Atlantic Hurricane Activity Prediction: A Machine Learning Approach
Atlantic Hurricane Activity Prediction: A Machine Learning Approach
复制标题
DOI：
10.3390/atmos12040455
复制
发表时间：
2021-04
期刊：
影响因子：
2.9
通讯作者：
Tanmay Asthana;H. Krim;Xia Sun;Siddharth Roheda;Lianqi Xie
中科院分区：
文献类型：
--
作者：
Tanmay Asthana;H. Krim;Xia Sun;Siddharth Roheda;Lianqi Xie
长期的飓风预测一直受到人们的极大关注，以保护社区免受生命损失和环境破坏。这种预测有助于为任何适当的预防和规划提供早期预警指导。在本文中，我们提出了一个能够对大西洋飓风活动进行良好季前预测的机器学习模型。该模型的发展需要一个明智的和非线性融合的各种数据模式，如海平面气压（SLP），海表面温度（SST），和风。卷积神经网络（CNN）被用作每个数据模态的特征提取器。这之后是一个特征级融合，以实现适当的推理。这种高度非线性的模型被进一步证明有潜力提前18个月做出熟练的预测。
Long-term hurricane predictions have been of acute interest in order to protect the community from the loss of lives, and environmental damage. Such predictions help by providing an early warning guidance for any proper precaution and planning. In this paper, we present a machine learning model capable of making good preseason-prediction of Atlantic hurricane activity. The development of this model entails a judicious and non-linear fusion of various data modalities such as sea-level pressure (SLP), sea surface temperature (SST), and wind. A Convolutional Neural Network (CNN) was utilized as a feature extractor for each data modality. This is followed by a feature level fusion to achieve a proper inference. This highly non-linear model was further shown to have the potential to make skillful predictions up to 18 months in advance.