Glacier Facies Mapping Using a Machine-Learning Algorithm: The Parlung Zangbo Basin Case Study

Abstract

Glaciers in the Tibetan Plateau are an important indicator of climate change. Automatic glacier facies mapping utilizing remote sensing data is challenging due to the spectral similarity of supraglacial debris and the adjacent bedrock. Most of the available glacier datasets do not provide the boundary of clean ice and debris-covered glacier facies, while debris-covered glacier facies play a key role in mass balance research. The aim of this study was to develop an automatic algorithm to distinguish ice cover types based on multi-temporal satellite data, and the algorithm was implemented in a subregion of the Parlung Zangbo basin in the southeastern Tibetan Plateau. The classification method was built upon an automated machine learning approach: Random Forest in combination with the analysis of topographic and textural features based on Landsat-8 imagery and multiple digital elevation model (DEM) data. Very high spatial resolution Gao Fen-1 (GF-1) Panchromatic and Multi-Spectral (PMS) imagery was used to select training samples and validate the classification results. In this study, all of the land cover types were classified with overall good performance using the proposed method. The results indicated that fully debris-covered glaciers accounted for approximately 20.7% of the total glacier area in this region and were mainly distributed at elevations between 4600 m and 4800 m above sea level (a.s.l.). Additionally, an analysis of the results clearly revealed that the proportion of small size glaciers (<1 km 2 ) were 88.3% distributed at lower elevations compared to larger size glaciers (≥1 km 2 ). In addition, the majority of glaciers (both in terms of glacier number and area) were characterized by a mean slope ranging between 20 • and 30 • , and 42.1% of glaciers had a northeast and north orientation in the Parlung Zangbo basin.In the past few decades, much work has been accomplished to map the extent of clean glacial ice and to quantify changes over time using satellite image data [6]. Methods applied range from visual interpretation [7] to segmentation of band ratio or spectral indices (e.g., the Normalized Difference Snow Index) images [8] and different unsupervised (e.g., the Iterative Self Organizing Data Analysis Techniques Algorithm, ISODATA) [9] and supervised (e.g., the Maximum Likelihood algorithm) classification [10] and decision tree methods [5,11]. For extracting debris-covered glaciers using multispectral imagery, fully manual onscreen digitizing is widely considered to be a common classification approach [12]. However, the accuracy of results using manual approaches depends greatly on the researcher's experience. Due to the laborious work of manual delineation, many researchers have further proposed semi-automated methods to extract the debris-covered glacial surface [13,14]. The use of Unmanned Aerial Vehicles (UAVs) and terrestrial remote sensing techniques offers new ways to monitor the debris-covered glaciers on a detailed spatial scale [15,16].Nevertheless, the spatial heterogeneity of the g...

Glacier Mapping Based on Random Forest Algorithm: A Case Study over the Eastern Pamir

“…The accuracy of Random Forest is similar to (or even better than) other studies [33,42,43]. The glacier movement provided important information for understanding glacial changes.…”

“…Currently, with the requirement of glacier inventory establishment and more in-depth research in glaciers, several prominent methods of identifying and classifying glaciers to extract clean glacier boundaries, mainly including artificial visual interpretation [9], the band ratio threshold method [10,11], supervised classification [12], and unsupervised classification [13,14], have been extensively developed. Due to the fact that the band ratio threshold method is the most methods and satellite remote sensing data, different types of glaciers can be quickly extracted [27,42,43]. However, none of the above studies considered the characteristics of glacier movement.…”

Explorative Study on Mapping Surface Facies of Selected Glaciers from Chandra Basin, Himalaya Using WorldView-2 Data

“…Therefore, to solve this problem and to check the capacity for debris characterization in such a scenario, this study maps ice-mixed debris (IMD) and debris. IMD is reported in several glacier classification schemes [3,33,109,118,119] and is consistent with its separability from debris due to the mixing of snow (refer to Sections 3.2.1 and 3.2.2). However, as the margin of differentiation between IMD and debris is low, their characterization is bound to consist of misclassifications.…”

GlacierNet: A Deep-Learning Approach for Debris-Covered Glacier Mapping

“…Recently, machine learning has been used for glacier mapping effectively [17], [18], but it differs from the deep-learning approach presented here. Deep-learning approaches represent a subset of the family of machine-learning approaches and algorithms that can be used.…”