arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2312.08264eess.SPcs.LGphysics.ao-ph
收藏

Kunyu:一种超越回归损失的高性能全球天气模型

Kunyu: A High-Performing Global Weather Model Beyond Regression Losses

Accutar Biotechnology Inc(Accutar生物技术公司)

Zekun Ni

AI总结:

针对现有数据驱动全球天气模型依赖回归损失导致预报模糊的问题,提出整合回归与对抗损失的Kunyu模型,在0.35°分辨率下实现高精度预报,部分性能超越ECMWF HRES,缩小了与数值预报的实用性差距。

摘要:

过去一年,数据驱动的全球天气预报已成为传统数值天气预报的新替代方案。这种创新方法能以极低的计算成本生成精度相当的预报。遗憾的是,据我所知,现有模型完全依赖回归损失,生成的预报存在严重模糊问题。这种模糊性虽然降低了实用性,却在评估指标上占据不公平优势。本文提出Kunyu,这是一种数据驱动的全球天气预报模型,能在0.35°分辨率下对一系列全面的大气变量做出准确预测。其训练框架整合了回归损失与对抗损失,使Kunyu生成的预报清晰度和真实感均有所提升。在异常极值估计等方面,它的性能甚至超过ECMWF HRES(欧洲中期天气预报中心高分辨率预报系统),同时在RMSE(均方根误差)和ACC(异常相关系数)等评估指标上与ECMWF HRES相当。Kunyu是缩小数值天气预报与数据驱动天气预报间实用性差距的重要一步。

英文摘要:

Over the past year, data-driven global weather forecasting has emerged as a new alternative to traditional numerical weather prediction. This innovative approach yields forecasts of comparable accuracy at a tiny fraction of computational costs. Regrettably, as far as I know, existing models exclusively rely on regression losses, producing forecasts with substantial blurring. Such blurring, although compromises practicality, enjoys an unfair advantage on evaluation metrics. In this paper, I present Kunyu, a global data-driven weather forecasting model which delivers accurate predictions across a comprehensive array of atmospheric variables at 0.35° resolution. With both regression and adversarial losses integrated in its training framework, Kunyu generates forecasts with enhanced clarity and realism. Its performance outpaces even ECMWF HRES in some aspects such as the estimation of anomaly extremes, while remaining competitive with ECMWF HRES on evaluation metrics such as RMSE and ACC. Kunyu is an important step forward in closing the utility gap between numerical and data-driven weather prediction.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑