Snow cover estimation from MODIS and Sentinel-1 SAR data using machine learning algorithms in the western part of the Tianshan Mountains

Liu, Yang; Chen, Xi; Hao, Jinkai; Li, Lanhai

doi:10.1007/s11629-019-5723-1

Cited by 22 publications

(7 citation statements)

References 67 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Major rivers recharged by glacier/snow melt water originating from the TS (e.g., the Ili River, Syr Darya River, Amu Darya River, Tarim River, and Chu River) feed the lowland areas of Kazakhstan, Kyrgyzstan, Uzbekistan, and China's north-western Xinjiang Uyghur Autonomous Region, which together form one of the largest irrigated areas in the world [26,28,29]. Spatiotemporal variations of the snow cover in the TS exert a significant impact on the changes of water source for its surrounding arid regions and the hydrological and biological processes [30][31][32]. Therefore, the detection and exhaustive analysis of spatiotemporal variation of the SLA over the entire TS are quite essential for the protection and utilization of local water resources.…”

Section: Introductionmentioning

confidence: 99%

Spatiotemporal Dynamics of Snowline Altitude and Their Responses to Climate Change in the Tienshan Mountains, Central Asia, during 2001–2019

Deng

Tang

et al. 2021

Sustainability

View full text Add to dashboard Cite

Snow cover is an important water resource in arid and semi-arid regions of Central Asia, and is related to agricultural and livestock production, ecosystems, and socio-economic development. The snowline altitude (SLA) is a significant indicator for monitoring the changes in snow cover in mountainous regions under the changing climate. Here, we investigate the spatiotemporal variation of SLA in the Tienshan Mountains (TS) during 2001–2019 using Moderate Resolution Imaging Spectroradiometer (MODIS) snow cover products on a grid-by-grid basis. The potential influence of topographic factors (slope gradient and aspect) on SLA and the correlation between SLA, temperature, precipitation, and solar radiation are also investigated. The results are as follows: (1) The annual cycle of SLA shows strong seasonal fluctuations (from about 2000 m in late December to 4100 m in early August). The SLA over the TS exhibits a large spatiotemporal heterogeneity. (2) SLA increases with a steeper slope gradient. The SLA of the northerly aspect is generally less than the southerly. (3) The SLA over the TS generally shows an increasing trend in the recent years (2001–2019). The change trend of SLA varies in different months. Except for a slight decrease in June, the SLA increased in almost all months, especially at the start of the melt season (March and April) and the end of melting season (July and August). (4) The SLA increases with increased temperature/radiation in the TS, and decreases with increased precipitation. Solar radiation is the dominant climatic factor affecting the changes of SLA in the TS. Compared with precipitation, temperature is more correlated to SLA dynamics.

show abstract

Section: Introductionmentioning

confidence: 99%

Spatiotemporal Dynamics of Snowline Altitude and Their Responses to Climate Change in the Tienshan Mountains, Central Asia, during 2001–2019

Deng

Tang

et al. 2021

Sustainability

View full text Add to dashboard Cite

show abstract

“…The original NDSI data were reclassified as snow, nonsnow, and data-gaps classes (Chen et al, 2020;Huang et al, 2018. The pixels with an NDSI value of 40-100 in the NDSI_Snow_Cover band were reclassified as snow (Riggs et al, 2017).…”

Section: Daily Modis Snow Cover Productsmentioning

confidence: 99%

HMRFS–TP: long-term daily gap-free snow cover products over the Tibetan Plateau from 2002 to 2021 based on hidden Markov random field model

Huang¹,

Xu²,

Xu³

et al. 2022

Earth Syst. Sci. Data

View full text Add to dashboard Cite

Abstract. Snow cover plays an essential role in climate change and the hydrological cycle of the Tibetan Plateau. The widely used Moderate Resolution Imaging Spectroradiometer (MODIS) snow products have two major issues: massive data gaps due to frequent clouds and relatively low estimate accuracy of snow cover due to complex terrain in this region. Here we generate long-term daily gap-free snow cover products over the Tibetan Plateau at 500 m resolution by applying a hidden Markov random field (HMRF) technique to the original MODIS snow products over the past two decades. The data gaps of the original MODIS snow products were fully filled by optimally integrating spectral, spatiotemporal, and environmental information within HMRF framework. The snow cover estimate accuracy was greatly increased by incorporating the spatiotemporal variations of solar radiation due to surface topography and sun elevation angle as the environmental contextual information in HMRF-based snow cover estimation. We evaluated our snow products, and the accuracy is 98.29 % in comparison with in situ observations, and 91.36 % in comparison with high-resolution snow maps derived from Landsat images. Our evaluation also suggests that the incorporation of spatiotemporal solar radiation as the environmental contextual information in HMRF modeling, instead of the simple use of surface elevation as the environmental contextual information, results in the accuracy of the snow products increases by 2.71 % and the omission error decreases by 3.59 %. The accuracy of our snow products is especially improved during snow transitional period, and over complex terrains with high elevation and sunny slopes. The new products can provide long-term and spatiotemporally continuous information of snow cover distribution, which is critical for understanding the processes of snow accumulation and melting, analyzing its impact on climate change, and facilitating water resource management in Tibetan Plateau. This dataset can be freely accessed from the National Tibetan Plateau Data Center at https://doi.org/10.11888/Cryos.tpdc.272204 (Huang and Xu, 2022).

show abstract

“…This study focused on the middle Tianshan Mountains in China, extending 1700 km from east to west in the territory of China (Figure 1a). The study area comprises a series of oases, valleys, pre-mountain plains, mountain basins, mountain ranges and other geomorphological units (Liu, Xi et al, 2020). The meteorological conditions in the study area varied spatially.…”

Section: Study Areamentioning

confidence: 99%

“…The continental snow climate is characterized by low temperatures, low amount of snowfall and low-snow density (Mock et al, 2017). Most snow-related studies in the Tianshan Mountains focused on the snow phenology, snow depth and distribution of snow cover (Li et al, 2019;Liu, Xi, et al, 2020;Yang et al, 2019;Zhang et al, 2019). Few studies analysed or estimated snow density in the Tianshan Mountains in different snow periods at a regional scale.…”

Section: Introductionmentioning

confidence: 99%

Spatial variability of snow density and its estimation in different periods of snow season in the middle Tianshan Mountains, China

Feng

Zhu

Huang

et al. 2022

Hydrological Processes

View full text Add to dashboard Cite

Snow density is an essential property of snowpack. To obtain the spatial variability of snow density and estimate it in different periods of the snow season remain challenging, particularly in the mountainous area. This study analysed the spatial variability of snow density with in‐situ measurements in three different periods (i.e., accumulation, stable and melt periods) of the snow seasons of 2017/2018 and 2018/2019 in the middle Tianshan Mountains, China. The simulation performances of the multiple linear regression (MLR) model and three machine learning (random forest [RF], extreme gradient boosting [XGB] and light gradient boosting machine [LGBM]) models were evaluated. Results showed that snow density in the melt period (0.27 g cm−3) was generally greater than that in the stable (0.20 g cm−3) and accumulation periods (0.18 g cm−3), and the spatial variability of snow density in the melt period was slightly smaller compared to that in other two periods. The snow density in the mountainous areas was generally higher than that in the plain or oasis areas. It increased significantly (p < 0.05) with elevation during the accumulation and stable periods. In addition to elevation, latitude and ground surface temperature also had critically impacted the spatial variability of snow density in the study area. In the current study, the machine learning models, especially RF, performed better than MLR for simulating snow density in the three periods. Based on the key environmental variables identified by the machine learning model and correlation analysis, this study also provides practical MLR equations to estimate the spatial variance of snow density during different snow periods in the middle Tianshan Mountains. This method can be used for regional snow mass and snow water equivalent prediction, leading to a better understanding of local snow resources.

show abstract

Snow cover estimation from MODIS and Sentinel-1 SAR data using machine learning algorithms in the western part of the Tianshan Mountains

Cited by 22 publications

References 67 publications

Spatiotemporal Dynamics of Snowline Altitude and Their Responses to Climate Change in the Tienshan Mountains, Central Asia, during 2001–2019

Spatiotemporal Dynamics of Snowline Altitude and Their Responses to Climate Change in the Tienshan Mountains, Central Asia, during 2001–2019

HMRFS–TP: long-term daily gap-free snow cover products over the Tibetan Plateau from 2002 to 2021 based on hidden Markov random field model

Spatial variability of snow density and its estimation in different periods of snow season in the middle Tianshan Mountains, China

Contact Info

Product

Resources

About