Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
169 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
45 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

FengWu-GHR: Learning the Kilometer-scale Medium-range Global Weather Forecasting (2402.00059v1)

Published 28 Jan 2024 in cs.LG, cs.AI, and physics.ao-ph

Abstract: Kilometer-scale modeling of global atmosphere dynamics enables fine-grained weather forecasting and decreases the risk of disastrous weather and climate activity. Therefore, building a kilometer-scale global forecast model is a persistent pursuit in the meteorology domain. Active international efforts have been made in past decades to improve the spatial resolution of numerical weather models. Nonetheless, developing the higher resolution numerical model remains a long-standing challenge due to the substantial consumption of computational resources. Recent advances in data-driven global weather forecasting models utilize reanalysis data for model training and have demonstrated comparable or even higher forecasting skills than numerical models. However, they are all limited by the resolution of reanalysis data and incapable of generating higher-resolution forecasts. This work presents FengWu-GHR, the first data-driven global weather forecasting model running at the 0.09${\circ}$ horizontal resolution. FengWu-GHR introduces a novel approach that opens the door for operating ML-based high-resolution forecasts by inheriting prior knowledge from a pretrained low-resolution model. The hindcast of weather prediction in 2022 indicates that FengWu-GHR is superior to the IFS-HRES. Furthermore, evaluations on station observations and case studies of extreme events support the competitive operational forecasting skill of FengWu-GHR at the high resolution.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (40)
  1. A new equitable score suitable for verifying precipitation in numerical weather prediction. Quarterly Journal of the Royal Meteorological Society, 136(650):1344–1363, 2010.
  2. The benefits of increasing resolution in global and regional climate simulations for european climate extremes. Geoscientific Model Development, 13(11):5583–5607, 2020.
  3. The benefit of high-resolution operational weather forecasts for flash flood warning. Hydrology and Earth System Sciences, 12(4):1039–1051, 2008.
  4. A synergistic use of a high-resolution numerical weather prediction model and high-resolution earth observation products to improve precipitation forecast. Remote Sensing, 11(20):2387, 2019.
  5. Resolution dependence of european precipitation in a state-of-the-art atmospheric general circulation model. Journal of Climate, 28(13):5134–5149, 2015a.
  6. Resolution dependence of circulation forced future central european summer drying. Environmental Research Letters, 10(5):055002, 2015b.
  7. North atlantic storm-track sensitivity to warming increases with model resolution. Journal of Climate, 28(11):4513–4524, 2015.
  8. The benefits of global high resolution for climate simulation: process understanding and the enabling of stakeholder decisions at the regional scale. Bulletin of the American Meteorological Society, 99(11):2341–2359, 2018.
  9. Accurate medium-range global weather forecasting with 3d neural networks. Nature, 619(7970):533–538, 2023.
  10. Learning skillful medium-range global weather forecasting. Science, 382(6677):1416–1421, 2023.
  11. Fengwu: Pushing the skillful global medium-range weather forecast beyond 10 days lead. arXiv preprint arXiv:2304.02948, 2023a.
  12. Neural general circulation models. arXiv preprint arXiv:2311.07222, 2023.
  13. Fourcastnet: Accelerating global high-resolution weather forecasting using adaptive fourier neural operators. In Proceedings of the Platform for Advanced Scientific Computing Conference, pages 1–11, 2023.
  14. Numerical integration of the barotropic vorticity equation. Tellus, 2(4):237–254, 1950.
  15. Peter Lynch. The origins of computer weather prediction and climate modeling. Journal of computational physics, 227(7):3431–3444, 2008.
  16. Ifs upgrade brings many improvements and unifies medium-range resolutions, 07/2023 2023. URL  .
  17. Understanding, modeling and predicting weather and climate extremes: Challenges and opportunities. Weather and climate extremes, 18:65–74, 2017.
  18. Diffusion model-based probabilistic downscaling for 180-year east asian climate reconstruction. 2024.
  19. Downscaling ssp-consistent global spatial urban land projections from 1/8-degree to 1-km resolution 2000–2100. Scientific Data, 8(1):281, 2021.
  20. The rise of data-driven weather forecasting. arXiv preprint arXiv:2307.10128, 2023.
  21. Weatherbench 2: A benchmark for the next generation of data-driven global weather models. arXiv preprint arXiv:2308.15560, 2023.
  22. Fuxi: a cascade machine learning forecasting system for 15-day global weather forecast. npj Clim Atmos Sci, 6(190), 2023b. 10.1038/s41612-023-00512-1.
  23. Ryan Keisler. Forecasting global weather with graph neural networks. arXiv preprint arXiv:2202.07575, 2022.
  24. Gencast: Diffusion-based ensemble forecasting for medium-range weather. arXiv preprint arXiv:2312.15796, 2023.
  25. Attention is all you need. Advances in neural information processing systems, 30, 2017.
  26. Learning mesh-based simulation with graph networks. arXiv preprint arXiv:2010.03409, 2020.
  27. Learning to simulate complex physics with graph networks. In International conference on machine learning, pages 8459–8468. PMLR, 2020.
  28. A survey on vision transformer. IEEE transactions on pattern analysis and machine intelligence, 45(1):87–110, 2022.
  29. Visual instruction tuning. arXiv preprint arXiv:2304.08485, 2023.
  30. Language models are few-shot learners. Advances in neural information processing systems, 33:1877–1901, 2020.
  31. Llama: Open and efficient foundation language models. arXiv preprint arXiv:2302.13971, 2023.
  32. An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929, 2020.
  33. The era5 global reanalysis. Quarterly Journal of the Royal Meteorological Society, 146(730):1999–2049, 2020.
  34. Roformer: Enhanced transformer with rotary position embedding. Neurocomputing, 568:127063, 2024.
  35. Train short, test long: Attention with linear biases enables input length extrapolation. arXiv preprint arXiv:2108.12409, 2021.
  36. A length-extrapolatable transformer. arXiv preprint arXiv:2212.10554, 2022.
  37. Efficient estimation of word representations in vector space. arXiv preprint arXiv:1301.3781, 2013.
  38. Lora: Low-rank adaptation of large language models. arXiv preprint arXiv:2106.09685, 2021.
  39. Connection between the large-scale 500 hpa geopotential height fields and precipitation over greece during wintertime. Climate research, 14(2):129–146, 2000.
  40. Persistence and periodicity in the precipitation series of turkey and associations with 500 hpa geopotential heights. Climate Research, 21(1):59–81, 2002.
Citations (9)
View on Semantic Scholar

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now