arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2602.16579cs.LGcs.AIphysics.app-ph
收藏

AIFL:基于确定性LSTM的全球每日径流预报模型,利用ERA5-Land预训练和IFS微调

AIFL: A Global Daily Streamflow Forecasting Model Using a Deterministic LSTM Pre-trained on ERA5-Land and Fine-tuned on IFS

European Centre for Medium-Range Weather Forecasts(欧洲中期天气预报中心)
Maria Luisa Taccari, Kenza Tazi, Oisín M. Morrison, Andreas Grafberger, Juan Colonese, Corentin Carton de Wiart, Christel Prudhomme, Cinzia Mazzetti, Matthew Ch… 展开作者

Maria Luisa Taccari, Kenza Tazi, Oisín M. Morrison, Andreas Grafberger, Juan Colonese, Corentin Carton de Wiart, Christel Prudhomme, Cinzia Mazzetti, Matthew Chantry, Florian Pappenberger

AI总结:

AIFL通过预训练和微调结合的方法,实现全球每日径流预报,具有高预测能力和透明的驱动管道。

摘要:

可靠的全球径流预报对于洪水准备和水资源管理至关重要,但数据驱动模型在从历史再分析数据过渡到业务预报产品时往往存在性能差距。本文介绍了AIFL(人工智能用于洪水),一种用于全球每日径流预报的确定性LSTM模型。该模型在CARAVAN数据集中的18588个流域上进行训练,利用一种新颖的两阶段训练策略来弥合再分析到预报领域的转换差距。模型首先在40年的ERA5-Land再分析数据(1980-2019)上进行预训练,以捕捉稳健的水文过程,然后在业务集成预报系统(IFS)控制预报(2016-2019)上进行微调,以适应业务数值天气预测的特定误差结构和偏差。据我们所知,这是第一个在CARAVAN生态系统内端到端训练的全球模型。在独立的时间测试集(2021-2024)上,AIFL实现了高预测能力,中位数修改后的Kling-Gupta效率(KGE')为0.66,中位数Nash-Sutcliffe效率(NSE)为0.53。基准测试结果显示,AIFL与当前最先进的全球系统具有高度竞争力,实现了与之相当的准确性,同时保持了透明和可重复的驱动管道。该模型在极端事件检测中表现出卓越的可靠性,为全球水文界提供了流线且业务上稳健的基准。

英文摘要:

Reliable global streamflow forecasting is essential for flood preparedness and water resource management, yet data-driven models often suffer from a performance gap when transitioning from historical reanalysis to operational forecast products. This paper introduces AIFL (Artificial Intelligence for Floods), a deterministic LSTM-based model designed for global daily streamflow forecasting. Trained on 18,588 basins curated from the Caravan dataset, AIFL utilises a two-stage transfer-learning strategy to bridge the reanalysis-to-forecast domain shift. The model is first pre-trained on 40 years of ERA5-Land reanalysis (1980-2019) to capture robust hydrological processes, then fine-tuned on operational Integrated Forecasting System (IFS) forecasts (2016-2019) to adapt to the specific error structures and biases of operational numerical weather prediction. Ablation experiments confirm that this two-stage approach outperforms both a naive IFS-only baseline and a mixed-forcing single-stage alternative. To our knowledge, this is the first global model trained end-to-end within the Caravan ecosystem. On an independent temporal test set (2021-2024), AIFL achieves high predictive skill with a median modified Kling-Gupta Efficiency (KGE') of 0.66 and a median Nash-Sutcliffe Efficiency (NSE) of 0.53. Benchmarking results show that AIFL achieves comparable accuracy to current state-of-the-art global systems. The model provides a streamlined and operationally robust baseline for the global hydrological community.

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。

↑