Large-Scale Debris Cover Glacier Mapping Using Multisource Object-Based Image Analysis Approach

Abstract

Large-scale debris cover glacier mapping can be efficiently conducted from high spatial resolution (HSR) remote sensing imagery using object-based image analysis (OBIA), which works on a group of pixels. This paper presents the spectral and spatial capabilities of OBIA to classify multiple glacier cover classes using a multisource approach by integrating multispectral, thermal, and slope information into one workflow. The novel contributions of this study are effective mapping of small yet important geomorphological features, classification of shadow regions without manual corrections, discrimination of snow/ice, ice-mixed debris, and supraglacial debris without using shortwave infrared bands, and an adaptation of an area-weighted error matrix specifically built for assessing OBIA’s accuracy. The large-scale glacier cover map is produced with a high overall accuracy of ≈94% (area-weighted error matrix). The proposed OBIA approach also proved to be effective in mapping minor geomorphological features such as small glacial lakes, exposed ice faces, debris cones, rills, and crevasses with individual class accuracies in the range of 96.9–100%. We confirm the portability of our proposed approach by comparing the results with reference glacier inventories and applying it to different sensor data and study areas.

Multispectral Characteristics of Glacier Surface Facies (Chandra-Bhaga Basin, Himalaya, and Ny-Ålesund, Svalbard) through Investigations of Pixel and Object-Based Mapping Using Variable Processing Routines

“…In such cases, the current study may prove useful as the lack of spectral bands may be overcome by utilizing VHR data and spatial-spectral GEOBIA rule sets. In a recent GEOBIA based approach for mapping debris cover in addition to other facies, Mitkari et al [22] utilized thermal infrared (TIR) band (Landsat TM) and a NIR2/Yellow index (Table 5) from WV-2 to map IMD. In the current study, we have also utilized the same index for mapping IMD for the CYRN2, VNIR, and VNIR_SWIR rule set 1 and 3 subsets.…”

“…pixel value of NIR1/2 for rule sets 2 and 3, the R_B ratio for BGRN1 and the mean reflectance of NIR2 for VNIR and VNIR_SWIR in rule sets 1 and 3. Mitkari et al [22] utilized brightness temperature and slope via GEOBIA to separate supraglacial and periglacial debris. Often, boundaries of debris-covered glaciers are difficult to ascertain without the use of ancillary data due to confounding properties with the surrounding geology.…”

“…Crevasses are elongated deep cracks or fractures in the ice [22] resulting from the type of flow of the glacier [105]. Owing to this shape, crevasses may be easily detected in GEOBIA via the appropriate segmentation parameter.…”

“…GEOBIA also provides an efficient structure for adding ancillary information to extract maximum features from the primary data. As demonstrated by Mitkari et al [22], debris cover is efficiently mapped through GEOBIA using a multiscale segmentation approach using ancillary data for identifying glacial lakes, minor features such as debris cones, rills, and other features such as crevasses, exposed ice, snow, ice mixed debris, and supraglacial debris. GEOBIA permits arithmetic operations on its segmented objects; this enables application of band ratios [23] and customized spectral indices [3].…”

Image Classification Learning Method Incorporating Zero-Sample Learning and Small-Sample Learning

“…is phenomenon is known as over-simulation because if the depth model is very complex, it is easy to consider the noise in a small-sample training data set as a sign of the whole sample and therefore the training model on the test data set performs poorly [2].…”