Retrieval of cloud properties from thermal infrared radiometry using convolutional neural network

Retrieval of cloud properties from thermal infrared radiometry using convolutional neural network
复制标题

使用卷积神经网络从热红外辐射测量中检索云特性

DOI:
10.1016/j.rse.2022.113079
复制
发表时间:
2022
影响因子:
13.5
通讯作者:
Minghuai Wang
Minghuai Wang
中科院分区:
工程技术1区
文献类型:
--
作者:
Quan Wang;Chen Zhou;Xiaoyong Zhuge;Chao Liu;Fuzhong Weng;Minghuai Wang

文献摘要

参考文献

相似文献

在这项研究中,开发了一种深度学习算法,可以在没有辅助大气参数的情况下,从被动卫星观测中一致地检索白天和夜间云的属性。该算法将热红外(TIR)辐射,观察几何和高度纳入卷积神经网络(表示为TIR-CNN),并同时检索云掩模,云光学厚度(COT),有效粒子半径(CER)和云顶高度(CTH)。TIR-CNN模型在一整年中使用白天中分辨率成像光谱仪(MODIS)产品进行训练,并使用独立年份中观察到的被动和主动产品对结果进行验证和评估。评价结果表明,TIR-CNN反演的云特征与MODIS所有白天产品(云掩模、COT、CER和CTH)和夜间产品(云掩模和CTH)具有较好的一致性。检索的COT和CTH也表现出良好的协议与活跃的传感器在白天和夜间,表明该算法在昼夜循环中稳定地执行。·使用CNN对被动卫星的云属性进行太阳独立检索。·与传统算法相比,计算成本更低。·在没有辅助大气参数的情况下达到令人满意的精度。
In this study, a deep learning algorithm is developed to consistently retrieve the daytime and nighttime cloud properties from passive satellite observations without auxiliary atmospheric parameters. The algorithm involves the thermal infrared (TIR) radiances, viewing geometry, and altitude into a convolutional neural network (denoted as TIR-CNN), and retrieves the cloud mask, cloud optical thickness (COT), effective particle radius (CER), and cloud top height (CTH) simultaneously. The TIR-CNN model is trained using daytime Moderate Resolution Imaging Spectroradiometer (MODIS) products during a full year, and the results are validated and evaluated using passive and active products observed in independent years. The evaluation results show that the cloud properties retrieved by the TIR-CNN are well consistent with all available MODIS day-time products (cloud mask, COT, CER, and CTH) and night-time products (cloud mask and CTH). The retrieved COT and CTH also show good agreements with active sensors for both daytime and nighttime, indicating that the algorithm performs stably in the diurnal cycle. • Solar-independent retrieval of cloud properties for passive satellites with CNN. • Lower computational cost compared with traditional algorithms. • Achieving satisfactory accuracy without auxiliary atmospheric parameters.
DOI: 10.1016/j.rse.2019.05.022
发表时间: 2019-09
影响因子: 13.5
作者:
M. Wieland;Yu Li;S. Martinis
通讯作者: M. Wieland;Yu Li;S. Martinis
DOI: 10.1175/jam2309.1
发表时间: 2005-12-01
期刊: JOURNAL OF APPLIED METEOROLOGY
影响因子: --
作者:
Baum, BA;Yang, P;Bedka, ST
通讯作者: Bedka, ST
DOI: 10.5194/amt-2019-409
发表时间: 2019-11
影响因子: 3.8
作者:
Chenxi Wang;S. Platnick;K. Meyer;Zhibo Zhang;Yaping Zhou
通讯作者: Chenxi Wang;S. Platnick;K. Meyer;Zhibo Zhang;Yaping Zhou
DOI: 10.1016/j.rse.2011.01.010
发表时间: 2011-06
影响因子: 13.5
作者:
T. Nauss;A. Kokhanovsky
通讯作者: T. Nauss;A. Kokhanovsky
太阳光谱和红外光谱重叠区域的辐射传输
DOI: 10.1016/j.jqsrt.2018.08.025
发表时间: 2018
影响因子: 2.3
作者:
Zhang Feng;Wu Kun;Li Jiangnan;Zhang Hua;Hu Shuai
通讯作者: Hu Shuai