Robust streamflow simulation at glacial basins is essential for the improvement of water sustainability assessment, water security evaluation, and water resource management under the rapidly changing climate. Therefore, we proposed a hybrid modelling framework to link the SWAT+ model considering glacial hydrological processes (GSWAT+) with Gated Recurrent Unit (GRU) neural networks to improve the model simulations and to establish a framework for the robust simulation and forecast of high and low flows in glacial river basins, which could be further used for the explorations of extreme hydrological events under a warming climate. The performance of different models (GSWAT+, GRU, and GRU-GSWAT+, respectively) were thoroughly investigated based on numerical experiments for two data-scarce glacial watersheds in Northwest China. The results suggested that the hybrid model (GRU-GSWAT+) outperformed both the individual deep learning (DL) model (GRU) and the conventional hydrological model (GSWAT+) in terms of simulation and prediction accuracy. Notably, the proposed hybrid model considerably enhanced the simulations of low and high flows that the conventional GSWAT+ failed to capture. Furthermore, utilizing suitable data integration (DI) schemes on feature and target sequences can substantially help to strengthen model stability and representativeness for monthly and annual streamflow sequences. Specifically, introducing one order differential method and decomposition approach, such as ensemble empirical signal decomposition (EEMD) and complete EEMD with adaptive noise (CEEMDAN), into feature and target sequences enriched the learnable ancillary information, which consequently strengthened the predictive performance of the proposed model. Overall, the proposed hybrid model with the suitable DI scheme has the potential to significantly enhance the accuracy of streamflow simulation in data-scarce glacial river basins. This hybrid model not only upheld the fundamental physical principles from the GSWAT+ model, but also considerably mitigated the accumulated bias errors, which caused by the shortage of climate data and inadequate hydrological principles, by using DL based model and DI schemes.

Broad-scale changes in arctic-alpine vegetation and their global effects have long been recognized and labeled one of the clearest examples of the terrestrial impacts of climate change. Arctic-alpine dwarf shrubs are a key factor in those processes, responding to accelerated warming in complex and still poorly understood ways. Here, we look closely into such responses of deciduous and evergreen species, and for the first time, we make use of high-precision dendrometers to monitor the radial growth of dwarf shrubs at unprecedented temporal resolution, bridging the gap between classical dendroecology and the underlying growth physiology of a species. Using statistical methods on a five-year dataset, including a relative importance analysis based on partial least squares regression, linear mixed modeling, and correlation analysis, we identified distinct growth mechanisms for both evergreen (Empetrum nigrum ssp. hermaphroditum) and deciduous (Betula nana) species. We found those mechanisms in accordance with the species respective physiological requirements and the exclusive micro-environmental conditions, suggesting high phenotypical plasticity in both focal species. Additionally, growth in both species was negatively affected by unusually warm conditions during summer and both responded to low winter temperatures with radial stem shrinking, which we interpreted as an active mechanism of frost protection related to changes in water availability. However, our analysis revealed contrasting and inter-annually nuanced response patterns. While B. nana benefited from winter warming and a prolonged growing season, E. hermaphroditum showed high negative sensitivity to spring cold spells after an earlier growth start, relying on additional photosynthetic opportunities during snow-free winter periods. Thus, we conclude that climate-growth responses of dwarf shrubs in arctic-alpine environments are highly seasonal and heterogenic, and that deciduous species are overall likely to show a positive growth response to predicted future climate change, possibly dominating over evergreen competitors at the same sites, contributing to the ongoing greening trend.