arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~

LoRA 适配强度在 Aurora-WRF 中的表现:区域强降雨预报的权衡

LoRA Adaptation Strength in Aurora-WRF: Trade-offs in Regional Heavy-Rainfall Forecasting

Boyan Liu, Xiaoyuan Zhang

arXiv 2610.03747首次发表:更新:

发表机构

Zhongguancun Academy(中关村学院)

机构由 AI 辅助整理,请以论文原文为准。

AI 中文总结

本研究通过京津冀地区 Aurora-WRF 耦合实验,发现中等 LoRA 适配强度可显著降低降水强度误差并校准频率偏差,但会削弱强降雨检测能力,揭示了适配强度与下游预报性能之间的权衡。

AI 中文摘要

我们研究了在京津冀地区受控的 Aurora-WRF 耦合实验中,大气基础模型的参数高效适配如何影响下游区域降水。基于 2020-2021 年 5 月至 9 月的数据,训练了 AuroraPretrained 的单步、降水加权 LoRA 适配,并使用 2022 年验证数据进行选择。五种推理时适配强度与不变的 9 公里 WRF 配置耦合,并在共同的 ERA5 初始化和辅助场规则下与 GFS 驱动的控制实验进行比较。评估使用了 2023 年的 17 次初始化、逐小时 ERA5 降水数据,并保守重映射到固定的 356 格点、0.25 度验证网格。强降雨被专门定义为连续 24 小时窗口内至少 50 毫米,逐小时推进。对于从 0 到 48 小时的窗口起始时间,未适配的 Aurora 达到了最高的平均关键成功指数(CSI),为 0.216,而 GFS 控制实验为 0.144。中等 LoRA 强度 0.75 将 Aurora 驱动的 24 小时降水均方误差降低了 30.7%,并将合并频率偏差从 1.510 降至 1.024,但 CSI 降至 0.182。GFS 保持了最低的全域误差。这些结果刻画了降水检测、频率校准和强度误差之间的权衡,显示了在共同耦合框架内针对多个下游标准评估适配强度的重要性。

英文摘要

We investigate how parameter-efficient adaptation of an atmospheric foundation model affects downstream regional precipitation in a controlled Aurora-WRF coupling experiment over the Beijing-Tianjin-Hebei region. A single-step, precipitation-weighted LoRA adaptation of AuroraPretrained is trained on May-September 2020-2021 and selected using 2022 validation data. Five inference-time adaptation strengths are coupled to an unchanged 9-km WRF configuration and compared with a GFS-driven control under common ERA5 initialization and auxiliary-field rules. Evaluation uses 17 initializations in 2023, hourly ERA5 precipitation, and conservative remapping to a fixed 356-cell, 0.25-degree verification grid. Heavy rainfall is defined exclusively as at least 50 mm in a continuous 24-hour window, advanced hourly. For window starts from 0 to 48 hours, unadapted Aurora attains the highest mean critical success index (CSI), 0.216, compared with 0.144 for the GFS control. An intermediate LoRA strength of 0.75 reduces the Aurora-driven 24-hour precipitation mean squared error by 30.7% and brings pooled frequency Bias from 1.510 to 1.024, but lowers CSI to 0.182. GFS retains the lowest whole-domain error. These results characterize a trade-off between rainfall detection, frequency calibration, and intensity error, showing the importance of evaluating adaptation strength against multiple downstream criteria within a common coupling framework.

论文原文

arXiv 摘要页 · PDF 原文 · HTML 原文

↑