Evaluation of effective spectral features for glacial lake mapping by using Landsat-8 OLI imagery

Zhang, Meimei; Zhao, Hang; Chen, Fang; Zeng, Jiangyuan

doi:10.1007/s11629-020-6255-4

Cited by 10 publications

(4 citation statements)

References 62 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Visual interpretation method can be used to accurately delineate glacier lake boundaries, but these methods are time-consuming, laborious, costly, and the corresponding subjective factors are relatively large; thus, these methods are not suitable for mapping glacial lakes or conducting dynamic monitoring research in remote or large-scale regions. Thus, many automatic extraction methods have emerged for delineating water bodies, such as classification methods [22,23], threshold segmentation methods [24][25][26][27][28], machine learning methods [29][30][31][32], and other improved methods [33,34] (e.g., methods in which classification tree-based image segmentation and object-oriented spatial metrics are implemented to improve existing water body indices). However, it is still difficult to distinguish glacial lakes or their boundaries in some images due to the small sizes of lakes, lakes being shadowed by steep terrain, or lakes being ice-covered or snow-covered; these factors can change dramatically over a year or even over several months [32].…”

Section: Introductionmentioning

confidence: 99%

Inventory and Spatiotemporal Patterns of Glacial Lakes in the HKH-TMHA Region from 1990 to 2020

Wang

Gao

et al. 2022

Remote Sensing

View full text Add to dashboard Cite

The Himalayan, Karakoram, and Hindu Kush (HKH-TMHA) are the three main mountain ranges in the high-mountain Asia region, covering the China–Pakistan Economic Corridor (CPEC). In this study, we identified glacial lakes in the HKH-TMHA region based on multitemporal Landsat images taken from 1990 to 2020. We analyzed the spatial distribution and evolution of glacial lakes in the HKH-TMHA region from the perspective of their elevation, size, and terrain aspect; then, we described their temporal changes. The results showed that approximately 84.56% of the glacial lakes (84.1% of the total lake area) were located at elevations between 4000 m and 5500 m, and glacial lakes with areas ranging from 0.01–0.5 km2 accounted for approximately 95.21% of the number and 63.01% of the total area of glacial lakes. The number (38.64%) and area (58.83%) of south-facing glacial lakes were largest in HKH-TMHA and expanded significantly over time. There were 5835 (664.84 ± 89.72 km2) glacial lakes in 1990; from 1990 to 2020, the number of glacial lakes in the HKH-TMHA region increased by 5974 (408.93 km2) in total; and the annual average increase in the area of glacial lakes reached 13.63 km2 (11.15%). In 2020, the total number of glacial lake reached to 9673 (899.66 ± 120.63 km2). In addition, most glacial lakes were located in the Eastern Himalayan, China, and the Indus Basin. Based on the precipitation and temperature analyses performed in our study area, we found inconsistent climate characteristics and changes in the three mountain ranges. In general, the daily precipitation (temperature) increased by 1.0766 mm (1.0311 °C), 0.8544 mm (0.8346 °C), and 0.8245 mm (−0.1042 °C) on the yearly, summer, and winter scales, respectively. Glacial melting and climate change are common contributors to glacial lake expansion. The investigation of glacial lakes in this region can provide basic supporting data for research on glacial lake-related disasters, land cover, and climate change in the high-mountain Asia region.

show abstract

Section: Introductionmentioning

confidence: 99%

Inventory and Spatiotemporal Patterns of Glacial Lakes in the HKH-TMHA Region from 1990 to 2020

Wang

Gao

et al. 2022

Remote Sensing

View full text Add to dashboard Cite

show abstract

“…El uso del índice Kappa en este estudio tiene el fin de enriquecer la evaluación de exactitud de las clasificaciones. Aunque este índice sea discutido (Pontius y Millones, 2011), varias investigaciones actuales emplean el índice Kappa como referencia para la validación del mapeo de áreas con cobertura glaciar (e.g., López-Moreno et al, 2020;Sood et al, 2021;Zhang et al, 2020).…”

Section: Evaluación De La Exactitud De La Clasificaciónunclassified

Evaluación del retroceso glaciar de la Sierra Nevada del Cocuy, Colombia a partir de la clasificación de imágenes multisensor

Cardenas

Gómez

et al. 2022

Boletín de Geología

View full text Add to dashboard Cite

Los glaciares andinos representan una de las fuentes principales del recurso hídrico en Suramérica y durante las últimas décadas se han reducido significativamente como producto del cambio climático y la variabilidad climática. En los Andes colombianos, el pico nevado más extenso corresponde a la Sierra Nevada del Cocuy (SRC), un cordón montañoso localizado al noreste de la Cordillera Oriental con presencia de nieves perpetuas en alturas que oscilan aproximadamente entre los 4800 y los 5345 metros sobre el nivel del mar (msnm). A partir de imágenes satelitales de Landsat-4 (1987), Landsat-5 (1991, 1997, 2009), Landsat-7 (2000, 2003), Landsat-8 (2014, 2016, 2017), y Sentinel-2 (2019, 2021) se realizó una clasificación orientada a píxel usando el software PCI Geomatics, en la cual se definieron 4 tipos de cobertura: área glaciar, suelo-roca, vegetación y agua. Para la validación de exactitud (accuracy) fueron utilizadas como datos de referencia, imágenes satelitales de alta resolución espacial (Google Earth ~1,0 m y Planet’s high-resolution, analysis-ready mosaics of the world’s tropics ~4,7 m) y puntos de control de campo. Los valores de exactitud global (todas las coberturas) oscilaron entre 86-99%, con una exactitud para la cobertura de área glaciar entre 97-100%. La disminución de dicha área es de 1099,59 ha en un lapso de 34 años (1987-2021). Este análisis reveló que el área glaciar disminuyó aproximadamente en un 37,92% con respecto a la primera escena (1987). Según dicha tendencia, el glaciar de la SRC se extinguiría para el año 2048. La tasa de retroceso glaciar está influenciada principalmente por factores relacionados con el calentamiento global como lo son el aumento de la temperatura media anual y la disminución en las tasas de precipitación, y factores de variabilidad climática como el fenómeno de El Niño.

show abstract

“…Feature F 3 refers to the water index. Due to the simplicity of the expression and relatively stable thresholds used for the classification of lakes [13,37], NDWI was selected in this study, as follows:…”

Section: Water Attention Modulementioning

confidence: 99%

GAN-GL: Generative Adversarial Networks for Glacial Lake Mapping

2021

Self Cite

View full text Add to dashboard Cite

Remote sensing is a powerful tool that provides flexibility and scalability for monitoring and investigating glacial lakes in High Mountain Asia (HMA). However, existing methods for mapping glacial lakes are designed based on a combination of several spectral features and ancillary data (such as the digital elevation model, DEM) to highlight the lake extent and suppress background information. These methods, however, suffer from either the inevitable requirement of post-processing work or the high costs of additional data acquisition. Signifying a key advancement in the deep learning models, a generative adversarial network (GAN) can capture multi-level features and learn the mapping rules in source and target domains using a minimax game between a generator and discriminator. This provides a new and feasible way to conduct large-scale glacial lake mapping. In this work, a complete glacial lake dataset was first created, containing approximately 4600 patches of Landsat-8 OLI images edited in three ways—random cropping, density cropping, and uniform cropping. Then, a GAN model for glacial lake mapping (GAN-GL) was constructed. The GAN-GL consists of two parts—a generator that incorporates a water attention module and an image segmentation module to produce the glacial lake masks, and a discriminator which employs the ResNet-152 backbone to ascertain whether a given pixel belonged to a glacial lake. The model was evaluated using the created glacial lake dataset, delivering a good performance, with an F1 score of 92.17% and IoU of 86.34%. Moreover, compared to the mapping results derived from the global–local iterative segmentation algorithm and random forest for the entire Eastern Himalayas, our proposed model was superior regarding the segmentation of glacial lakes under complex and diverse environmental conditions, in terms of accuracy (precision = 93.19%) and segmentation efficiency. Our model was also very good at detecting small glacial lakes without assistance from ancillary data or human intervention.

show abstract

Evaluation of effective spectral features for glacial lake mapping by using Landsat-8 OLI imagery

Cited by 10 publications

References 62 publications

Inventory and Spatiotemporal Patterns of Glacial Lakes in the HKH-TMHA Region from 1990 to 2020

Inventory and Spatiotemporal Patterns of Glacial Lakes in the HKH-TMHA Region from 1990 to 2020

Evaluación del retroceso glaciar de la Sierra Nevada del Cocuy, Colombia a partir de la clasificación de imágenes multisensor

GAN-GL: Generative Adversarial Networks for Glacial Lake Mapping

Contact Info

Product

Resources

About