a primary deterministic component and stochastic residual component, each modeled by distinct parts of the architecture. The deterministic component reconstructs the primary temperature field, whereas the stochastic diffusion component captures small‐scale details and uncertainties. Moreover, this framework integrates vertical dynamics by incorporating physical priors derived from the fundamental temperature variation equation, combined through zero convolution, and applied as physics priors in the downscaling process using a 3D U‐Net architecture as the encoder. The model's loss function includes Charbonnier loss for data fitting along with static stability loss, gradient loss, and coupling loss to ensure physical consistency and accurate vertical interaction representation. Comparative experiments demonstrate that our method outperforms traditional techniques, reducing the error between downscaled results and high‐resolution observations to 0.627 K compared to 1.394 K with bicubic interpolation.
- 15 September 2025
- Published by American Geophysical Union (AGU) in Journal of Geophysical Research: Atmospheres
- Vol. 130 (18)
A Diffusion Framework for Temperature Fields Reconstruction With Embedded Vertical Dynamics
High‐resolution meteorological data are crucial for accurate climate research and weather forecasting. However, climate change and global warming are altering the patterns in meteorological data, leading to gradual shifts in the statistical characteristics of climate variables. Existing statistical downscaling approaches primarily focus on fitting historical data while neglecting the integration of essential physical laws governing atmospheric dynamics. Although these models may perform well on past data, they risk losing accuracy when applied to future climate scenarios, particularly when faced with climate shifts or changing conditions. To address this challenge, we introduce a physics‐informed framework to downscale continuous temperature fields. Our framework is designed to decompose the temperature fields into a primary deterministic component and stochastic residual component, each modeled by distinct parts of the architecture. The deterministic component reconstructs the primary temperature field, whereas the stochastic diffusion component captures small‐scale details and uncertainties. Moreover, this framework integrates vertical dynamics by incorporating physical priors derived from the fundamental temperature variation equation, combined through zero convolution, and applied as physics priors in the downscaling process using a 3D U‐Net architecture as the encoder. The model's loss function includes Charbonnier loss for data fitting along with static stability loss, gradient loss, and coupling loss to ensure physical consistency and accurate vertical interaction representation. Comparative experiments demonstrate that our method outperforms traditional techniques, reducing the error between downscaled results and high‐resolution observations to 0.627 K compared to 1.394 K with bicubic interpolation.
- Open Access
- 24 July 2024
- Published by American Geophysical Union (AGU) in Earth and Space Science
- Vol. 11 (7)
A Self‐Supervised Framework for Refined Reconstruction of Geophysical Fields via Domain Adaptation
Reconstructing fine‐grained, detailed spatial structures from time‐evolving coarse‐scale geophysical fields has been a long‐standing challenge. Current deep learning approaches addressing this issue generally require massive fine‐scale fields as supervision, which is often unavailable due to limitations in existing observational systems and the scarcity of widespread high‐precision sensors. Here, we present AdaptDeep, a self‐supervised framework for refined reconstruction of geophysical fields via domain adaptation from the coarse‐scale source domain to the fine‐scale target domain. This method incorporates two pretext tasks, cropped field reconstruction and temporal augmentation‐assisted contrastive learning, to leverage spatial and temporal correlations in the target domain. A global propagation structure is proposed in the feature extraction network to leverage bidirectional information for enhanced long‐range dependencies and robustness against estimation errors. In experiments, AdaptDeep correctly identifies local, fine structures and significantly recovers 81.2% detailed information in sea surface temperature fields.
- 24 July 2024
- Published by American Geophysical Union (AGU) in Earth and Space Science
- Vol. 11 (7)
Open AccessA Self‐Supervised Framework for Refined Reconstruction of Geophysical Fields via Domain Adaptation
Reconstructing fine‐grained, detailed spatial structures from time‐evolving coarse‐scale geophysical fields has been a long‐standing challenge. Current deep learning approaches addressing this issue generally require massive fine‐scale fields as supervision, which is often unavailable due to limitations in existing observational systems and the scarcity of widespread high‐precision sensors. Here, we present AdaptDeep, a self‐supervised framework for refined reconstruction of geophysical fields via domain adaptation from the coarse‐scale source domain to the fine‐scale target domain. This method incorporates two pretext tasks, cropped field reconstruction and temporal augmentation‐assisted contrastive learning, to leverage spatial and temporal correlations in the target domain. A global propagation structure is proposed in the feature extraction network to leverage bidirectional information for enhanced long‐range dependencies and robustness against estimation errors. In experiments, AdaptDeep correctly identifies local, fine structures and significantly recovers 81.2% detailed information in sea surface temperature fields.
- Open Access
- 23 January 2024
- Published by MDPI AG in Remote Sensing
- Vol. 16 (3) , 442
A Temporal Downscaling Model for Gridded Geophysical Data with Enhanced Residual U-Net
Temporal downscaling of gridded geophysical data is essential for improving climate models, weather forecasting, and environmental assessments. However, existing methods often cannot accurately capture multi-scale temporal features, affecting their accuracy and reliability. To address this issue, we introduce an Enhanced Residual U-Net architecture for temporal downscaling. The architecture, which incorporates residual blocks, allows for deeper network structures without the risk of overfitting or vanishing gradients, thus capturing more complex temporal dependencies. The U-Net design inherently can capture multi-scale features, making it ideal for simulating various temporal dynamics. Moreover, we implement a flow regularization technique with advection loss to ensure that the model adheres to physical laws governing geophysical fields. Our experimental results across various variables within the ERA5 dataset demonstrate an improvement in downscaling accuracy, outperforming other methods.
- 23 January 2024
- Published by MDPI AG in Remote Sensing
- Vol. 16 (3) , 442
Open AccessA Temporal Downscaling Model for Gridded Geophysical Data with Enhanced Residual U-Net
Temporal downscaling of gridded geophysical data is essential for improving climate models, weather forecasting, and environmental assessments. However, existing methods often cannot accurately capture multi-scale temporal features, affecting their accuracy and reliability. To address this issue, we introduce an Enhanced Residual U-Net architecture for temporal downscaling. The architecture, which incorporates residual blocks, allows for deeper network structures without the risk of overfitting or vanishing gradients, thus capturing more complex temporal dependencies. The U-Net design inherently can capture multi-scale features, making it ideal for simulating various temporal dynamics. Moreover, we implement a flow regularization technique with advection loss to ensure that the model adheres to physical laws governing geophysical fields. Our experimental results across various variables within the ERA5 dataset demonstrate an improvement in downscaling accuracy, outperforming other methods.
- Open Access
- 21 September 2023
- Published by MDPI AG in Preprints.org
A Temporal Downscaling Model for Gridded Geophysical Data with Enhanced Residual U-Net
Temporal downscaling of gridded geophysical data is essential for improving climate models, weather forecasting, and environmental assessments. However, existing methods often could not accurately capture multi-scale temporal features, affecting their accuracy and reliability. To address this issue, we introduce an Enhanced Residual U-Net architecture for temporal downscaling. The architecture, which incorporates residual blocks, allows for deeper network structures without the risk of overfitting or vanishing gradients, thus capturing more complex temporal dependencies. The U-Net design inherently could capture multi-scale features, making it ideal for simulating various temporal dynamics. Moreover, we implement a flow regularization technique with advection loss to ensure that the model adheres to physical laws governing geophysical fields. Our experimental results across various variables within the ERA5 dataset demonstrate an improvement in downscaling accuracy, outperforming other methods.
- 21 September 2023
- Published by MDPI AG in Preprints.org
Open AccessA Temporal Downscaling Model for Gridded Geophysical Data with Enhanced Residual U-Net
Temporal downscaling of gridded geophysical data is essential for improving climate models, weather forecasting, and environmental assessments. However, existing methods often could not accurately capture multi-scale temporal features, affecting their accuracy and reliability. To address this issue, we introduce an Enhanced Residual U-Net architecture for temporal downscaling. The architecture, which incorporates residual blocks, allows for deeper network structures without the risk of overfitting or vanishing gradients, thus capturing more complex temporal dependencies. The U-Net design inherently could capture multi-scale features, making it ideal for simulating various temporal dynamics. Moreover, we implement a flow regularization technique with advection loss to ensure that the model adheres to physical laws governing geophysical fields. Our experimental results across various variables within the ERA5 dataset demonstrate an improvement in downscaling accuracy, outperforming other methods.
- 10 August 2022
- Published by American Geophysical Union (AGU) in Geophysical Research Letters
- Vol. 49 (15)
Self‐Supervised Classification of Weather Systems Based on Spatiotemporal Contrastive Learning
The classification of weather systems provides a simple description of atmospheric circulations and bridges the gap between large‐scale atmospheric conditions and local‐scale environmental variables. However, the existing classification methods are challenged due to a lack of labels and inaccurate similarity measures between data samples. In this letter, we propose a self‐supervised Spatiotemporal Contrastive Learning (SCL) framework for the classification of weather systems without manual labels. In particular, we operate both spatial and temporal augmentation on multivariate meteorological data to fully explore temporal context information and spatial stability in accordance with synoptic nature. For the assessment and comparison of the classification results, we apply a statistical method based on analog forecasting using the classification results as input. The experimental results demonstrate that the proposed SCL model outperforms traditional classification methods.
- 10 August 2022
- Published by American Geophysical Union (AGU) in Geophysical Research Letters
- Vol. 49 (15)
Self‐Supervised Classification of Weather Systems Based on Spatiotemporal Contrastive Learning
The classification of weather systems provides a simple description of atmospheric circulations and bridges the gap between large‐scale atmospheric conditions and local‐scale environmental variables. However, the existing classification methods are challenged due to a lack of labels and inaccurate similarity measures between data samples. In this letter, we propose a self‐supervised Spatiotemporal Contrastive Learning (SCL) framework for the classification of weather systems without manual labels. In particular, we operate both spatial and temporal augmentation on multivariate meteorological data to fully explore temporal context information and spatial stability in accordance with synoptic nature. For the assessment and comparison of the classification results, we apply a statistical method based on analog forecasting using the classification results as input. The experimental results demonstrate that the proposed SCL model outperforms traditional classification methods.
- Open Access
- 15 April 2022
- Published by Wiley in ESS Open Archive
Self-supervised Classification of Weather Systems Based on Spatiotemporal Contrastive Learning
Classification of weather systems provides a simple description of atmospheric circulations and bridges the gap between large-scale atmospheric conditions and local-scale environmental variables. H...
- 15 April 2022
- Published by Wiley in ESS Open Archive
Open AccessSelf-supervised Classification of Weather Systems Based on Spatiotemporal Contrastive Learning
Classification of weather systems provides a simple description of atmospheric circulations and bridges the gap between large-scale atmospheric conditions and local-scale environmental variables. H...
- Open Access
- 1 March 2022
- Published by Wiley in ESS Open Archive
Self-supervised Classification of Weather Systems Based on Spatiotemporal Contrastive Learning
Classification of weather systems provides a simple description of atmospheric circulations and bridges the gap between large-scale atmospheric conditions and local-scale environmental variables. However, the existing classification methods are challenged due to lack of labels and inaccurate similarity measures between data samples. In this letter, we propose a self-supervised Spatiotemporal Contrastive Learning (SCL) framework for the classification of weather systems without manual labels. In particular, we operate both spatial and temporal augmentation on multivariate meteorological data to fully explore temporal context information and spatial stability in accordance with synoptic nature. With the classification results, we apply a statistical downscaling method based on analog forecasting for the assessment and comparison of classification results. The experimental results demonstrate that the proposed SCL model outperforms traditional classification methods.
- 1 March 2022
- Published by Wiley in ESS Open Archive
Open AccessSelf-supervised Classification of Weather Systems Based on Spatiotemporal Contrastive Learning
Classification of weather systems provides a simple description of atmospheric circulations and bridges the gap between large-scale atmospheric conditions and local-scale environmental variables. However, the existing classification methods are challenged due to lack of labels and inaccurate similarity measures between data samples. In this letter, we propose a self-supervised Spatiotemporal Contrastive Learning (SCL) framework for the classification of weather systems without manual labels. In particular, we operate both spatial and temporal augmentation on multivariate meteorological data to fully explore temporal context information and spatial stability in accordance with synoptic nature. With the classification results, we apply a statistical downscaling method based on analog forecasting for the assessment and comparison of classification results. The experimental results demonstrate that the proposed SCL model outperforms traditional classification methods.