Convolutional neural networks for detecting challenging cases in cloud masking using Sentinel-2 imagery

Abstract

Cloud contamination represents a large obstacle for mapping the earth's surface using remotely sensed data. Therefore, cloudy pixels should be identified and eliminated before any further data processing can be achieved. Although several threshold, multi-temporal and machine learning applications have been developed to tackle this issue, it still remains a challenge. The main challenges are imposed by the difficulty to detect thin clouds and to separate bright clouds from bright non-cloud objects. Convolutional neural networks (CNNs) have proven to be one of the most promising methods for image classification tasks and their use is rapidly increasing in remote sensing problems. CNNs present interesting properties for image processing since they directly exploit not only the spectral information but also the spatial covariance of the data. In this work, we study the applicability of CNNs in cloud detection of Sentinel-2 imagery, a complex remote sensing problem with crucial spatial context. A patch-to-pixel CNN architecture consisting of three convolutional layers and two fully connected layers is trained on a recently available manually created public dataset. The results were evaluated both qualitatively and quantitatively through comparison with ground truth cloud masks and state-of-the art pixel-based algorithms (Fmask, Sen2Cor). It was shown that the proposed architecture even though simpler than the deep learning architectures proposed by recent literature, performs very favorably, especially in the challenging cases. Besides the evaluation of the results, feature maps where observed as an initial effort to extract the weights of the useful kernels for cloud masking applications.

Artificial intelligence convolutional neural networks map giant kelp forests from satellite imagery

“…The second potential drawback has to do with the cloud detection algorithm used. Cloud contamination is a recurrent challenge in applications using satellite imagery 21 , 72 , and our study might not be the exception. Typically, clouds are identified and removed before data processing 73 , 74 .…”

“…Yet, the potential presence of occasional clouds could have interfered in kelp detection, owing to changes in reflectance. Considering the automatic implementation proposed, it is not possible to measure such an effect, and only the future optimization of algorithms and sensors may overcome this 72 . The third potential drawback has to do with the high variability in the spatial patterns of kelp forests.…”

Fine-Tuning Self-Organizing Maps for Sentinel-2 Imagery: Separating Clouds from Bright Surfaces

“…Convolutional patch-to-pixel and encoder-decoder segmentation architectures have produced in general more successful and more effortless results for the separation of clouds from bright surfaces due to their inherent ability to perceive spatial information. Such a conclusion was reached in studies conducted in WV-2 [18], Sentinel-2 [18,36], Landsat [37] and Gaofen-1 [26] where bright non-cloud object misclassification was not observed. Satisfactory results were also produced by an artificial neural network architecture (ANN) that managed to separate sunglint and noise in Sentinel-2 ocean images [38].…”