CloudS2Mask: A novel deep learning approach for improved cloud and cloud shadow masking in Sentinel-2 imagery

Authors

Nicholas J. Wright, Department of Primary Industries and Regional Development, Western AustraliaFollow
John M A Duncan, The University of Western Australia
Nik Callow, University of Western Australia
Sally E. Thompson, The University of Western Australia
Richard J. George Dr, Department of Primary Industries and Regional Development, Western AustraliaFollow

Document Type

Article

Publication Date

5-15-2024

Journal Title

Remote Sensing of Environment

ISSN

Print: 0034-4257 Electronic: 1879-0704

Keywords

Cloud, Cloud shadow, Convolutional neural network, Deep learningMaskSentinel-2

Disciplines

Climate | Water Resource Management

Abstract

The Sentinel-2 satellite constellation produces high-resolution multispectral data, covering the entire Earth's land surface every five days. However, the use of this data is significantly impacted by the presence of pixels affected by cloud and shadow. Precise and efficient cloud and cloud shadow masking methods are required for the automated use of this data. Here, we present CloudS2Mask, a new and open-source Python deep-learning library to detect cloud and cloud shadows in Sentinel-2 data accurately and efficiently. CloudS2Mask is trained on multiple large global datasets including CloudSEN12, KappaSet, Sentinel-2 Cloud Mask Catalogue, Sentinel-2 reference cloud masks generated by an active learning method and a custom CloudS2Mask dataset. Using techniques such as progressive resizing, hard fine-tuning, and transfer learning, CloudS2Mask outperforms published models when evaluated on both the CloudSEN12 and the PixBox datasets in terms of classification accuracy. Compared to the next best-published results, CloudS2Mask improves Balanced Overall Accuracy metrics on the CloudSEN12 dataset by 1.2% for cloud, 2.8% for cloud shadow and 1.1% for clear classification. CloudS2Mask provides a range of customisable options combined with novel pre-processing and post-processing approaches to meet task-specific needs, enabling mean scene processing speeds up to 44 times faster than current state-of-the-art methods. The application of novel techniques in CloudS2Mask, combined with its accuracy and processing speed, underscores its potential to streamline the automated cloud and cloud shadow detection of Sentinel-2 data.

Recommended Citation

Wright, N J, Duncan, J M, Callow, N, Thompson, S E, and George, R J. (2024), CloudS2Mask: A novel deep learning approach for improved cloud and cloud shadow masking in Sentinel-2 imagery. Remote Sensing of Environment, 306 (114122).
https://library.dpird.wa.gov.au/cs_researchart/6