ハドレー循環と熱帯低気圧の数日規模の相互作用

哈德利环流与热带气旋之间的多日相互作用

• 批准号: 20J21462
• 负责人: 王 心月
• 金额: $ 1.6万
• 依托单位: Tohoku University
• 依托单位国家: 日本
• 项目类别: Grant-in-Aid for JSPS Fellows
• 财政年份: 2020
• 资助国家: 日本
• 起止时间: 2020-04-24 至 2023-03-31
• 项目状态: 已结题
• 来源: https://kaken.nii.ac.jp/en/grant/KAKENHI-PROJECT-20J21462/
• 关键词: deep neural network; Deep neural network; Cloud retrieval; Himawari-8

In this year, we developed a cloud retrieval model for the Himawari-8 infrared measurements, based on a deep neural network. The model has high accuracy when validated with the the active remote sensing datasets, it performs much better than physics-based retrieval models and can provide near-real time estimate of cloud properties such as cloud top height, cloud optical thickness, and cloud mask, which can be realistically applied to severe weather monitoring and mesoscale studies.

今年，我们开发了一个基于深度神经网络的Himawari-8红外测量云检索模型。该模型经主动遥感数据验证，具有较高的精度，比基于物理的反演模型性能更好，可以提供近实时的云顶高度、云光学厚度和云掩模等云属性估计，可实际应用于灾害性天气监测和中尺度研究。

项目成果

Cloud identification and property retrieval from Himawari-8 infrared measurements via a deep neural network

• DOI: 10.1016/j.rse.2022.113026
• 发表时间: 2022-06
• 期刊: Remote Sensing of Environment
• 影响因子: 13.5
• 作者: Xinyue Wang;H. Iwabuchi;Takaya Yamashita

Retrieval of cloud properties from Himawari-8 measurement with a deep neural network method

使用深度神经网络方法从 Himawari-8 测量中检索云属性

• 发表时间: 2021
• 作者: Wang Xinyue;Iwabuchi Hironobu;Yamashita Takaya;欧陽珊珊;Xinyue Wang
• 通讯作者: Xinyue Wang