scholarly journals Evaluation of Methods for Mapping the Snow Cover Area at High Spatio-Temporal Resolution with VENμS

2020 ◽  
Vol 12 (18) ◽  
pp. 3058
Author(s):  
Mohamed Wassim Baba ◽  
Simon Gascoin ◽  
Olivier Hagolle ◽  
Elsa Bourgeois ◽  
Camille Desjardins ◽  
...  
Keyword(s):  
Machine Learning ◽  
Snow Cover ◽  
Temporal Resolution ◽  
Near Infrared ◽  
Snow Accumulation ◽  
Learning Method ◽  
Snow Cover Area ◽  
High Atlas ◽  
Detection Algorithms ◽  
Sentinel 2

The VENμS mission launched in 2017 provides multispectral optical images of the land surface with a 2-day revisit time at 5 m resolution for over 100 selected sites. A few sites are subject to seasonal snow accumulation, which gives the opportunity to monitor the variations of the snow cover area at unprecedented spatial and temporal resolution. However, the 12 spectral bands of VENμS only cover the visible and near-infrared region of the spectra while existing snow detection algorithms typically make use of a shortwave infrared band to determine the presence of snow. Here, we evaluate two alternative snow detection algorithms. The first one is based on a normalized difference index between the near-infrared and the visible bands, and the second one is based on a machine learning approach using the Theia Sentinel-2 snow products as training data. Both approaches are tested using Sentinel-2 data (as surrogate of VENμS data) as well as actual VENμS in the Pyrenees and the High Atlas. The results confirm the possibility of retrieving snow cover without SWIR with a slight loss in performance. As expected, the results confirm that the machine learning method provides better results than the index-based approach (e.g., an RMSE equal to the learning method 1.35% and for the index-based method 10.80% in the High Atlas.). The improvement is more evident in the Pyrenees probably due to the presence of vegetation which complicates the spectral signature of the snow cover area in VENμS images.

scholarly journals Assimilation of Sentinel-2 Data into a Snowpack Model in the High Atlas of Morocco

2018 ◽  
Author(s):  
Mohamed Wassim Baba ◽  
Simon Gascoin ◽  
Lahoucine Hanich
Keyword(s):  
Data Assimilation ◽  
Snow Cover ◽  
Snow Water Equivalent ◽  
Snow Cover Area ◽  
High Atlas ◽  
Data Assimilation Scheme ◽  
Snow Cover Extent ◽  
Assimilation Scheme ◽  
Sentinel 2

The snow melt from the High Atlas is a critical water resource in Morocco. In spite of its importance, monitoring the spatio-temporal evolution of key snow cover properties like the snow water equivalent remains challenging due to the lack of in situ measurements at high elevation. Since 2015, the Sentinel-2 mission provides high spatial resolution images with a 5 day revisit time, which offers new opportunities to characterize snow cover distribution in mountain regions. Here we present a new data assimilation scheme to estimate the state of the snowpack without in situ data. The model was forced using MERRA-2 data and a particle filter was developed to dynamically reduce the biases in temperature and precipitation using Sentinel-2 observations of the snow cover area. The assimilation scheme was implemented using SnowModel, a distributed energy-balance snowpack model and tested in a pilot catchment in the High Atlas. The study period covers 2015-2016 snow season which corresponds to the first operational year of Sentinel-2A, therefore the full revisit capacity was not yet achieved. Yet, we show that the data assimilation led to a better agreement with independent observations of the snow height at an automatic weather station and the snow cover extent from MODIS. The performance of the data assimilation scheme should benefit from the continuous improvements in MERRA-2 reanalyses and the full revisit capacity of Sentinel-2.

scholarly journals Assimilation of Sentinel-2 Data into a Snowpack Model in the High Atlas of Morocco

2018 ◽  
Vol 10 (12) ◽  
pp. 1982 ◽  
Author(s):  
Mohamed Baba ◽  
Simon Gascoin ◽  
Lahoucine Hanich
Keyword(s):  
Data Assimilation ◽  
Snow Cover ◽  
Snow Water Equivalent ◽  
Snow Cover Area ◽  
High Atlas ◽  
Data Assimilation Scheme ◽  
Snow Cover Extent ◽  
Assimilation Scheme ◽  
Sentinel 2

The snow melt from the High Atlas is a critical water resource in Morocco. In spite of its importance, monitoring the spatio-temporal evolution of key snow cover properties like the snow water equivalent remains challenging due to the lack of in situ measurements at high elevation. Since 2015, the Sentinel-2 mission provides high spatial resolution images with a 5 day revisit time, which offers new opportunities to characterize snow cover distribution in mountain regions. Here we present a new data assimilation scheme to estimate the state of the snowpack without in situ data. The model was forced using MERRA-2 data and a particle filter was developed to dynamically reduce the biases in temperature and precipitation using Sentinel-2 observations of the snow cover area. The assimilation scheme was implemented using SnowModel, a distributed energy-balance snowpack model and tested in a pilot catchment in the High Atlas. The study period covers 2015-2016 snow season which corresponds to the first operational year of Sentinel-2A, therefore the full revisit capacity was not yet achieved. Yet, we show that the data assimilation led to a better agreement with independent observations of the snow height at an automatic weather station and the snow cover extent from MODIS. The performance of the data assimilation scheme should benefit from the continuous improvements of MERRA-2 reanalysis and the full revisit capacity of Sentinel-2.

An Alternative Machine Learning-Based Methodology for H-SAF H35 Fractional Snow Cover Product

2021 ◽  
Author(s):  
Semih Kuter ◽  
Cansu Aksu ◽  
Kenan Bolat ◽  
Zuhal Akyurek
Keyword(s):  
Machine Learning ◽  
Snow Cover ◽  
Computational Cost ◽  
Multivariate Adaptive Regression Splines ◽  
Pixel Resolution ◽  
European Organization ◽  
Finnish Meteorological Institute ◽  
Fractional Snow Cover ◽  
Turkish State ◽  
Sentinel 2

<p>The fractional snow cover (FSC) product H35 is a daily operational product based on multi-channel analysis of AVHRR onboard to NOAA and MetOp satellites. H35 is supplied by the European Organization for the Exploitation of Meteorological Satellites (EUMETSAT) Satellite Application Facility on Support to Operational Hydrology and Water Management (HSAF). The “traditional” H35 FSC product is generated at pixel resolution by exploiting the brightness intensity, which is the convolution of the snow signal and the fraction of snow within the pixel and the sampling is carried out at 1-km intervals. The product for flat/forested regions is generated by Finnish Meteorological Institute (FMI) and the product for mountainous areas is generated by Turkish State Meteorological Service (TSMS). Both products, thereafter, are merged at FMI. This presentation aims to represent the latest findings of our efforts in developing an “alternative” H35 FSC product for the mountainous part by using two data-driven machine learning methodologies, namely, multivariate adaptive regression splines (MARS) and random forests (RFs). In total, 332 Sentinel 2 images over Alps, Tatra Mountains and Turkey acquired between November 2018 and April 2019 are used in order to generate the necessary reference FSC maps for the training of the MARS and RF models. AVHRR bands 1-5, NDSI and NDVI are used as predictor variables. Binary classified Sentinel 2 snow maps, ERA5 snow depth and MODIS MOD10A1 NDSI data are employed in the validation of the models. The results show that both MARS- and RF-based H35 product are i) in good agreement with reference FSC maps (as indicated by low RMSE and relatively high R values) and ii) able to capture the spatial variability of the snow extend. However, MARS-based H35 is preferred for an operational FSC product generation due to the high computational cost required in RF model.</p>

scholarly journals Effect of digital elevation model resolution on the simulation of the snow cover evolution in the High Atlas

2018 ◽  
Author(s):  
Mohamed Wassim Baba ◽  
Simon Gascoin ◽  
Christophe Kinnard ◽  
Ahmed Marchane ◽  
Lahoucine Hanich
Keyword(s):  
Snow Cover ◽  
Optical Sensors ◽  
Snow Water Equivalent ◽  
Computation Time ◽  
Balance Model ◽  
Snow Melt ◽  
Model Resolution ◽  
Snow Cover Area ◽  
Adequate Model ◽  
High Atlas

The snow melt from the High Atlas represents a crucial water resource for crop irrigation in the semi-arid regions of Morocco. Recent studies have used assimilation of snow cover area (SCA) data from high resolution optical sensors to compute the snow water equivalent (SWE) and snow melt in other mountain regions. These techniques require large model ensembles and therefore a challenge is to determine the adequate model resolution, which yields accurate results with reasonable computation time. Here we study the sensitivity of an energy-balance model to the resolution of the model grid for a pilot catchment in the High Atlas. We used a time series of 8 m resolution SCA maps with an average revisit time of 7.5 days to evaluate the model results. The DEM was generated from Pléiades stereo-images and resampled from 8 m to 30 m, 90 m, 250 m, 500 m and 1000 m. The results indicate that the model performs well from 8 m to 250 m but the agreement with observations drops at 500 m. This is because significant features of the topography were too smoothed out to properly characterize the spatial variability of meteorological forcing, including solar radiation. We conclude that a resolution of 250 m might be sufficient in this area. This result is consistent with the shape of the semivariogram of the topographic slope, suggesting that this semivariogram analysis could be used to transpose our conclusion to other study regions.

scholarly journals Theia Snow collection: high resolution operational snow cover maps from Sentinel-2 and Landsat-8 data

2018 ◽  
Author(s):  
Simon Gascoin ◽  
Manuel Grizonnet ◽  
Marine Bouchet ◽  
Germain Salgues ◽  
Olivier Hagolle
Keyword(s):  
High Resolution ◽  
Snow Cover ◽  
Snow Depth ◽  
Western Europe ◽  
Landsat 8 ◽  
Mountain Regions ◽  
Snow Cover Area ◽  
Level 2 ◽  
Sentinel 2

Abstract. The Theia Snow collection routinely provides high resolution maps of the snow cover area from Sentinel-2 and Landsat-8 observations. The collection covers selected areas worldwide including the main mountain regions in Western Europe (e.g. Alps, Pyrenees) and the High Atlas in Morocco. Each product of the Snow collection contains four classes: snow, no-snow, cloud and no-data. We present the algorithm to generate the snow products and provide an evaluation of their accuracy using in situ snow depth measurements, higher resolution snow maps, and visual control. The results suggest that the snow is accurately detected in the Theia snow collection, and that the snow detection is more accurate than the sen2cor outputs (ESA level 2 product). An issue that should be addressed in a future release is the occurrence of false snow detection in some large clouds. The snow maps are currently produced and freely distributed in average 5 days after the image acquisition as raster and vector files via the Theia portal (http://doi.org/10.24400/329360/F7Q52MNK).

scholarly journals Ground surface temperatures indicate the presence of permafrost in North Africa (Djebel Toubkal, High Atlas, Morocco)

2016 ◽  
Author(s):  
Gonçalo Vieira ◽  
Carla Mora ◽  
Ali Faleh
Keyword(s):  
Snow Cover ◽  
North Africa ◽  
Thermal Regime ◽  
Ground Surface ◽  
Cold Season ◽  
Snow Accumulation ◽  
Landsat 8 ◽  
High Atlas ◽  
Freeze Thaw ◽  
Air Temperatures

Abstract. Relict and present-day periglacial activity have been reported in the literature for the upper reaches of the High Atlas mountains, the highest range in North Africa (Djebel Toubkal – 4,167 m a.s.l.). Lobate features in the Irhzer Ikbi South at 3,800 m a.s.l. have been previously interpreted as an active rock glacier, but no measurements of ground or air temperatures are known to exist for the area. In order to assess on the possible presence of permafrost, analyse data from June 2015 to June 2016 from two air temperature sites at 2,370 and 3,200 m a.s.l., and from four ground surface temperature (GST) sites at 3,200, 3,815, 3,980 and 4,160 m a.s.l. allowing to characterize conditions along an altitudinal gradient along the Oued Ihghyghaye valley to the summit of the Djebel Toubkal. GST were collected at 1-hour intervals and the presence of snow cover at the monitoring sites was validated using Landsat-8 and Sentinel-2 imagery. Two field visits allowed for logger installation and collection and for assessing the geomorphological features in the area. The results show that snow plays a major role on the thermal regime of the shallow ground, inducing important spatial variability. The lowest site at 3,210 m showed a regime characterized by frequent freeze-thaw cycles during the cold season but with a small number of days of snow. When snow sets, the ground remains isothermal at 0 °C and the thermal regime indicates the absence of permafrost. The highest sites at 3,980 and 4,160 m a.s.l. showed very frequent freeze-thaw cycles and a small influence of the snow cover on GST, reflecting the lack of snow accumulation due to the their wind-exposed settings in a ridge and in the summit plateau. The site located at 3,815 m in the Irhzer Ikbi South valley showed a stable thermal regime from December to March with GST varying from −4.5 to −6 °C, under a continuous snow cover. The site's location in a concave setting favours snow accumulation and lower incoming solar radiation due to the effect of a southwards ridge, favouring the maintenance of a thick snow pack. The stable and low GST are interpreted as a strong indicator of the probable presence of permafrost at this site, an interpretation which is supported by the presence of lobate and arcuate forms in the talus deposits. These results are still a first approach and observations through geophysics and boreholes are foreseen. This is the first time that probable permafrost is reported from temperature observations in the mountains of North Africa.

scholarly journals Simulation of snow distribution and melt under cloudy conditions in an alpine watershed

2010 ◽  
Vol 7 (3) ◽  
pp. 3189-3211 ◽  
Author(s):  
H.-Y. Li ◽  
J. Wang
Keyword(s):  
Snow Cover ◽  
Snow Water Equivalent ◽  
Interpolation Method ◽  
Snow Accumulation ◽  
Energy Budgets ◽  
Bias Error ◽  
Snow Cover Area ◽  
Snow Cover Extent ◽  
Snow Distribution ◽  
Alpine Watershed

Abstract. An energy balance method and remote sensing data were used to simulate snow distribution and melt in an alpine watershed in Northwestern China within a complete snow accumulation-melt period. Spatial energy budgets were simulated using the meteorological observations and digital elevation model of the watershed. A linear interpolation method was used to discriminate daily snow cover area under cloudy conditions, using Moderate Resolution Imaging Spectroradiometer data. Hourly snow distribution and melt, snow cover extent, and daily discharge were included in the simulated results. The bias error between field snow water equivalent samplings and simulated results is −2.1 cm, and Root Mean Square Error is 33.9 cm. The Nash and Sutcliffe efficiency statistic (R2) between measured and simulated discharges is 0.673, and the volume difference (Dv) is 3.9%. Using the method introduced in this article, modeling spatial snow distribution and melt runoff will become relatively convenient.

scholarly journals IMPROVING LULC CLASSIFICATION FROM SATELLITE IMAGERY USING DEEP LEARNING – EUROSAT DATASET

2021 ◽  
Vol XLIII-B3-2021 ◽  
pp. 369-376
Author(s):  
H. Yassine ◽  
K. Tout ◽  
M. Jaber
Keyword(s):  
Machine Learning ◽  
Deep Learning ◽  
Satellite Imagery ◽  
Vegetation Index ◽  
Near Infrared ◽  
Spectral Feature ◽  
Classification Performance ◽  
Training Data ◽  
Data Set ◽  
Sentinel 2

Abstract. Machine learning (ML) has proven useful for a very large number of applications in several domains. It has realized a remarkable growth in remote-sensing image analysis over the past few years. Deep Learning (DL) a subset of machine learning were applied in this work to achieve a better classification of Land Use Land Cover (LULC) in satellite imagery using Convolutional Neural Networks (CNNs). EuroSAT benchmarking data set is used as training data set which uses Sentinel-2 satellite images. Sentinel-2 provides images with 13 spectral feature bands, but surprisingly little attention has been paid to these features in deep learning models. The majority of applications focused only on using RGB due to high availability of the RGB models in computer vision. While RGB gives an accuracy of 96.83% using CNN, we are presenting two approaches to improve the classification performance of Sentinel-2 images. In the first approach, features are extracted from 13 spectral feature bands of Sentinel-2 instead of RGB which leads to accuracy of 98.78%. In the second approach features are extracted from 13 spectral bands of Sentinel-2 in addition to calculated indices used in LULC like Blue Ratio (BR), Vegetation index based on Red Edge (VIRE) and Normalized Near Infrared (NNIR), etc. which gives a better accuracy of 99.58%.

scholarly journals New observations indicate the possible presence of permafrost in North Africa (Djebel Toubkal, High Atlas, Morocco)

2017 ◽  
Vol 11 (4) ◽  
pp. 1691-1705 ◽  
Author(s):  
Gonçalo Vieira ◽  
Carla Mora ◽  
Ali Faleh
Keyword(s):  
Snow Cover ◽  
North Africa ◽  
Thermal Regime ◽  
Ground Surface ◽  
Cold Season ◽  
Snow Accumulation ◽  
Landsat 8 ◽  
High Atlas ◽  
Freeze Thaw ◽  
Air Temperatures

Abstract. Relict and present-day periglacial features have been reported in the literature for the upper reaches of the High Atlas mountains, which is the highest range in North Africa (Djebel Toubkal – 4167 m a.s.l.). A lobate feature in the Irhzer Ikhibi south at 3800 m a.s.l. has been previously interpreted as an active rock glacier, but no measurements of ground or air temperatures are known to exist for the area. In order to assess the possible presence of permafrost, we analyse data from June 2015 to June 2016 from two air temperature measurement sites at 2370 and 3210 m a.s.l. and from four ground surface temperature (GST) sites at 3220, 3815, 3980 and 4160 m a.s.l. to characterize conditions along an altitudinal gradient along the Oued Ihghyghaye valley to the summit of the Djebel Toubkal. GSTs were collected at 1 h intervals, and the presence of snow cover at the monitoring sites was validated using Landsat 8 and Sentinel-2 imagery. Two field visits allowed for logger installation and collection and for assessing the geomorphological features in the area. The results show that snow plays a major role on the thermal regime of the shallow ground, inducing important spatial variability. The lowest site at 3220 m had a thermal regime characterized by frequent freeze–thaw cycles during the cold season but with few days of snow. When snow settled, the ground surface remained isothermal at 0 °C , indicating the absence of permafrost. The highest sites at 3980 and 4160 m a.s.l. showed very frequent freeze–thaw cycles and a small influence of the snow cover on GST, reflecting the lack of snow accumulation due to the wind-exposed settings on a ridge and on the summit plateau. The site located at 3815 m in the Irhzer Ikhibi south valley had a cold, stable thermal regime with GST varying from −4.5 to −6 °C from December to March, under a continuous snow cover. The site's location in a concave setting favours wind-driven snow accumulation and lower incoming solar radiation due to the shading effect of a ridge, inducing the conservation of a thick snow pack. The stable and low GSTs are interpreted as a strong indicator of the probable presence of permafrost at this site, which is an interpretation supported by the presence of lobate and arcuate features in the talus deposits. We present first results and further observations using geophysics, and borehole measurements are foreseen. This is the first time that probable permafrost has been reported from temperature observations in the mountains of North Africa.

scholarly journals Linear or Nonlinear Covariance of Seasonal Snowmelt and Snow Cover in Western Himalayas

1992 ◽  
Vol 23 (3) ◽  
pp. 183-192 ◽  
Author(s):  
B. Dey ◽  
V. K. Sharma ◽  
A. Rango
Keyword(s):  
Linear Regression ◽  
Snow Cover ◽  
Regression Models ◽  
Early Spring ◽  
Senior Author ◽  
Snow Accumulation ◽  
Western Himalayas ◽  
Linear Regression Models ◽  
Snow Cover Area ◽  
Seasonal Flow

Log-linear, exponential and fractional relations for estimating seasonal snowmelt from early-spring snow accumulation in the Indus and Kabul river basins in the western Himalayas are developed with a view to improve the prediction given by bivariate linear regression models earlier developed by the senior author in collaboration with others. This study shows that although the transformed data may improve the above prediction, they fail to satisfy the condition of nonlinearity; a property that must be borne in mind before recommending any nonlinear regression model. Any further improvement in the prediction of seasonal flow volume from basin snow cover area, therefore, has to come from within the domain of linear regression models only or from improvements in the original input data.

Sign in / Sign up

Export Citation Format

Share Document