Search

Understanding dynamics of urban land-use is crucial for comprehending urban spaces and evaluating planning strategies. A range of data-driven models based on the representation learning of multiple data sources have focused on extracting spatially explicit characteristics at the feature level for urban function inference. However, they commonly pay no attention to the systematic relationships between urban land-use and transportation as the core components of urban systems. Consequently, while performing relatively well in urban land-use recognition, these models cannot transfer across various urban tasks and have almost no generalizability in integrated urban modeling. Guided by the theory of integrated land-use and transport modeling, this study proposes a multi-modal deep learning model to leverage the systematic relationships between urban components. First, spaces of urban places, urban forms, urban flows, and urban locations are conceptualized from the interactions between land use and transportation systems and represented by multi-source heterogeneous spatial features. Second, to account for both direct and indirect interactions in these spaces, a Deep & Wide network is introduced to fuse different modalities of spatial features. Using Shenzhen city as a testbed, extensive experimental results show that our approach improves accuracy by 13.3% compared to state-of-the-art models. We further validate the superior generalizability of our approach across various urban tasks, such as predicting urban land-use, housing prices, and population density, over other baselines. Enabling such a doubly-informed framework of urban theory and AI, this study provides a pilot demonstration for the new scientific paradigm of AI for Urban Science and Modeling.

With the advancement of lead–bismuth fast reactors, there has been increasing attention directed towards the design of and manufacturing technology for electromagnetic pumps employed to drive liquid lead–bismuth eutectic (LBE). These electromagnetic pumps are characterized by a simple structure, effective sealing, and ease of flow control. They exploit the excellent electrical conductivity of liquid metals, allowing the liquid metal to be propelled by Lorentz forces generated by the traveling magnetic field within the pump. To better understand the performance characteristics of electromagnetic pumps and master the techniques for integrated manufacturing and performance optimization, this study conducted fundamental research, development of key components, and the assembly of the complete pump. Consequently, an annular linear induction pump (ALIP) suitable for liquid lead–bismuth eutectic was developed. Additionally, within the lead–bismuth thermal experimental loop, startup and preheating experiments, performance tests, and flow-head experiments were conducted on this electromagnetic pump. The experimental results demonstrated that the output flow of the electromagnetic pump increased linearly with the input current. When the input current reached 99 A, the loop achieved a maximum flow rate of 8 m3/h. The efficiency of the electromagnetic pump also increased with the input current, with a maximum efficiency of 5.96% during the experiments. Finally, by analyzing the relationship between the flow rate and the pressure difference of the electromagnetic pump, a flow-head model specifically applicable to lead–bismuth electromagnetic pumps was established.