Shuwen Qi

Reliable prediction of suspended sediment concentration is essential for reservoir operation, sustainable water management, and river ecosystem restoration. However, accurate forecasting remains challenging due to the strong nonlinearity and nonstationarity of sediment transport processes, as well as the complex interactions between hydrological variability and sediment supply dynamics.This study develops an integrated forecasting framework that combines signal decomposition, feature selection, deep learning, and optimization. In the proposed framework, variational mode decomposition is used to decompose suspended sediment concentration time series into multiple subcomponents, enabling the separation of temporal patterns at different scales. An improved sparrow search algorithm calibrates the decomposition parameters and improves component stability. Multigene genetic programming is then applied to select informative subcomponents and reduce redundancy. A hybrid convolution-transformer network is constructed to model both local fluctuation patterns and longer-range dependencies within the selected components. Finally, the improved sparrow search algorithm(ISSA) optimizes the weighting of individual model outputs to form an integrated adaptive predictor. The framework is evaluated using daily streamflow(Q) and suspended sediment concentration observations from 1977 to 1986 at the Tangnaihai Hydrological Station in the upper Yellow River Basin. The results show high predictive accuracy, achieving a Nash-Sutcliffe efficiency of 0.9535 on an independent test period with consistently low error metrics. Overall, the proposed framework provides a robust and generalizable approach for suspended sediment concentration forecasting under complex environmental conditions.

Over the past decades, China has experienced severe compound natural disasters, such as extreme rainfalls, which have led to significant losses. In response to the challenges posed by the lack of a clear investigation process and inadequate comprehensiveness in evaluating the natural disaster chains, this study proposes a comprehensive retrospective simulation strategy for emergency investigation and simulation of heavy rainstorm–flash flood–debris flow chain disasters at the county–town level. The primary aim is to avert potential new chain disasters and alleviate subsequent disasters. This study combines emergency investigation efforts with hydrodynamic models to digitally simulate and analyze compound chain disasters triggered by an extreme rainfall event in the Haihe River regional area, specifically Gaoyakou Valley, Liucun Town, Changping District, Beijing, in July 2023, along with potential new disasters in adjacent regions. The findings indicate that the heavy rainstorm chain disaster on “7.29” resulted from a complex interplay of interrelated natural phenomena, including flash floods, debris flows, urban floodings, and river overflows. Hantai Village has experienced flash flood and debris flow events at different times in this area. Should the rainfall volume experienced in Liucun Town be replicated in the Ming Tombs Town area, approximately 6.2 km² of land would be inundated, leading to damages to 458 residences and impacting around 240 ha of agricultural land. The anticipated release of floodwater from the reservoir would lead to significant impacts on downstream residents and roads. Our research can improve the efficacy of emergency investigations and assessments, which in turn can help with the management and reduction of disaster risks at the grassroots level.