The understanding of glacier and ice shelf front changes is of paramount importance in analyzing their material balance and their significant contributions to global sea-level variations. Recently, the increasing availability of remote sensing images has provided ample data support for calving front detection. By combining massive amounts of data, deep learning techniques have demonstrated great potential in front extraction, as they can automatically generate task-specific features. In this study, in contrast to the traditional framework based on a pure CNN architecture, we propose a novel calving front detection network, GLA-STDeepLab, by incorporating the Swin transformer module into DeepLabv3+ to enhance the modeling capability of long-range contextual dependencies. We also introduce Global-local attention mechanisms into the module, striving to foster interactions between the corresponding coarse and fine-grained feature maps. Through extensive experimentation on a diverse and challenging SAR database, CaFFe, our network is shown to surpass the current state-of-the-art methods, achieving results with an IoU of 0.94 and a mean distance error (MDE) of 473±34 m. More meaningfully, we extracted the time-series front information of the Amery Ice Shelf from 2015 to 2023 and precisely captured the calving events of the D-28 and D-32 icebergs. The findings demonstrate that our method enables precise monitoring of the dynamic information of glacier and ice shelf fronts, as well as their far-reaching implications for ice sheet mass balance and global climate change. The code used in this study is provided at https://github.com/Tangyu35/Calving-front-detection.

Rich datasets related to the earth have been obtained because of the rapid development of earth observation technologies. A broad range of prior research has investigated how to obtain the correlation relationships of relevant features from a large number of data containing spatio-temporal information, which is also the technical basis for big data analysis. Based on the dynamic time warping (DTW) algorithm, this research proposes a correlation analysis method of time series data, and applies it to the correlation analysis between the time series features of the surface temperature and melting area of the Antarctic ice sheet. The results show that our method based on the DTW algorithm can effectively distinguish the change details of the non-linear time series. The correlation coefficients between these two highly-correlated factors computed by our method are higher than Pearson’s correlation coefficients by more than 0.2 almost in all study areas where data are available. In summary, the method proposed in this study provides a new feasible way for the correlation study of time-series data. It outperforms than traditional correlation coefficients such as Pearson’s correlation coefficient in some fields, specifically when complex nonlinear time series data with certain periodicity are used.

Wetlands represent one of the three principal ecosystems and serve a vital function in the protection of water resources and the regulation of climate. However, wetlands are currently experiencing significant challenges, particularly in the agriculturally productive wetlands of the Heilongjiang River Basin, which have been considerably impacted by human activities. This study focuses on three representative wetlands situated within the Heilongjiang River Basin. This study analyses changes in wetland area and landscape patterns from 2002 to 2022, as well as the impact of agriculture and impervious surface expansion on the wetlands. The findings indicate that agricultural expansion is the primary driver of wetland area loss. The wetland area affected by agriculture demonstrates the most significant change, with the largest observed shift reaching 47.2%. The expansion of impervious surfaces was found to have a significant impact on wetland fragmentation, resulting in a notable decrease in wetland connectivity. This was evidenced by a reduction in the average patch size, which decreased by 14.68 ha over the decade from 2007 to 2017, a period during which impervious surfaces expanded. This paper identifies the distinctions in the influence of diverse human activities on wetland landscape patterns in the Heilongjiang Basin and employs natural samples for control, thereby attenuating the impact of the natural environment. This study offers a novel perspective on the processes of wetland change and the maintenance of wetland health, which is crucial for the realisation of clean water and sanitation (Sustainable Development Goal 6.6).

Monitoring changes in water-related ecosystems is central to SDG 6.6.1, yet most existing wetland products are produced at annual scales and therefore cannot resolve seasonal transitions in wetland extent and type composition. This limitation is particularly important in delta wetlands, where river discharge, tidal inundation, vegetation phenology, and human activities drive pronounced intra-annual wetland dynamics. Accurately characterizing these seasonal dynamics is essential for understanding wetland ecological functions, evaluating hydrological regulation capacity, and supporting adaptive conservation and management. However, seasonal-scale wetland characterization remains constrained by the lack of temporally explicit labels, frequent cloud contamination, and severe sample imbalance among rare wetland classes. To address these challenges, this study proposes STEP-Unet, a weakly supervised framework that derives seasonally resolved wetland type information from annual wetland products without additional manual annotations. Experimental results in the Yellow River Delta demonstrate that STEP-Unet consistently outperforms direct classification using annual labels across all seasons, achieving an overall accuracy of 0.905 and a mean intersection-over-union of 0.800. The model was further applied to characterize seasonal wetland class dynamics in the Yellow River Delta from 2020 to 2022, revealing clear intra-annual transitions among wetland types. These results indicate that refining annual wetland products into seasonally explicit wetland class information can provide a more detailed basis for SDG 6.6.1 monitoring and adaptive management of dynamic delta wetland ecosystems.