In this work nine non-linear regression models were compared for sub-pixel impervious surface area mapping from Landsat images. The comparison was done in three study areas both for accuracy of imperviousness coverage evaluation in individual points in time and accuracy of imperviousness change assessment. The performance of individual machine learning algorithms (Cubist, Random Forest, stochastic gradient boosting of regression trees, k-nearest neighbors regression, random k-nearest neighbors regression, Multivariate Adaptive Regression Splines, averaged neural networks, and support vector machines with polynomial and radial kernels) was also compared with the performance of heterogeneous model ensembles constructed from the best models trained using particular techniques. The results proved that in case of sub-pixel evaluation the most accurate prediction of change may not necessarily be based on the most accurate individual assessments. When single methods are considered, based on obtained results Cubist algorithm may be advised for Landsat based mapping of imperviousness for single dates. However, Random Forest may be endorsed when the most reliable evaluation of imperviousness change is the primary goal. It gave lower accuracies for individual assessments, but better prediction of change due to more correlated errors of individual predictions. Heterogeneous model ensembles performed for individual time points assessments at least as well as the best individual models. In case of imperviousness change assessment the ensembles always outperformed single model approaches. It means that it is possible to improve the accuracy of sub-pixel imperviousness change assessment using ensembles of heterogeneous non-linear regression models.

This paper presents a detailed study of melting processes conducted on Hansbreen - a tidewater glacier terminating in the Hornsund fjord, Spitsbergen. The fieldwork was carried out from April to July 2010. The study included observations of meltwater distribution within snow profiles in different locations and determination of its penetration time to the glacier ice surface. In addition, the variability of the snow temperature and heat transfer within the snow cover were measured. The main objective concerns the impact of meltwater on the diversity of physical characteristics of the snow cover and its melting dynamics. The obtained results indicate a time delay between the beginning of the melting processes and meltwater reaching the ice surface. The time necessary for meltwater to percolate through the entire snowpack in both, the ablation zone and the equilibrium line zone amounted to c. 12 days, despite a much greater snow depth at the upper site. An elongated retention of meltwater in the lower part of the glacier was caused by a higher amount of icy layers (ice formations and melt-freeze crusts), resulting from winter thaws, which delayed water penetration. For this reason, a reconstruction of rain-on-snow events was carried out. Such results give new insight into the processes of the reactivation of the glacier drainage system and the release of freshwater into the sea after the winter period.