Utilization of a Lightweight 3D U-Net Model for Reducing Execution Time of Numerical Weather Prediction Models
Conventional weather forecasting relies on numerical weather prediction (NWP), which solves atmospheric equations using numerical methods. The Korea Meteorological Administration (KMA) adopted the Met Office Global Seasonal Forecasting System version 6 (GloSea6) NWP model from the UK and runs it on...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-01-01
|
| Series: | Atmosphere |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2073-4433/16/1/60 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832589131610324992 |
|---|---|
| author | Hyesung Park Sungwook Chung |
| author_facet | Hyesung Park Sungwook Chung |
| author_sort | Hyesung Park |
| collection | DOAJ |
| description | Conventional weather forecasting relies on numerical weather prediction (NWP), which solves atmospheric equations using numerical methods. The Korea Meteorological Administration (KMA) adopted the Met Office Global Seasonal Forecasting System version 6 (GloSea6) NWP model from the UK and runs it on a supercomputer. However, due to high task demands, the limited resources of the supercomputer have caused job queue delays. To address this, the KMA developed a low-resolution version, Low GloSea6, for smaller-scale servers at universities and research institutions. Despite its ability to run on less powerful servers, Low GloSea6 still requires significant computational resources like those of high-performance computing (HPC) clusters. We integrated deep learning with Low GloSea6 to reduce execution time and improve meteorological research efficiency. Through profiling, we confirmed that deep learning models can be integrated without altering the original configuration of Low GloSea6 or complicating physical interpretation. The profiling identified “tri_sor.F90” as the main CPU time hotspot. By combining the biconjugate gradient stabilized (BiCGStab) method, used for solving the Helmholtz problem, with a deep learning model, we reduced unnecessary hotspot calls, shortening execution time. We also propose a convolutional block attention module-based Half-UNet (CH-UNet), a lightweight 3D-based U-Net architecture, for faster deep-learning computations. In experiments, CH-UNet showed 10.24% lower RMSE than Half-UNet, which has fewer FLOPs. Integrating CH-UNet into Low GloSea6 reduced execution time by up to 71 s per timestep, averaging a 2.6% reduction compared to the original Low GloSea6, and 6.8% compared to using Half-UNet. This demonstrates that CH-UNet, with balanced FLOPs and high predictive accuracy, offers more significant execution time reductions than models with fewer FLOPs. |
| format | Article |
| id | doaj-art-91892be87bb648789b60026f9907c31f |
| institution | Kabale University |
| issn | 2073-4433 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Atmosphere |
| spelling | doaj-art-91892be87bb648789b60026f9907c31f2025-01-24T13:21:53ZengMDPI AGAtmosphere2073-44332025-01-011616010.3390/atmos16010060Utilization of a Lightweight 3D U-Net Model for Reducing Execution Time of Numerical Weather Prediction ModelsHyesung Park0Sungwook Chung1Department of Computer Engineering, Changwon National University, Changwon 51140, Republic of KoreaDepartment of Computer Engineering, Changwon National University, Changwon 51140, Republic of KoreaConventional weather forecasting relies on numerical weather prediction (NWP), which solves atmospheric equations using numerical methods. The Korea Meteorological Administration (KMA) adopted the Met Office Global Seasonal Forecasting System version 6 (GloSea6) NWP model from the UK and runs it on a supercomputer. However, due to high task demands, the limited resources of the supercomputer have caused job queue delays. To address this, the KMA developed a low-resolution version, Low GloSea6, for smaller-scale servers at universities and research institutions. Despite its ability to run on less powerful servers, Low GloSea6 still requires significant computational resources like those of high-performance computing (HPC) clusters. We integrated deep learning with Low GloSea6 to reduce execution time and improve meteorological research efficiency. Through profiling, we confirmed that deep learning models can be integrated without altering the original configuration of Low GloSea6 or complicating physical interpretation. The profiling identified “tri_sor.F90” as the main CPU time hotspot. By combining the biconjugate gradient stabilized (BiCGStab) method, used for solving the Helmholtz problem, with a deep learning model, we reduced unnecessary hotspot calls, shortening execution time. We also propose a convolutional block attention module-based Half-UNet (CH-UNet), a lightweight 3D-based U-Net architecture, for faster deep-learning computations. In experiments, CH-UNet showed 10.24% lower RMSE than Half-UNet, which has fewer FLOPs. Integrating CH-UNet into Low GloSea6 reduced execution time by up to 71 s per timestep, averaging a 2.6% reduction compared to the original Low GloSea6, and 6.8% compared to using Half-UNet. This demonstrates that CH-UNet, with balanced FLOPs and high predictive accuracy, offers more significant execution time reductions than models with fewer FLOPs.https://www.mdpi.com/2073-4433/16/1/60weather forecastGloSea6deep learninglightweight networkexecution time reduction |
| spellingShingle | Hyesung Park Sungwook Chung Utilization of a Lightweight 3D U-Net Model for Reducing Execution Time of Numerical Weather Prediction Models Atmosphere weather forecast GloSea6 deep learning lightweight network execution time reduction |
| title | Utilization of a Lightweight 3D U-Net Model for Reducing Execution Time of Numerical Weather Prediction Models |
| title_full | Utilization of a Lightweight 3D U-Net Model for Reducing Execution Time of Numerical Weather Prediction Models |
| title_fullStr | Utilization of a Lightweight 3D U-Net Model for Reducing Execution Time of Numerical Weather Prediction Models |
| title_full_unstemmed | Utilization of a Lightweight 3D U-Net Model for Reducing Execution Time of Numerical Weather Prediction Models |
| title_short | Utilization of a Lightweight 3D U-Net Model for Reducing Execution Time of Numerical Weather Prediction Models |
| title_sort | utilization of a lightweight 3d u net model for reducing execution time of numerical weather prediction models |
| topic | weather forecast GloSea6 deep learning lightweight network execution time reduction |
| url | https://www.mdpi.com/2073-4433/16/1/60 |
| work_keys_str_mv | AT hyesungpark utilizationofalightweight3dunetmodelforreducingexecutiontimeofnumericalweatherpredictionmodels AT sungwookchung utilizationofalightweight3dunetmodelforreducingexecutiontimeofnumericalweatherpredictionmodels |