Detecting rock glacier flow structures using Gabor filters and IKONOS imagery

While ridges and furrows on the surface of rock glaciers are probably the most characteristic morphological features of this expression of creeping mountain permafrost, this is the first study that examines the utility of texture filters in detecting rock glacier flow structures. Texture features were derived from a Gabor filterbank applied to two panchromatic IKONOS orthoimages from the Chilean Andes, and terrain attributes were obtained in order to narrow down the area of interest and as additional predictor variables. Four classification methods of different complexity (generalized linear model, GLM; generalized additive model, GAM; support vector machine, SVM; Bundling) were applied to three sets of predictor variables (texture attributes, terrain attributes, and the combination of both), and predictive performances were estimated using two spatial cross-validation strategies in terms of the median area under the ROC (receiver operating characteristics) curve (AUROC). Overall, classifiers utilizing texture attributes alone or, usually even better, in combination with terrain attributes outperformed terrain attributes alone, and Bundling (in most cases followed by SVM) showed the overall best performance as a classification method. Cross-validated median AUROC values were mostly between 0.70 and 0.80, or “fair,” in this focused pilot study, but much better results are to be expected at the landscape scale. Permutation-based spatial variable importance measures indicate that Gabor features corresponding to texture wavelengths between 10 and 30 m are the most important predictors, which is consistent with typical ridge spacing on rock glaciers. Confounding occurred mostly in areas with linear erosion features and ridges or scarps in morainic and thermokarst terrain. We suggest that texture filters and the chosen methodological approach are relevant not only for rock glacier mapping but also for delineating debris-covered glaciers and characterizing glacier surfaces, as well as for other geomorphological and cryospheric applications.

► The utility of texture filters in detecting rock glacier flow patterns was assessed.
► A Gabor filterbank was compared to terrain attributes using four classifiers.
► Gabor filters achieved an AUROC of 0.726 on a highly focused data set.
► The Bundling classifier performed best overall.