Watershed

Adaptive graph construction and graph contrastive learning for geospatial feature embedding

Geospatial features serve as a cornerstone in urban planning and location-based services. Effective geospatial feature embedding is crucial for downstream geospatial Deep Neural Networks (DNN) applications. Currently, geospatial feature representation learning approaches rely on...

Effects of small-scale forest treatments on reducing wildfire burn severity

Background Intensive fire suppression and climate change have escalated wildfire intensity in fire-adapted forests. Although the consequences of fire suppression policies are well documented, fuel reduction treatment effectiveness – particularly across varying treatment sizes – r...

Engineering and land use intensified climate-driven Yangtze River flood hazards since the Little Ice Age

Understanding the interplay between climate variability and human activities is essential for assessing long-term river flood hazards. Yet, the relative contributions of natural and anthropogenic drivers to flood magnitude remain poorly constrained due to limited multicentury rec...