Evaluation of Cloud Mask Performance of KOMPSAT-3 Top-of-Atmosphere Reflectance Incorporating Deeplabv3+ with Resnet 101 Model

Cloud detection is a crucial task in satellite remote sensing, influencing applications such as vegetation indices, land use analysis, and renewable energy estimation. This study evaluates the performance of cloud masks generated for KOMPSAT-3 and KOMPSAT-3A imagery using the DeepLabV3+ deep learnin...

Full description

Saved in:
Bibliographic Details
Main Authors: Suhwan Kim, Doehee Han, Yejin Lee, Eunsu Doo, Han Oh, Jonghan Ko, Jongmin Yeom
Format: Article
Language:English
Published: MDPI AG 2025-04-01
Series:Applied Sciences
Subjects:
Online Access:https://www.mdpi.com/2076-3417/15/8/4339
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850183782053707776
author Suhwan Kim
Doehee Han
Yejin Lee
Eunsu Doo
Han Oh
Jonghan Ko
Jongmin Yeom
author_facet Suhwan Kim
Doehee Han
Yejin Lee
Eunsu Doo
Han Oh
Jonghan Ko
Jongmin Yeom
author_sort Suhwan Kim
collection DOAJ
description Cloud detection is a crucial task in satellite remote sensing, influencing applications such as vegetation indices, land use analysis, and renewable energy estimation. This study evaluates the performance of cloud masks generated for KOMPSAT-3 and KOMPSAT-3A imagery using the DeepLabV3+ deep learning model with a ResNet-101 backbone. To overcome the limitations of digital number (DN) data, Top-of-Atmosphere (TOA) reflectance was computed and used for model training. Comparative analysis between the DN and TOA reflectance demonstrated significant improvements with the TOA correction applied. The TOA reflectance combined with the NDVI channel achieved the highest precision (69.33%) and F1-score (59.27%), along with a mean Intersection over Union (mIoU) of 46.5%, outperforming all the other configurations. In particular, this combination was highly effective in detecting dense clouds, achieving an mIoU of 48.12%, while the Near-Infrared, green, and red (NGR) combination performed best in identifying cloud shadows with an mIoU of 23.32%. These findings highlight the critical role of radiometric correction and optimal channel selection in enhancing deep learning-based cloud detection. This study demonstrates the crucial role of radiometric correction, optimal channel selection, and the integration of additional synthetic indices in enhancing deep learning-based cloud detection performance, providing a foundation for the development of more refined cloud masking techniques in the future.
format Article
id doaj-art-30d5a13d8a564ae184c17c3f5cae9164
institution OA Journals
issn 2076-3417
language English
publishDate 2025-04-01
publisher MDPI AG
record_format Article
series Applied Sciences
spelling doaj-art-30d5a13d8a564ae184c17c3f5cae91642025-08-20T02:17:14ZengMDPI AGApplied Sciences2076-34172025-04-01158433910.3390/app15084339Evaluation of Cloud Mask Performance of KOMPSAT-3 Top-of-Atmosphere Reflectance Incorporating Deeplabv3+ with Resnet 101 ModelSuhwan Kim0Doehee Han1Yejin Lee2Eunsu Doo3Han Oh4Jonghan Ko5Jongmin Yeom6Department of Earth and Environmental Sciences, Jeonbuk National University, Jeonju 54896, Republic of KoreaDepartment of Earth and Environmental Sciences, Jeonbuk National University, Jeonju 54896, Republic of KoreaDepartment of Earth and Environmental Sciences, Jeonbuk National University, Jeonju 54896, Republic of KoreaDepartment of Earth and Environmental Sciences, Jeonbuk National University, Jeonju 54896, Republic of KoreaKorea Aerospace Research Institute, 169-84, Gwahak-ro, Yuseong, Daejeon 34133, Republic of KoreaApplied Plant Science, Chonnam National University, 77 Yongbong-ro, Buk-gu, Gwangju 61186, Republic of KoreaDepartment of Earth and Environmental Sciences, Jeonbuk National University, Jeonju 54896, Republic of KoreaCloud detection is a crucial task in satellite remote sensing, influencing applications such as vegetation indices, land use analysis, and renewable energy estimation. This study evaluates the performance of cloud masks generated for KOMPSAT-3 and KOMPSAT-3A imagery using the DeepLabV3+ deep learning model with a ResNet-101 backbone. To overcome the limitations of digital number (DN) data, Top-of-Atmosphere (TOA) reflectance was computed and used for model training. Comparative analysis between the DN and TOA reflectance demonstrated significant improvements with the TOA correction applied. The TOA reflectance combined with the NDVI channel achieved the highest precision (69.33%) and F1-score (59.27%), along with a mean Intersection over Union (mIoU) of 46.5%, outperforming all the other configurations. In particular, this combination was highly effective in detecting dense clouds, achieving an mIoU of 48.12%, while the Near-Infrared, green, and red (NGR) combination performed best in identifying cloud shadows with an mIoU of 23.32%. These findings highlight the critical role of radiometric correction and optimal channel selection in enhancing deep learning-based cloud detection. This study demonstrates the crucial role of radiometric correction, optimal channel selection, and the integration of additional synthetic indices in enhancing deep learning-based cloud detection performance, providing a foundation for the development of more refined cloud masking techniques in the future.https://www.mdpi.com/2076-3417/15/8/4339operational systemGK-2A satellitedeep learningsolar radiationaerosol optical depth
spellingShingle Suhwan Kim
Doehee Han
Yejin Lee
Eunsu Doo
Han Oh
Jonghan Ko
Jongmin Yeom
Evaluation of Cloud Mask Performance of KOMPSAT-3 Top-of-Atmosphere Reflectance Incorporating Deeplabv3+ with Resnet 101 Model
Applied Sciences
operational system
GK-2A satellite
deep learning
solar radiation
aerosol optical depth
title Evaluation of Cloud Mask Performance of KOMPSAT-3 Top-of-Atmosphere Reflectance Incorporating Deeplabv3+ with Resnet 101 Model
title_full Evaluation of Cloud Mask Performance of KOMPSAT-3 Top-of-Atmosphere Reflectance Incorporating Deeplabv3+ with Resnet 101 Model
title_fullStr Evaluation of Cloud Mask Performance of KOMPSAT-3 Top-of-Atmosphere Reflectance Incorporating Deeplabv3+ with Resnet 101 Model
title_full_unstemmed Evaluation of Cloud Mask Performance of KOMPSAT-3 Top-of-Atmosphere Reflectance Incorporating Deeplabv3+ with Resnet 101 Model
title_short Evaluation of Cloud Mask Performance of KOMPSAT-3 Top-of-Atmosphere Reflectance Incorporating Deeplabv3+ with Resnet 101 Model
title_sort evaluation of cloud mask performance of kompsat 3 top of atmosphere reflectance incorporating deeplabv3 with resnet 101 model
topic operational system
GK-2A satellite
deep learning
solar radiation
aerosol optical depth
url https://www.mdpi.com/2076-3417/15/8/4339
work_keys_str_mv AT suhwankim evaluationofcloudmaskperformanceofkompsat3topofatmospherereflectanceincorporatingdeeplabv3withresnet101model
AT doeheehan evaluationofcloudmaskperformanceofkompsat3topofatmospherereflectanceincorporatingdeeplabv3withresnet101model
AT yejinlee evaluationofcloudmaskperformanceofkompsat3topofatmospherereflectanceincorporatingdeeplabv3withresnet101model
AT eunsudoo evaluationofcloudmaskperformanceofkompsat3topofatmospherereflectanceincorporatingdeeplabv3withresnet101model
AT hanoh evaluationofcloudmaskperformanceofkompsat3topofatmospherereflectanceincorporatingdeeplabv3withresnet101model
AT jonghanko evaluationofcloudmaskperformanceofkompsat3topofatmospherereflectanceincorporatingdeeplabv3withresnet101model
AT jongminyeom evaluationofcloudmaskperformanceofkompsat3topofatmospherereflectanceincorporatingdeeplabv3withresnet101model