Zhejiang Water Conservancy and Hydropower Survey and Design Institute

Optimal Transport-Based Heterogeneous Federated Learning for Chest X-Rays

In some federated learning (FL) scenarios, discrepancies in local client devices result in inconsistent image resolutions, which motivates clients to adopt models with different depths and widths. Existing heterogeneous federated learning methods struggle to maintain model accura...

Effectiveness of Microbial Composite Strains in Reducing River Sediment

The accumulation of sediment in rivers and lakes can elevate riverbeds, leading to a reduction in river channel flood-carrying capacity, impairment of water conservancy project benefits, and destruction of aquatic ecosystems. Systematic dredging projects are required in the routi...

A Two-Stage Machine Learning Framework for High-Resolution Multi-Source Precipitation Fusion in Complex Terrain: A Case Study of Shaoxing, China

High-resolution precipitation fields are essential for flash-flood forecasting and hydrological risk management, especially in small and medium-sized basins, yet single-source precipitation products often show limited accuracy over complex terrain. This study develops a two-stage...

Numerical Investigation on Water Hammer Pressure in Long-Distance and Large-Diameter Gravity Flow Water Pipelines in Hilly Areas

Abstract The closure strategy of the downstream end valve is one of the important factors affecting the safety of long-distance, large-diameter gravity flow water supply pipelines. This paper takes the large-diameter gravity flow water supply pipeline of the Siqiao Reservoir Irri...