Preprints
https://doi.org/10.5194/essd-2024-536
https://doi.org/10.5194/essd-2024-536
26 Nov 2024
 | 26 Nov 2024
Status: this preprint is currently under review for the journal ESSD.

A Global Classification Dataset of Daytime and Nighttime Marine Low-cloud Mesoscale Morphology Based on Deep Learning Methods

Yuanyuan Wu, Jihu Liu, Yannian Zhu, Yu Zhang, Yang Cao, Kang-En Huang, Boyang Zheng, Yichuan Wang, Yanyun Li, Quan Wang, Chen Zhou, Yuan Liang, Jianning Sun, Minghuai Wang, and Daniel Rosenfeld

Abstract. Marine low clouds tend to organize into larger mesoscale patterns with distinct morphological appearances over the ocean, referred to as mesoscale morphology. While prior studies have mainly examined the fundamental characteristics and shortwave radiative effects of these mesoscale morphologies, their behaviour in the nighttime marine boundary layer (MBL) remains underexplored due to limited observations. To address this, we created a global classification dataset of daytime and nighttime mesoscale morphologies of marine low clouds using a deep residual network model and Moderate Resolution Imaging Spectroradiometer (MODIS) infrared radiance data, with machine-learning-retrieved all-day cloud optical thickness aiding in model training. We analysed day-night contrasts in climatology, seasonal cycles, and cloud properties of different cloud morphology types in this study. Results show that relative frequency of occurrence (RFO) of closed mesoscale cellular convection (MCC) significantly increase at night, while that of suppressed cumulus (Cu) shows a remarkable decrease. Disorganized MCC and clustered Cu display a slight frequency increase during night. In addition, solid stratus and three MCC types exhibit distinct seasonal variations, whereas two cumuliform types show no clear seasonal cycle. Our dataset extends the study of mesoscale cloud morphologies from daytime to nighttime and 1° × 1° resolution makes it better match with other climate datasets. It will provide a vital foundation for further research on the interactions between cloud morphology and climate processes. Our dataset is open-access and available at https://doi.org/10.5281/zenodo.13990646 (Wu et al., 2024).

Publisher's note: Copernicus Publications remains neutral with regard to jurisdictional claims made in the text, published maps, institutional affiliations, or any other geographical representation in this preprint. The responsibility to include appropriate place names lies with the authors.
Yuanyuan Wu, Jihu Liu, Yannian Zhu, Yu Zhang, Yang Cao, Kang-En Huang, Boyang Zheng, Yichuan Wang, Yanyun Li, Quan Wang, Chen Zhou, Yuan Liang, Jianning Sun, Minghuai Wang, and Daniel Rosenfeld

Status: open (until 11 Jan 2025)

Comment types: AC – author | RC – referee | CC – community | EC – editor | CEC – chief editor | : Report abuse
Yuanyuan Wu, Jihu Liu, Yannian Zhu, Yu Zhang, Yang Cao, Kang-En Huang, Boyang Zheng, Yichuan Wang, Yanyun Li, Quan Wang, Chen Zhou, Yuan Liang, Jianning Sun, Minghuai Wang, and Daniel Rosenfeld

Data sets

Global Classification Dataset of Daytime and Nighttime Marine Low-cloud Mesoscale Morphology Yuanyuan Wu, Jihu Liu, Yannian Zhu, Yu Zhang, Yang Cao, Kang-En Huang, Boyang Zheng, Yichuan Wang, Quan Wang, Chen Zhou, Yuan Liang, Minghuai Wang, and Daniel Rosenfeld https://doi.org/10.5281/zenodo.13990646

Model code and software

Cloud-morphology-dataset Yuanyuan Wu, Jihu Liu, Yannian Zhu, Yu Zhang, Yang Cao, Kang-En Huang, Boyang Zheng, and Yichuan Wang https://github.com/YuanyuanWu-NJU/Cloud-morphology-dataset

Yuanyuan Wu, Jihu Liu, Yannian Zhu, Yu Zhang, Yang Cao, Kang-En Huang, Boyang Zheng, Yichuan Wang, Yanyun Li, Quan Wang, Chen Zhou, Yuan Liang, Jianning Sun, Minghuai Wang, and Daniel Rosenfeld

Viewed

Total article views: 148 (including HTML, PDF, and XML)
HTML PDF XML Total Supplement BibTeX EndNote
118 25 5 148 22 3 3
  • HTML: 118
  • PDF: 25
  • XML: 5
  • Total: 148
  • Supplement: 22
  • BibTeX: 3
  • EndNote: 3
Views and downloads (calculated since 26 Nov 2024)
Cumulative views and downloads (calculated since 26 Nov 2024)

Viewed (geographical distribution)

Total article views: 148 (including HTML, PDF, and XML) Thereof 148 with geography defined and 0 with unknown origin.
Country # Views %
  • 1
1
 
 
 
 
Latest update: 13 Dec 2024
Download
Short summary
In this paper, based on deep learning method, we established a global classification dataset of daytime and nighttime marine low-cloud mesoscale morphology. It aims to promote a comprehensive understanding of the cloud dynamics and cloud-climate feedback. Closed mesoscale cellular convection (MCC) clouds occur more frequently at night, while suppressed cumulus exhibit remarkable decrease. Solid stratus and MCC cloud types show clear seasonal variations.
Altmetrics