用于骤旱预测与解释的深度学习
Deep learning for flash drought forecasting and interpretation
AI总结:
针对现有业务系统难以准确预测骤旱的问题,提出基于公开水文气候数据的可解释深度学习模型IT-Drought,可提前更久预测土壤湿度和骤旱,还能提供骤旱发生的可解释性,助力干旱风险缓解。
摘要:
受气候变化影响,骤旱在全球范围内的发生频次日益增加,造成了广泛的社会经济与农业损失。然而,由于交互式水文气候过程的表征存在不确定性,业务预报系统仍难以实现及时、准确的骤旱预测。本文提出了IT-Drought(可解释干旱Transformer),这是一款基于公开水文气候数据构建的深度学习模型。在美国本土范围内,IT-Drought可有效预测最长42天的土壤湿度,平均可提前11天预测骤旱,表现大幅优于现有预报系统——现有系统仅能实现10天的有效土壤湿度预报,且无法预测骤旱。IT-Drought为骤旱发生提供了全新的数据驱动可解释性,确立了土壤湿度记忆效应的基准,揭示了以辐射和温度为主的气候条件的异质性影响与有效时间范围。研究结果凸显了利用IT-Drought开展骤旱预警与机制研究的潜力,最终可为干旱风险缓解提供支持。
英文摘要:
Flash droughts are increasingly occurring worldwide due to climate change, causing widespread socioeconomic and agricultural losses. However, timely and accurate flash drought forecasting remains challenging for operational forecast systems due to uncertain representations of interactive hydroclimate processes. Here, we introduce the Interpretable Transformer for Drought (IT-Drought), a deep learning model based on publicly available hydroclimate data. IT-Drought skillfully forecasts soil moisture up to 42 days and flash droughts up to 11 days ahead on average across the contiguous U.S., substantially outperforming existing forecast systems limited to 10-day skillful soil moisture forecasting and unable to forecast flash droughts. IT-Drought offers novel data-driven interpretability on flash drought onset, benchmarking the memory effects of soil moisture, and revealing heterogeneous impacts and effective time ranges of climatic conditions, predominantly radiation and temperature. The findings highlight the potential of leveraging IT-Drought for early warning and mechanistic investigation of flash droughts, ultimately supporting drought risk mitigation.
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。