The west branch of Karayaylak Glacier (eastern Pamir Plateau) surged in May 2015, significantly impacting on local socio-economic development. This event was also of great significance for studies of surging glaciers. Using Sentinel-1 imagery analyzed by offset tracking, based on normalized cross-correlation (NCC), and with the support of the Google Earth Engine (GEE) platform, we quantified the ice surface velocity of the west branch and terminus of Karayaylak Glacier from 13 October 2014 to 17 October 2020. Sentinel-1 images were acquired at intervals of 12 or 24 days. We also used a three-dimensional (3-D) laser scanner to measure the velocity of 3 ablation stakes and 56 feature points in the study region from 15 August to 6 October 2015, for the purpose of accuracy assessment. We set up an automatic meteorological station to record the air temperature in the same period and combined this with data from Tashkurgan meteorological station from 1957 to 2015. Analysis of this dataset provided insights into the glacier surge mechanism, with the following conclusions. (1) Surface velocity of the west branch and terminus of Karayaylak Glacier increased sharply after October 2014. The velocity then dropped significantly in the two months after the surge, and stayed at low values for nearly a year. After 2017, the velocity was slightly higher than in the previous period. (2) The surge event occurred from 11 April to 17 May 2015; the average surface velocity in this phase attained 2395 m a⁻¹ with a maximum velocity of 4265 m a⁻¹ at the west branch terminus. (3) From 2017 to 2020, the velocity showed periodic annual changes. (4) Based on the meteorological data analysis, we conclude that this surge resulted from the interaction between thermal and hydrological control mechanisms. Simultaneously, we demonstrate the high potential of the GEE platform and Sentinel-1 data to extract glacier surface velocity.

Glaciers in High‐mountain Asia play a critical role in both climate change studies and regional water resource management. However, detailed observations over a large spatial extent remain scarce. In this study, we reconstruct annual glacier‐wide mass balance from 2000 to 2020 for glaciers larger than 0.1 km² across the Tien Shan and Pamir using machine learning (ML) techniques. Five ensemble ML and a deep neural network models were tested, with XGBoost demonstrating the best performance and thus selected for the reconstruction of the glacier mass balance time series. Predictor variables included meteorological data from the ERA5‐Land data set and topographic features. The results indicate an average mass loss of −0.39 m water equivalent (m w.e.) per year for the studied period, with the highest losses observed in the Djungar Alatau (−0.68 m w.e. yr⁻¹), and the lowest in the eastern Pamir (−0.10 m w.e. yr⁻¹). Additionally, the results reveal that small glaciers (area <1 km²) experience more rapid mass loss. The temporal evolution of glacier mass balance exhibits, on average, an acceleration but with spatiotemporal variability. Variable importance analysis identified glacier elevation and geographic location as the dominant factors influencing mass balance, followed by the temperatures of July and August. This work further advances the application of ML methods in glaciology, enhancing our understanding of regional glacier mass balance.