This study describes a machine learning workflow that brings together a variety of surface mass balance (SMB) measurements and a SMB model to improve model skill and to evaluate the performance of the trained and untrained model. The research makes a novel contribution to glacier mass balance modelling, with the potential for transferability across diverse climatic and glaciological settings. The workflow also provides a valuable framework that could inform the wider development and application of hybrid modelling approaches to glacier evolution that remain physically grounded.

Quantifying the distribution of mountain snow is critical issue to ensure effective water resource management, skillful hydrological prediction, and hazard mitigation. This manuscript presents a highly impactful framework for quantifying meteorological forcing uncertainty in model simulations of mountain snow using novel machine learning applications and large sample emulators. By strictly adhering to FAIR data principles and utilizing open-source, automated workflows, the study provides a compelling demonstration of best practices in hydrological modeling. This paper will serve as an invaluable guide for early-career hydrologists seeking practical examples of rigorous code development and modeling workflows.

The surface mass balance (SMB) of polar ice sheets is vital to their overall mass gain or loss. However, evaluating SMB across Antarctica is extremely difficult because observations that can validate climate-model estimates are widely lacking. In this manuscript, the authors present a highly original approach to this problem: they use GPS observations to evaluate SMB models. Analysis of GPS data from sites across Antarctica is used to evaluate the variability in SMB from several atmospheric models. The findings are timely and important, especially as more SMB models are available at increasingly fine spatial resolution. Overall, the study contributes valuable insights into estimates of ice-sheet mass variability and its varying contribution to sea-level change.

By tracking post-fire tundra recovery up to 90 years using satellite radar across North America, this study reveals that while annual permafrost degradation stabilizes within 7–13 years, seasonal deformation and elevated soil moisture persist for roughly 50 years. This study moves beyond localized, single-site studies to establish a scalable, regional framework across diverse permafrost zones. Ultimately, these findings resolve a major spatial gap in permafrost research by proving that recovery timelines are strongly controlled by regional thermal regimes, providing crucial observational constraints for Earth system models and climate research.

This paper describes the rapid, recent decline of Glacier AX010, the glacier with the oldest observational mass balance record in the Nepal Himalayas. It also discusses the likely disappearance of the glacier within the next two decades, highlighting the ongoing importance of monitoring small glaciers in high mountain regions given their vulnerability to climate warming.