Evaluation of Indian Lightning Location Network (ILLN) and characterization of cloud-to-ground lightning over Lucknow and Shillong using an ordinary camera

Our analysis demonstrates the capability of machine learning models in estimating glacier mass balance in terms of performance metrics and dataset availability. Feature importance analysis suggests that ablation features are significant. This is in agreement with the predominantly negative mass balance observations. We show that ensemble tree models typically depict the best performance. However, neural network models are preferable for biased inputs and kernel-based models for smaller datasets.