Spatial and Temporal Adaptive Gap-Filling Method Producing Daily Cloud-Free NDSI Time Series

Chen, Siyong; Wang, Xiaoyan; Guo, Hui; Xie, Peiyao; Sirelkhatim, Abuobaida M.

doi:10.1109/jstars.2020.2993037

Cited by 21 publications

(10 citation statements)

References 53 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In [150], Filmy cloud is removed on satellite imagery with NIR image and conditional generative adversarial nets, where the generator also adapts U-net architecture. Multi-temporal data can also be used in thick cloud removal [151]. In reference [152], the gated convolutional networks were used for cloud removal from bi-temporal remote sensing images, where U-net is used but not in GAN architecture.…”

Section: A Missing Data Reconstructionmentioning

confidence: 99%

A Review on Remote Sensing Data Fusion with Generative Adversarial Networks (GAN)

Liu¹

2021

Preprint

View full text Add to dashboard Cite

In the past decades, remote sensing (RS) data fusion has always been an active research community. A large number of algorithms and models have been developed. Generative Adversarial Networks (GAN), as an important branch of deep learning, show promising performances in variety of RS image fusions. This review provides an introduction to GAN for remote sensing data fusion. We briefly review the frequently-used architecture and characteristics of GAN in data fusion and comprehensively discuss how to use GAN to realize fusion for homogeneous RS data, heterogeneous RS data, and RS and ground observation data. We also analyzed some typical applications with GAN-based RS image fusion. This review takes insight into how to make GAN adapt to different types of fusion tasks and summarizes the advantages and disadvantages of GAN-based RS data fusion. Finally, we discuss the promising future research directions and make a prediction on its trends.

show abstract

Section: A Missing Data Reconstructionmentioning

confidence: 99%

A Review on Remote Sensing Data Fusion with Generative Adversarial Networks (GAN)

Liu¹

2021

Preprint

View full text Add to dashboard Cite

show abstract

“…The truth snow condition in cloud gaps is unknown. Here, we apply a cloud assumption method to verify the gap-filling method [35,51,52]. The idea of the cloud assumption is to use clouds to mask the known SCE and then compare the recovered SCE with the known SCE to assess the performance of the cloud removal results.…”

Section: Validation Based On the Cloud Assumptionmentioning

confidence: 99%

“…The basic evaluation metrics based on the confusion matrix (Table 1) were applied to evaluate the results of the produced daily cloud-free MODIS SCE products; the metrics included the overestimation error (OE), underestimation error (UE), overall accuracy (OA), and F-score (Fs) [52,60]. OE is the probability that the recovered pixel is snow but the corresponding pixel in the true image is snow-free; UE is the probability that the recovered pixel is snow-free but the true pixel is snow; OA is defined by the number of correctly recovered pixels divided by the total number of pixels; Fs penalizes both the overestimation and underestimation of snow without the influence of extensive snow-free areas.…”

Section: Accuracy Assessment Metricsmentioning

confidence: 99%

A Conditional Probability Interpolation Method Based on a Space-Time Cube for MODIS Snow Cover Products Gap Filling

et al. 2020

Self Cite

View full text Add to dashboard Cite

Seasonal snow cover is closely related to regional climate and hydrological processes. In this study, Moderate Resolution Imaging Spectroradiometer (MODIS) daily snow cover products from 2001 to 2018 were applied to analyze the snow cover variation in northern Xinjiang, China. As cloud obscuration causes significant spatiotemporal discontinuities in the binary snow cover extent (SCE), we propose a conditional probability interpolation method based on a space-time cube (STCPI) to remove clouds completely after combining Terra and Aqua data. First, the conditional probability that the central pixel and every neighboring pixel in a space-time cube of 5 × 5 × 5 with the same snow condition is counted. Then the snow probability of the cloud pixels reclassified as snow is calculated based on the space-time cube. Finally, the snow condition of the cloud pixels can be recovered by snow probability. The validation experiments with the cloud assumption indicate that STCPI can remove clouds completely and achieve an overall accuracy of 97.44% under different cloud fractions. The generated daily cloud-free MODIS SCE products have a high agreement with the Landsat–8 OLI image, for which the overall accuracy is 90.34%. The snow cover variation in northern Xinjiang, China, from 2001 to 2018 was investigated based on the snow cover area (SCA) and snow cover days (SCD). The results show that the interannual change of SCA gradually decreases as the elevation increases, and the SCD and elevation have a positive correlation. Furthermore, the interannual SCD variation shows that the area of increase is higher than that of decrease during the 18 years.

show abstract

“…Popular methods to fill the cloud gaps in the MODIS snow cover product include temporal-spatial filtering methods [36][37][38][39], adjacent temporal composite methods [40,41], and multisource fusion methods in which the cloud pixels are filled with the microwave snow water equivalent (SWE) or snow depth data [42][43][44]. Recently, some new gap-filling methods have been developed, such as methods based on similar pixels [45][46][47], time-space cubes [48], and conditional probability interpolation [49,50]. The basic idea of these cloud removal methods is to fill the value of pixels under the cloud with cloud-free pixels in the spatiotemporal neighborhood.…”

Section: Introductionmentioning

confidence: 99%

Cloud–Snow Confusion with MODIS Snow Products in Boreal Forest Regions

et al. 2022

Self Cite

View full text Add to dashboard Cite

Reliable cloud masks in Moderate Resolution Imaging Spectroradiometer (MODIS) snow cover products have a high potential to improve the retrieval of snow properties. However, cloud–snow confusion is a popular problem in MODIS snow cover products, especially in boreal forest areas. A large amount of forest snow is misclassified as clouds because of the low normalized difference snow index (NDSI), and excessive cloud masks limit the application of snow products. In addition, ice clouds are easily misclassified as snow due to their similar spectral characteristics, which leads to snow commission errors. In this paper, we quantitatively evaluated the cloud–snow confusion in Northeast China and found that snow-covered forests and transition zones from snow-covered to snow-free areas are prone to being misclassified as clouds, while clouds are less likely to be misclassified as snow. A temporal-sequence cloud–snow-distinguishing algorithm based on the high-frequency observation characteristics of the Himawarri-8 geostationary meteorological satellite is proposed. In the temporal-sequence images acquired from that satellite, the NDSI variance in cloud pixels should be greater than that of snow because clouds vary over time, while snow is relatively stable. In the MODIS snow cover products, the cloud pixels with NDSI variance lower than a threshold are identified as cloud-free areas and attributed their raw NDSI value, while the snow pixels with NDSI variance greater than the threshold are marked as clouds. We applied this method to MOD10A1 C6 in Northeast China. The results showed that the excessive cloud masks were greatly eliminated, and the new cloud mask was in good agreement with the real cloud distribution. At the same time, some possible ice clouds which had been misclassified as snow for their spectral characteristics similar to those of snow were identified correctly.

show abstract

Spatial and Temporal Adaptive Gap-Filling Method Producing Daily Cloud-Free NDSI Time Series

Cited by 21 publications

References 53 publications

A Review on Remote Sensing Data Fusion with Generative Adversarial Networks (GAN)

A Review on Remote Sensing Data Fusion with Generative Adversarial Networks (GAN)

A Conditional Probability Interpolation Method Based on a Space-Time Cube for MODIS Snow Cover Products Gap Filling

Cloud–Snow Confusion with MODIS Snow Products in Boreal Forest Regions

Contact Info

Product

Resources

About