Derivation of Supraglacial Debris Cover by Machine Learning Algorithms on the Gee Platform: A Case Study of Glaciers in the Hunza Valley

Xie, Fuming; Liu, Shiyin; Gao, Yun; Zhu, Yanzi; Wu, Kunpeng; Qi, Miaomiao; Duan, Shimei; Tahir, Amjed

doi:10.5194/isprs-annals-v-3-2020-417-2020

Cited by 6 publications

(6 citation statements)

References 49 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As noted, machine/deep learning algorithms have been widely utilized to map debriscovered glaciers [45][46][47][48][49], including artificial neural networks (ANN), the support vector machine (SVM), the random forest (RF) classifier [34], and convolutional neural networks (CNN). Nevertheless, applying these machine learning techniques is limited by cloud cover, rough terrain, mountain shadows, and freshly frozen lakes [49].…”

Section: Glacier Delineationsmentioning

confidence: 99%

“…Object-based image analysis was applied in surface segmentation, e.g., glacier mapping [37,292], definition of debris-covered glaciers [292,293], and rock glacier detection [141]. Machine/deep-learning classifiers continue to develop and find application in identifying cryospheric factors [35], e.g., glacier delineations [34,[294][295][296][297], debris-covered glacier mapping [45][46][47][48]298], snow cover and depth [35], rock glacier distributions [141], etc. However, quantities of visual interpretation and manual work remain indispensable in pre-processing and post-processing, especially for outlining surge-type glaciers [16].…”

Section: Summary Of Cryosphere Studies From Spacementioning

confidence: 99%

See 1 more Smart Citation

Remote Sensing and Modeling of the Cryosphere in High Mountain Asia: A Multidisciplinary Review

Ye,

Wang,

Liu

et al. 2024

Remote Sensing

View full text Add to dashboard Cite

Over the past decades, the cryosphere has changed significantly in High Mountain Asia (HMA), leading to multiple natural hazards such as rock–ice avalanches, glacier collapse, debris flows, landslides, and glacial lake outburst floods (GLOFs). Monitoring cryosphere change and evaluating its hydrological effects are essential for studying climate change, the hydrological cycle, water resource management, and natural disaster mitigation and prevention. However, knowledge gaps, data uncertainties, and other substantial challenges limit comprehensive research in climate–cryosphere–hydrology–hazard systems. To address this, we provide an up-to-date, comprehensive, multidisciplinary review of remote sensing techniques in cryosphere studies, demonstrating primary methodologies for delineating glaciers and measuring geodetic glacier mass balance change, glacier thickness, glacier motion or ice velocity, snow extent and water equivalent, frozen ground or frozen soil, lake ice, and glacier-related hazards. The principal results and data achievements are summarized, including URL links for available products and related data platforms. We then describe the main challenges for cryosphere monitoring using satellite-based datasets. Among these challenges, the most significant limitations in accurate data inversion from remotely sensed data are attributed to the high uncertainties and inconsistent estimations due to rough terrain, the various techniques employed, data variability across the same regions (e.g., glacier mass balance change, snow depth retrieval, and the active layer thickness of frozen ground), and poor-quality optical images due to cloudy weather. The paucity of ground observations and validations with few long-term, continuous datasets also limits the utilization of satellite-based cryosphere studies and large-scale hydrological models. Lastly, we address potential breakthroughs in future studies, i.e., (1) outlining debris-covered glacier margins explicitly involving glacier areas in rough mountain shadows, (2) developing highly accurate snow depth retrieval methods by establishing a microwave emission model of snowpack in mountainous regions, (3) advancing techniques for subsurface complex freeze–thaw process observations from space, (4) filling knowledge gaps on scattering mechanisms varying with surface features (e.g., lake ice thickness and varying snow features on lake ice), and (5) improving and cross-verifying the data retrieval accuracy by combining different remote sensing techniques and physical models using machine learning methods and assimilation of multiple high-temporal-resolution datasets from multiple platforms. This comprehensive, multidisciplinary review highlights cryospheric studies incorporating spaceborne observations and hydrological models from diversified techniques/methodologies (e.g., multi-spectral optical data with thermal bands, SAR, InSAR, passive microwave, and altimetry), providing a valuable reference for what scientists have achieved in cryosphere change research and its hydrological effects on the Third Pole.

show abstract

Section: Glacier Delineationsmentioning

confidence: 99%

Section: Summary Of Cryosphere Studies From Spacementioning

confidence: 99%

Remote Sensing and Modeling of the Cryosphere in High Mountain Asia: A Multidisciplinary Review

Ye,

Wang,

Liu

et al. 2024

Remote Sensing

View full text Add to dashboard Cite

show abstract

“…However, variations in the debris cover across the whole Karakoram region remain unknown. Mapping glaciers with debris cover is still challenging (Paul et al, 2004;Pfeffer et al, 2014;Farinotti et al, 2020), with various data and approaches having been proposed to address this issue, including using SAR (synthetic aperture radar) coherence maps, optical bands, thermal infrared features, terrain parameters, machine learning, and other methods (Bhambri et al, 2011;Mölg et al, 2018;Alifu et al, 2020;Xie et al, 2020a).…”

Section: Introductionmentioning

confidence: 99%

Interdecadal glacier inventories in the Karakoram since the 1990s

Xie

Liu

Gao

et al. 2023

Earth Syst. Sci. Data

Self Cite

View full text Add to dashboard Cite

Abstract. Multi-temporal glacier inventories provide key information about the glaciers, their characteristics, and changes and are inevitable for glacier modelling and investigating geodetic mass changes. However, to date, no consistent multi-temporal glacier inventory for the whole of the Karakoram exists, negatively affecting the monitoring of spatio-temporal variations in glaciers' geometric parameters and their related applications. We used a semi-automatic method combining automatic segmentation and manual correction and produced a multi-temporal Karakoram glacier inventory (KGI) compiled from Landsat TM/ETM+/OLI (Thematic Mapper, Enhanced Thematic Mapper Plus, and Operational Land Imager) images for the 1990s, 2000s, 2010s, and 2020s. Our assessments using independent multiple digitisation of 37 glaciers show that the KGI is sufficiently accurate, with an overall uncertainty of ±3.68 %. We also performed uncertainty evaluation for the contiguous glacier polygons using a buffer of half a pixel, which resulted in an average mapping uncertainty of ±5.21 %. We calculated more than 20 attributes for each glacier, including coordinates, area, supraglacial debris area, date information, and topographic parameters derived from the ASTER GDEM (Advanced Spaceborne Thermal Emission and Reflection Radiometer global digital elevation model). According to KGI-2020s, approximately 10 500 alpine glaciers (>0.01 km2 each) cover an area of 22 510±828 km2 of which 10.18±0.38 % (2290±84 km2) is covered by supraglacial debris. Over the past 3 decades, the glaciers experienced a loss of clean ice and/or snow area but a gain in supraglacial debris. Supraglacial debris cover has increased by 17.63±1.44 % (343.30±27.95 km2), while non-debris-covered glaciers decreased by 1.56±0.24 % (319.85±49.92 km2). The total glacier area was relatively stable and showed only a slight insignificant increase of 23.45±28.85 km2 (0.10±0.13 %). The glacier area has declined by 3.27±0.24 % in the eastern Karakoram, while the glacier area slightly increased in central (0.65±0.10 %) and western Karakoram (1.26±0.11 %). Supraglacial debris has increased over the whole of Karakoram, especially in areas above 4200 m a.s.l. (above sea level), showing an upward shift. The glacier area changes were characterised by strong spatial heterogeneity, influenced by surging and advancing glaciers. However, due to global warming, the glaciers are on average retreating. This is in particular true for small and debris-free glaciers. The multi-temporal KGI data are available at the National Cryosphere Desert Data Center of China: https://doi.org/10.12072/ncdc.glacier.db2386.2022 (F. Xie et al., 2022).

show abstract

“…However, variations in the debris cover across the whole Karakoram region remains unknown. Mapping glaciers with debris cover is still challenging (Paul et al, 2004;Pfeffer et al, 2014;Farinotti et al, 2020), with various data and approaches having been proposed 120 to address this issue, including using SAR (Synthetic Aperture Radar) coherence maps, optical bands, thermal infrared features, terrain parameters, machine learning and other methods (Bhambri et al, 2011;Mölg et al, 2018;Alifu et al, 2020;Xie et al, 2020a).…”

Section: Introductionmentioning

confidence: 99%

Interdecadal glacier inventories in the Karakoram since the 1990s

Xie

Liu

Gao

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

Abstract. Multi-temporal glacier inventories provide key information about the glaciers, their characteristics and changes and are inevitable for glacier modelling and investigating geodetic mass changes. However, to date, no consistent multi-tempo glacier inventory for the whole of the Karakoram exists, negatively affecting the monitoring of spatiotemporal variations of glaciers’ geometric parameters and their related applications. We used a semi-automatic method combining automatic segmentation and manual correction and produced multi-temporal Karakoram glacier inventories (KGI) compiled from Landsat TM/ETM+/OLI images for the 1990s, 2000s, 2010s, and 2020s. Our assessments using independent multiple digitization of 37 glaciers show that the KGI is sufficiently accurate, with an overall uncertainty of ±3.68 %. We also performed uncertainty evaluation for the contiguous glacier polygons using a buffer of half a pixel, which resulted in an average mapping uncertainty of ±3.68 %. We calculated more than 20 attributes for each glacier, including coordinates, area, supraglacial debris area, date information, and topographic parameters derived from the ASTER GDEM. According to the KGI-2020, approximately 10500 alpine glaciers (> 0.01 km2 each) cover an area of 22510 ± 828 km2 of which 10.18 ± 0.38 % (2290 ± 84 km2) are covered by supraglacial debris. Over the past three decades, the glaciers experienced a loss of clean ice/snow area but a gain in supraglacial debris. Supraglacial debris cover has increased by 17.63 ± 1.44 % (343.30 ± 27.95 km2) while non-debris-covered glaciers decreased by 1.56 ± 0.0.24 % (319.85 ± 49.92 km2). The total glacier area was relatively stable and showed only a slight insignificant increase of 23.45 ± 28.85 km2 (0.10 ± 0.13 %). The glacier area has declined by 3.27 ± 0.24 % in the eastern Karakoram while the glacier area slightly increased in central (0.65 ± 0.10 %) and western Karakoram (1.26 ± 0.11 %). Supraglacial debris has increased over whole Karakoram, especially in areas above 4200 m a.s.l., showing an upward shift. The glacier area changes were characterized by strong spatial heterogeneity, influenced by surging and advancing glaciers. However, due to global warming, the glaciers are on average retreating. This is in particular true for small and debris-free glaciers. The multi-temporal KGI data are available at the National Cryosphere Desert Data Center of China: https://doi.org/10.12072/ncdc.glacier.db2386.2022 (Xie et al., 2022a).

show abstract

Derivation of Supraglacial Debris Cover by Machine Learning Algorithms on the Gee Platform: A Case Study of Glaciers in the Hunza Valley

Cited by 6 publications

References 49 publications

Remote Sensing and Modeling of the Cryosphere in High Mountain Asia: A Multidisciplinary Review

Remote Sensing and Modeling of the Cryosphere in High Mountain Asia: A Multidisciplinary Review

Interdecadal glacier inventories in the Karakoram since the 1990s

Interdecadal glacier inventories in the Karakoram since the 1990s

Contact Info

Product

Resources

About