Improving Fmask cloud and cloud shadow detection in mountainous area for Landsats 4–8 images

Qiu, Shi; He, Bin; Zhu, Zhe; Liao, Ziqi; Quan, Xingwen

doi:10.1016/j.rse.2017.07.002

Cited by 116 publications

(78 citation statements)

References 44 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Twelve Landsat 8 images (level 1 images from 2015‐2017) with a resolution of 30 m and cloud cover less than 20% were seamlessly mosaicked to account for the high cloud coverage over Southeast Asia and Singapore. The Fmask algorithm (Qiu et al, ; Zhu et al, ) was applied before mosaicking to further separate cloud cirrus, shadow, and water from clear pixels. This mosaicked image, together with data for building height and vegetation, was used in SAGA GIS software (Conrad et al, ) to discriminate between the spectral attribute and building height of different LCZ types based on the training areas, which were created by digitizing parts of the city and the surrounding areas that represent exemplars of LCZ types in the study area based on researchers' local knowledge.…”

Section: Model Configurationsmentioning

confidence: 99%

High‐Resolution, Multilayer Modeling of Singapore's Urban Climate Incorporating Local Climate Zones

Mughal

Yin

et al. 2019

JGR Atmospheres

View full text Add to dashboard Cite

We applied Weather Research and Forecasting (WRF) model's Multilayer Urban Canopy Model (MLUCM) to simulate the urban climate of Singapore during a hot period in April 2016. The high‐resolution local climate zone (LCZ) map was used as urban land use/land cover data in order to study the intraurban variability in different LCZ classes. The LCZ map for Singapore was developed by adopting the World Urban Database and Access Portal Tools (WUDAPT) methodology based on satellite remote sensing imageries and building height data. The coupled WRF/MLUCM model was validated using meteorological data from stations across Singapore. Higher index of agreement compared to observations and lower root‐mean‐squared error of 2‐m temperature, relative humidity, and global horizontal irradiance showed satisfactory model performance. A sensitivity analysis of initial and boundary conditions helped in determining the model configuration with the least error for quantifying the urban heat island (UHI) effect. The diurnal cycle and the spatial pattern of UHI were investigated, and it was found that the mean UHI intensity peaked in the early morning at 2.2 °C, reaching 3.6 °C in the Compact High Rise (LCZ1) areas. The anthropogenic heat due to indoor air conditioning was found to play a major role in all the processes studied, while the effect of the different land use types was most pronounced during nighttime and least visible near noon. The UHI circulation developed near the central catchment is found to prevent sea breezes from further propagating inland.

show abstract

Section: Model Configurationsmentioning

confidence: 99%

High‐Resolution, Multilayer Modeling of Singapore's Urban Climate Incorporating Local Climate Zones

Mughal

Yin

et al. 2019

JGR Atmospheres

View full text Add to dashboard Cite

show abstract

“…As shown in Table 2, high-resolution Landsat as well as Sentinel-2 data were chosen based on the criteria of least cloud cover in the shortest temporal distance. The Fmask algorithm [52] was then applied to each scene to derive total SCE (for detailed parameters setting refer to [18]). Based on the resultant total SCE, 10,000 random points were stratified and sampled in both snow-covered and snow-free areas.…”

Section: External Validations With Optical-based Sce and Snow Depth Rmentioning

confidence: 99%

A Combination of PROBA-V/MODIS-Based Products with Sentinel-1 SAR Data for Detecting Wet and Dry Snow Cover in Mountainous Areas

et al. 2019

View full text Add to dashboard Cite

In the present study, we explore the value of employing both vegetation indexes as well as land surface temperature derived from Project for On-Board Autonomy – Vegetation (PROBA-V) and Moderate Resolution Imaging Spectroradiometer (MODIS) sensors, respectively, to support the detection of total (wet + dry) snow cover extent (SCE) based on a simple tuning machine learning approach and provide reliability maps for further analysis. We utilize Sentinel-1-based synthetic aperture radar (SAR) observations, including backscatter coefficient, interferometric coherence, and polarimetric parameters, and four topographical factors as well as vegetation and temperature information to detect the total SCE with a land cover-dependent random forest-based approach. Our results show that the overall accuracy and F-measure are over 90% with an ’Area Under the receiver operating characteristic Curve (ROC)’ (AUC) score of approximately 80% over five study areas located in different mountain ranges, continents, and hemispheres. These accuracies are also confirmed by a comprehensive validation approach with different data sources, attesting the robustness and global transferability. Additionally, based on the reliability maps, we find an inversely proportional relationship between classification reliability and vegetation density. In conclusion, comparing to a previous study only utilizing SAR-based observations, the method proposed in the present study provides a complementary approach to achieve a higher total SCE mapping accuracy while maintaining global applicability with reliable accuracy and corresponding uncertainty information.

show abstract

“…In recent years, researchers have developed many cloud detection methods. These methods can be divided into three main categories: threshold-based [6,7,8,9], handcrafted [10,11], and deep learning-based [12,13] approaches. Zhu et al in [7] introduced the Function of mask (Fmask) algorithm.…”

mentioning

confidence: 99%

“…from Cirrus band of Landsat 8 to increase the accuracy of the detected clouds and is currently utilized to produce cloud masks of the Landsat Level-1 data products [14]. Qui et al in [9] integrated Digital Elevation Map (DEM) information into Fmask and improved its performance in mountainous areas.…”

mentioning

confidence: 99%

Cloud-Net: An End-To-End Cloud Detection Algorithm for Landsat 8 Imagery

Mohajerani

Saeedi

2019

IGARSS 2019 - 2019 IEEE International Geoscience and Remote Sensing Symposium

142

View full text Add to dashboard Cite

Cloud detection in satellite images is an important first-step in many remote sensing applications. This problem is more challenging when only a limited number of spectral bands are available. To address this problem, a deep learning-based algorithm is proposed in this paper. This algorithm consists of a Fully Convolutional Network (FCN) that is trained by multiple patches of Landsat 8 images. This network, which is called Cloud-Net, is capable of capturing global and local cloud features in an image using its convolutional blocks. Since the proposed method is an end-to-end solution no complicated pre-processing step is required. Our experimental results prove that the proposed method outperforms the state-ofthe-art method over a benchmark dataset by 8.7% in Jaccard Index.

show abstract

Improving Fmask cloud and cloud shadow detection in mountainous area for Landsats 4–8 images

Cited by 116 publications

References 44 publications

High‐Resolution, Multilayer Modeling of Singapore's Urban Climate Incorporating Local Climate Zones

High‐Resolution, Multilayer Modeling of Singapore's Urban Climate Incorporating Local Climate Zones

A Combination of PROBA-V/MODIS-Based Products with Sentinel-1 SAR Data for Detecting Wet and Dry Snow Cover in Mountainous Areas

Cloud-Net: An End-To-End Cloud Detection Algorithm for Landsat 8 Imagery

Contact Info

Product

Resources

About