Search Results (5)

Accurate streamflow forecasting is crucial for water resources management and flood mitigation, yet it remains challenging due to the complex dynamics of hydrological systems. Conventional data-driven approaches often struggle to effectively capture spatio-temporal evolution characteristics, particularly the dynamic interdependencies among streamflow gauges. This study proposes a novel deep learning architecture, termed DynaSTG-Former. It employs a multi-channel dynamic graph constructor to adaptively integrate three spatial dependency patterns: physical topology, statistical correlation, and trend similarity. A dual-stream temporal predictor is designed to collaboratively model long-range dependencies and local transient features. In an empirical study within the Delaware River Basin, the model demonstrated exceptional performance in multi-step-ahead forecasting (12-, 36-, and 72 h). It achieved basin-scale Kling–Gupta Efficiency (KGE) values of 0.961, 0.956, and 0.855, significantly outperforming baseline models such as LSTM, GRU, and Transformer. Ablation studies confirmed the core contribution of the dynamic graph module, with the Pearson correlation graph playing a dominant role in error reduction. The results indicate that DynaSTG-Former effectively enhances the accuracy and stability of streamflow forecasts and demonstrates its strong robustness at the basin scale. It thus provides a reliable tool for precision water management. Full article

Density stratification plays a crucial role in estuarine hydrodynamics and material transport. In this study, we utilized a well-calibrated numerical model to investigate the stratification processes and underlying mechanisms in the dynamically wide Pearl River Estuary (PRE). In the upper estuary, longitudinal straining governs stratification, enhancing it during ebb tide and reducing it during flood tide. The Coriolis force becomes significant in the lower estuary due to the increased basin width, causing seaward freshwater to be confined to the West Shoal, where a pronounced transverse salinity gradient forms. Interacting with lateral current shear, density stratification is most pronounced in this region. The prevailing northeasterly wind creates a mixed layer near the surface, shifting stratification to the middle layer of the water column in the upper estuary. Wind stirring reduces stratification throughout the estuary. Under the wind’s influence, the seaward outflow is confined to a narrower region and shifts westward, resulting in the most apparent stratification occurring on the West Shoal of the PRE due to lateral straining. These findings on the evolution of freshwater pathways and their role in modulating density stratification have significant implications for other wide estuaries, such as Delaware Bay and the La Plata-Parana estuary. Full article

Runoff prediction plays an important role in the construction of intelligent hydraulic engineering. Most of the existing deep learning runoff prediction models use recurrent neural networks for single-step prediction of a single time series, which mainly model the temporal features and ignore the river convergence process within a watershed. In order to improve the accuracy of runoff prediction, a dynamic spatiotemporal graph neural network model (DSTGNN) is proposed considering the interaction of hydrological stations. The sequences are first input to the spatiotemporal block to extract spatiotemporal features. The temporal features are captured by the long short-term memory network (LSTM) with the self-attention mechanism. Then, the upstream and downstream distance matrices are constructed based on the river network topology in the basin, the dynamic matrix is constructed based on the runoff sequence, and the spatial dependence is captured by combining the above two matrices through the diffusion process. After that, the residual sequences are input to the next layer by the decoupling block, and, finally, the prediction results are output after multi-layer stacking. Experiments are conducted on the historical runoff dataset in the Upper Delaware River Basin, and the MAE, MSE, MAPE, and NSE were the best compared with the baseline model for forecasting periods of 3 h, 6 h, and 9 h. The experimental results show that DSTGNN can better capture the spatiotemporal characteristics and has higher prediction accuracy. Full article

Land system change has been identified as one of four major Earth system processes where change has passed a destabilizing threshold. A historical record of landscape change is required to understand the impacts change has had on human and natural systems, while scenarios of future landscape change are required to facilitate planning and mitigation efforts. A methodology for modeling long-term historical and future landscape change was applied in the Delaware River Basin of the United States. A parcel-based modeling framework was used to reconstruct historical landscapes back to 1680, parameterized with a variety of spatial and nonspatial historical datasets. Similarly, scenarios of future landscape change were modeled for multiple scenarios out to 2100. Results demonstrate the ability to represent historical land cover proportions and general patterns at broad spatial scales and model multiple potential future landscape trajectories. The resulting land cover collection provides consistent data from 1680 through 2100, at a 30-m spatial resolution, 10-year intervals, and high thematic resolution. The data are consistent with the spatial and thematic characteristics of widely used national-scale land cover datasets, facilitating use within existing land management and research workflows. The methodology demonstrated in the Delaware River Basin is extensible and scalable, with potential applications at national scales for the United States. Full article

The Delaware River has made a marked recovery in the half-century since the adoption of the Delaware River Basin Commission (DRBC) Compact in 1961 and passage of the Federal Clean Water Act amendments during the 1970s. During the 1960s, the DRBC set a 3.5 mg/L dissolved oxygen criterion for the river based on an economic analysis that concluded that a waste load abatement program designed to meet fishable water quality goals would generate significant recreational and environmental benefits. Scientists with the Delaware Estuary Program have recently called for raising the 1960s dissolved oxygen criterion along the Delaware River from 3.5 mg/L to 5.0 mg/L to protect anadromous American shad and Atlantic sturgeon, and address the prospect of rising temperatures, sea levels, and salinity in the estuary. This research concludes, through a nitrogen marginal abatement cost (MAC) analysis, that it would be cost-effective to raise dissolved oxygen levels to meet a more stringent standard by prioritizing agricultural conservation and some wastewater treatment investments in the Delaware River watershed to remove 90% of the nitrogen load by 13.6 million kg N/year (30 million lb N/year) for just 35% ($160 million) of the $449 million total cost. The annual least cost to reduce nitrogen loads and raise dissolved oxygen levels to meet more stringent water quality standards in the Delaware River totals $45 million for atmospheric NOX reduction, $130 million for wastewater treatment, $132 million for agriculture conservation, and $141 million for urban stormwater retrofitting. This 21st century least cost analysis estimates that an annual investment of $50 million is needed to reduce pollutant loads in the Delaware River to raise dissolved oxygen levels to 4.0 mg/L, $150 million is needed for dissolved oxygen levels to reach 4.5 mg/L, and $449 million is needed for dissolved oxygen levels to reach 5.0 mg/L. Full article