Improving statistical forecasts of Tropical Cyclone (TC) intensity is limited by complex nonlinear interactions and difficulty in identifying relevant predictors. Conventional methods prioritize correlation or fit, often overlooking confounding variables and limiting generalizability to unseen TCs. To address this, we leverage a multidata causal discovery framework with a replicated dataset based on Statistical Hurricane Intensity Prediction Scheme (SHIPS) using ERA5 meteorological reanalysis. We conduct multiple experiments to identify and select predictors causally linked to TC intensity changes. We then train multiple linear regression models to compare causal feature selection with no selection, correlation, and random forest feature importance across five forecast lead times from 1 to 5 days (24 to 120 hours). Causal feature selection consistently outperforms on unseen test cases, especially for lead times shorter than 3 days. The causal features primarily include vertical shear, mid-tropospheric potential vorticity and surface moisture conditions, which are physically significant yet often underutilized in TC intensity predictions. We build an extended predictor set (SHIPS plus) by adding selected features to the standard SHIPS predictors. SHIPS plus yields increased short-term predictive skill at lead times of 24, 48, and 72 hours. Adding nonlinearity using multilayer perceptron further extends skill to longer lead times, despite our framework being purely regional and not requiring global forecast data. Operational SHIPS tests confirm that three of the six added causally discovered predictors improve forecast skill, with the largest gains at longer lead times. Our results demonstrate that causal discovery improves TC intensity prediction and pave the way toward more empirical forecasts.

翻译：改进热带气旋（TC）强度的统计预报受限于复杂的非线性相互作用以及识别相关预测因子的困难。传统方法优先考虑相关性或拟合度，常常忽略混杂变量，并限制了对未见TC的泛化能力。为解决此问题，我们利用一个基于ERA5气象再分析数据的统计飓风强度预测方案（SHIPS）复现数据集，采用多数据因果发现框架。我们进行了多项实验，以识别和选择与TC强度变化存在因果关联的预测因子。随后，我们训练了多元线性回归模型，在1至5天（24至120小时）的五个预报提前期上，将因果特征选择与无选择、相关性选择以及随机森林特征重要性选择进行比较。因果特征选择在未见测试案例上始终表现更优，尤其是在提前期短于3天的情况下。这些因果特征主要包括垂直风切变、中层位势涡度和地表湿度条件，这些因子具有重要的物理意义，但在TC强度预测中常未得到充分利用。我们通过将选定的特征添加到标准SHIPS预测因子中，构建了一个扩展的预测因子集（SHIPS plus）。SHIPS plus在24、48和72小时的短期预报提前期上展现出更高的预测技巧。尽管我们的框架纯粹是区域性的且无需全球预报数据，但通过使用多层感知机引入非线性，进一步将预测技巧延伸至更长的提前期。业务化SHIPS测试证实，在新增的六个因果发现预测因子中，有三个提高了预报技巧，其中在较长提前期上增益最大。我们的结果表明，因果发现改进了TC强度预测，并为实现更具经验性的预报铺平了道路。