Machine Learning Algorithms for Extraction of Glacial Lakes Using Ground Range Detected (GRD) Data: A Case Study from Hunza River Basin, Pakistan

In the Karakoram Mountain range, glacial lakes are essential elements of the cryosphere. As a function of climate change and increasing temperature, these glacial lakes threaten downstream existence and the ecosystem by short time glacial lake outburst floods (GLOF). Therefore, the Glacial Lake mapping technique is a vital task to observe GLOF hazards. In this study, microwave Sentinel-1 Ground Range Detected (GRD) data used. It has the dual-polarization capability (HH + HV or VV + VH) and the ability to penetrate even through clouds or any weather condition. The study objective is to explore the application of GRD data and evaluate the efficiency and accuracy of machine learning algorithms for the extraction of water bodies. The study method is based on two main procedures, GRD backscattering analysis and supervised Machine Learning classifiers. The most commonly used machine learning classifiers are Random Forest (RF), K-nearest neighbor (KNN), and Maximum Likelihood. Although both procedures show better results for glacial lakes mapping in the study area, the mean backscatter parameter has the best accuracy rate than others in the total backscattering analysis. Likewise, in the classification approach, accuracy assessment was executed by comparing the results obtained for each classifier with the reference data. For all experiments, KNN performed the best at given training samples (Accuracy = 93%, Error rate = 0.06%) for both classes, compared to RF (Accuracy = 92%, Error rate = 0.07) and Maximum Likelihood (Accuracy = 90%, Error rate = 0.09%). The high classification accuracy obtained to extract glacial lakes using our approach will be useful to determine the short time flood outburst and take future precautionary measurements.

Morphological and Compositional Studies on Al/Ti/TiN/Si, Al/TiN/Si, Al/W/Si, Al/WN/Si Systems to Test the Diffusion Barrier Properties of Nanoscale-Thick Layers between Al and Si

In this work, an investigation of the properties of nanoscale-thick Ti/TiN, TiN, W, WN layers as diffusion barriers between Si and Al is carried out in view of Si-based electronic applications. Heat treatments were performed on the samples to activate interdiffusion between Si and Al. Changing annealing time and temperature, each sample was morphologically characterized by scanning electron microscopy and atomic force microscopy and compositionally characterized by Rutherford backscattering analysis. The aim is to evaluate the efficiency of the layers as diffusion barriers between Si and Al and, at the same time, to evaluate the surface morphological changes upon annealing processes.