Cloud Type Classification Through Semantic Segmentation for Analysis of Earth’s Radiative Balance

12 pages•Published: August 28, 2025

Yu-Wen Wu, Nofel Lagrosas, Sheng-Hsiang Wang and Albert Y. Chen

Abstract

Classifying nighttime clouds is crucial for understanding their impact on Earth's radiative balance. This study presents a semantic segmentation model using U-Net with a MobileNetV3 backbone for classification of the following cloud types: Cirrus, Nimbus, Stratus, and Cumulus from nighttime images. Despite challenges from reduced visibility at night, cloud types and coverage were effectively detected, classified and measured. The model results potentially facilitate future research on nighttime radiation analysis.

Keyphrases: ground based cloud images, night clouds, semantic segmentation model

In: Jack Cheng and Yu Yantao (editors). Proceedings of The Sixth International Conference on Civil and Building Engineering Informatics, vol 22, pages 947-958.

Links:	https://easychair.org/publications/paper/68WM
	https://doi.org/10.29007/9hjq

BibTeX entry

@inproceedings{ICCBEI2025:Cloud_Type_Classification_Through,
  author    = {Yu-Wen Wu and Nofel Lagrosas and Sheng-Hsiang Wang and Albert Y. Chen},
  title     = {Cloud Type Classification Through Semantic Segmentation for Analysis of Earth’s Radiative Balance},
  booktitle = {Proceedings of The Sixth International Conference on Civil and Building Engineering Informatics},
  editor    = {Jack Cheng and Yu Yantao},
  series    = {Kalpa Publications in Computing},
  volume    = {22},
  publisher = {EasyChair},
  bibsource = {EasyChair, https://easychair.org},
  issn      = {2515-1762},
  url       = {/publications/paper/68WM},
  doi       = {10.29007/9hjq},
  pages     = {947-958},
  year      = {2025}}

Download PDF Open PDF in browser