JOHAN: A Joint Online Hurricane Trajectory and Intensity Forecasting Framework

JOHAN: A Joint Online Hurricane Trajectory and Intensity Forecasting Framework
复制标题

JOHAN:联合在线飓风轨迹和强度预报框架

DOI:
10.1145/3447548.3467400
复制
发表时间:
2021
期刊:
KDD '21: Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining
影响因子:
--
通讯作者:
Tan, Pang-Ning
Tan, Pang-Ning
中科院分区:
--
文献类型:
--
作者:
Wang, Ding;Tan, Pang-Ning

文献摘要

参考文献

相似文献

飓风是最具灾难性的自然力量之一,大风和内陆洪水可能会造成严重的财产损失和人员伤亡。因此,准确地长期预测飓风前进的轨迹和强度对于向平民和应急响应人员提供及时警告以减轻代价高昂的损失及其危及生命的影响至关重要。在本文中,我们提出了一种名为 JOHAN 的新型在线学习框架,该框架根据动态(物理)飓风模型集合产生的输出同时预测飓风的轨迹和强度。此外,JOHAN 旨在生成序值飓风强度类别的准确预测,以确保其严重程度能够可靠地传达给公众。该框架还采用指数加权分位数损失函数来使算法偏向于提高对即将登陆的高类别飓风的预测准确性。使用真实世界飓风数据的实验结果证明了 JOHAN 与几种最先进的学习方法相比的优越性。
Hurricanes are one of the most catastrophic natural forces with potential to inflict severe damages to properties and loss of human lives from high winds and inland flooding. Accurate long-term forecasting of the trajectory and intensity of advancing hurricanes is therefore crucial to provide timely warnings for civilians and emergency responders to mitigate costly damages and their life-threatening impact. In this paper, we present a novel online learning framework called JOHAN that simultaneously predicts the trajectory and intensity of a hurricane based on outputs produced by an ensemble of dynamic (physical) hurricane models. In addition, JOHAN is designed to generate accurate forecasts of the ordinal-valued hurricane intensity categories to ensure that their severity level can be reliably communicated to the public. The framework also employs exponentially-weighted quantile loss functions to bias the algorithm towards improving its prediction accuracy for high category hurricanes approaching landfall. Experimental results using real-world hurricane data demonstrated the superiority of JOHAN compared to several state-of-the-art learning approaches.
ORION:在线正则化多任务回归及其在集合预测中的应用
DOI: 10.1109/icdm.2014.90
发表时间: 2014
期刊: 2014 IEEE International Conference on Data Mining
影响因子: --
作者:
Jianpeng Xu;P. Tan;L. Luo
通讯作者: L. Luo
OMuLeT:用于飓风轨迹预报的在线多引线时间位置预测
DOI: 10.1609/aaai.v34i01.5444
发表时间: 2020
影响因子: 1.4
作者:
Ding Wang;Boyang Liu;P. Tan;L. Luo
通讯作者: L. Luo
DOI: 10.5670/oceanog.2014.73
发表时间: 2014-09-01
期刊: OCEANOGRAPHY
影响因子: 2.8
作者:
Hogan, Timothy F.;Liu, Ming;Chang, Simon W.
通讯作者: Chang, Simon W.
应用支持向量回归的可变区域选择方法的开发
DOI: --
发表时间: 2012
期刊:
影响因子: --
作者:
金子弘昌;船津公人
通讯作者: 船津公人