Deep learning approach for detecting tropical cyclones and their precursors in the simulation by a cloud-resolving global nonhydrostatic atmospheric model
Deep learning approach for detecting tropical cyclones and their precursors in the simulation by a cloud-resolving global nonhydrostatic atmospheric model
复制标题
DOI：
10.1186/s40645-018-0245-y
复制
发表时间：
2018-12-19
影响因子：
3.9
通讯作者：
Uchida, Seiichi
中科院分区：
文献类型：
--
作者：
Matsuoka, Daisuke;Nakano, Masuo;Uchida, Seiichi
我们提出了一种深度学习方法来识别热带气旋（tc）及其前兆。利用云分辨全球大气模拟计算的20年模拟长波辐射（OLR）用于训练二维深度卷积神经网络（cnn）。cnn使用50,000个tc及其前体和500,000个非tc数据进行二值分类训练。将集成CNN分类器应用于10年独立的全球OLR数据，用于检测前体和tc。研究了cnn在不同流域、季节和交货期下的性能。CNN模型在7 - 11月期间成功检测到北太平洋西部的tc及其前兆，检测概率（POD）为79.9-89.1%，虚警率（FAR）为32.8-53.4%。在北太平洋西部，前体形成前2天、5天和7天的检测结果分别为91.2%、77.8%和74.8%。此外，尽管检测性能与训练数据量和TC寿命相关，但在几个海洋盆地（如北大西洋）的TC季节，在样本量有限、寿命短的情况下，POD超过70%、FAR低于50%是有可能实现高检测的。
We propose a deep learning approach for identifying tropical cyclones (TCs) and their precursors. Twenty year simulated outgoing longwave radiation (OLR) calculated using a cloud-resolving global atmospheric simulation is used for training two-dimensional deep convolutional neural networks (CNNs). The CNNs are trained with 50,000 TCs and their precursors and 500,000 non-TC data for binary classification. Ensemble CNN classifiers are applied to 10year independent global OLR data for detecting precursors and TCs. The performance of the CNNs is investigated for various basins, seasons, and lead times. The CNN model successfully detects TCs and their precursors in the western North Pacific in the period from July to November with a probability of detection (POD) of 79.9-89.1% and a false alarm ratio (FAR) of 32.8-53.4%. Detection results include 91.2%, 77.8%, and 74.8% of precursors 2, 5, and 7days before their formation, respectively, in the western North Pacific. Furthermore, although the detection performance is correlated with the amount of training data and TC lifetimes, it is possible to achieve high detectability with a POD exceeding 70% and a FAR below 50% during TC season for several ocean basins, such as the North Atlantic, with a limited sample size and short lifetime.