Beyond Point Prediction: Capturing Zero-Inflated & Heavy-Tailed Spatiotemporal Data with Deep Extreme Mixture Models
Beyond Point Prediction: Capturing Zero-Inflated & Heavy-Tailed Spatiotemporal Data with Deep Extreme Mixture Models
复制标题
DOI：
10.1145/3534678.3539464
复制
发表时间：
2022-08
期刊：
影响因子：
--
通讯作者：
T. Wilson;Andrew McDonald;A. Galib;Pang-Ning Tan;L. Luo
中科院分区：
文献类型：
--
作者：
T. Wilson;Andrew McDonald;A. Galib;Pang-Ning Tan;L. Luo
零膨胀、重尾时空数据在科学和工程领域很常见，从气候科学到气象学和地震学。在这种情况下，建模的一个核心目标是预测极端和非极端事件的强度、频率和时间;但在深度学习的背景下，这一目标提出了几个关键挑战。首先，应用于此类数据的深度学习框架必须统一表征零事件、中等事件和极端事件的分布混合。第二，框架必须能够在混合分布的每个组成部分上强制执行参数约束。最后，框架必须足够灵活，以适应训练后用于定义极端事件的阈值的任何变化。为了应对这些挑战，我们提出了深度极端混合模型（DEMM），将基于深度学习的障碍模型与极值理论相融合，以实现零膨胀，重尾时空变量的点和分布预测。该框架使用户能够动态地设置一个阈值来定义极端事件在推理时，而不需要重新训练。我们提出了一个广泛的实验分析应用DEMM降水预报，并观察点和分布预测的显着改善。所有代码都可以在https://github.com/andrewmcdonald27/DeepExtremeMixtureModel上找到。
Zero-inflated, heavy-tailed spatiotemporal data is common across science and engineering, from climate science to meteorology and seismology. A central modeling objective in such settings is to forecast the intensity, frequency, and timing of extreme and non-extreme events; yet in the context of deep learning, this objective presents several key challenges. First, a deep learning framework applied to such data must unify a mixture of distributions characterizing the zero events, moderate events, and extreme events. Second, the framework must be capable of enforcing parameter constraints across each component of the mixture distribution. Finally, the framework must be flexible enough to accommodate for any changes in the threshold used to define an extreme event after training. To address these challenges, we propose Deep Extreme Mixture Model (DEMM), fusing a deep learning-based hurdle model with extreme value theory to enable point and distribution prediction of zero-inflated, heavy-tailed spatiotemporal variables. The framework enables users to dynamically set a threshold for defining extreme events at inference-time without the need for retraining. We present an extensive experimental analysis applying DEMM to precipitation forecasting, and observe significant improvements in point and distribution prediction. All code is available at https://github.com/andrewmcdonald27/DeepExtremeMixtureModel.