ST-D3DDARN: Urban traffic flow prediction based on spatio-temporal decoupled 3D DenseNet with attention ResNet.

Urban traffic flow prediction plays a crucial role in intelligent transportation systems (ITS), which can enhance traffic efficiency and ensure public safety. However, predicting urban traffic flow faces numerous challenges, such as intricate temporal dependencies, spatial correlations, and the influence of external factors. Existing research methods cannot fully capture the complex spatio-temporal dependence of traffic flow. Inspired by video analysis in computer vision, we represent traffic flow as traffic frames and propose an end-to-end urban traffic flow prediction model named Spatio-temporal Decoupled 3D DenseNet with Attention ResNet (ST-D3DDARN). Specifically, this model extracts multi-source traffic flow features through closeness, period, trend, and external factor branches. Subsequently, it dynamically establishes global spatio-temporal correlations by integrating spatial self-attention and coordinate attention in a residual network, accurately predicting the inflow and outflow of traffic throughout the city. In order to evaluate the effectiveness of the ST-D3DDARN model, experiments are carried out on two publicly available real-world datasets. The results indicate that ST-D3DDARN outperforms existing models in terms of single-step prediction, multi-step prediction, and efficiency.

Immiscible hydrous Fe-Ca-P melt and the origin of iron oxide-apatite ore deposits.

The origin of iron oxide-apatite deposits is controversial. Silicate liquid immiscibility and separation of an iron-rich melt has been invoked, but Fe-Ca-P-rich and Si-poor melts similar in composition to the ore have never been observed in natural or synthetic magmatic systems. Here we report experiments on intermediate magmas that develop liquid immiscibility at 100 MPa, 1000-1040 °C, and oxygen fugacity conditions (fO2) of ∆FMQ = 0.5-3.3 (FMQ = fayalite-magnetite-quartz equilibrium). Some of the immiscible melts are highly enriched in iron and phosphorous ± calcium, and strongly depleted in silicon (<5 wt.% SiO2). These Si-poor melts are in equilibrium with a rhyolitic conjugate and are produced under oxidized conditions (~FMQ + 3.3), high water activity (aH2O ≥ 0.7), and in fluorine-bearing systems (1 wt.%). Our results show that increasing aH2O and fO2 enlarges the two-liquid field thus allowing the Fe-Ca-P melt to separate easily from host silicic magma and produce iron oxide-apatite ores.