用少量模拟精准找到极端风暴潮台风，提升风险评估效率。
LASSE: Learning Active Sampling for Storm Tide Extremes in Non-Stationary Climate Regimes
- 构建代理模型，通过在线学习主动选择关键台风样本。
- 仅用20%模拟数据即可100%准确识别破坏性台风。
- 适合气候风险评估、大尺度台风模拟研究者使用。
识别生成破坏性风暴潮的热带气旋对风险评估至关重要，但传统方法依赖大量昂贵的蒙特卡洛水动力模拟，难以实施。本文表明，代理模型在准确性、召回率和精确率方面表现优异，并能泛化到新气候情景。我们提出一种信息性在线学习方法，仅需少量水动力模拟即可快速搜索产生极端风暴潮的台风。从最小台风样本集出发，代理模型持续选择有信息量的数据进行在线重训练，迭代提升对破坏性台风的预测能力。在大规模降尺度台风目录上的实验显示，仅使用不足20%的模拟作为训练，即可实现100%精确度检索罕见破坏性风暴。该方法高效、可扩展，适用于大型台风目录及不同气候情景。
原文摘要 · Abstract (English)
Identifying tropical cyclones that generate destructive storm tides for risk assessment, such as from large downscaled storm catalogs for climate studies, is often intractable because it entails many expensive Monte Carlo hydrodynamic simulations. Here, we show that surrogate models are promising from accuracy, recall, and precision perspectives, and they "generalize" to novel climate scenarios. We then present an informative online learning approach to rapidly search for extreme storm tide-producing cyclones using only a few hydrodynamic simulations. Starting from a minimal subset of TCs with detailed storm tide hydrodynamic simulations, a surrogate model selects informative data to retrain online and iteratively improves its predictions of damaging TCs. Results on an extensive catalog of downscaled TCs indicate 100% precision in retrieving rare destructive storms using less than 20% of the simulations as training. The informative sampling approach is efficient, scalable to large storm catalogs, and generalizable to climate scenarios.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。