arXiv subjects

Qiang Ai

Publications and source records attributed to Qiang Ai.

2 recordsLinked to original sources

arXiv2024

Optically and remotely controlling localization of exciton polariton condensates in a potential lattice

Exciton polaritons are inherently tunable systems with adjustable potential landscape. In this work we show that exciton polariton condensates can be selectively localized in a fixed optically induced periodic lattice with uniform potential depth, by judiciously controlling a second focused pump of very small size away from the lattice chain. Specifically, the localized polariton condensate can be tuned among different potential traps by adjusting the relative distance between the small pump spot and the potential lattice. The adjustment of the excitation position of the smaller pump spot and its combination with the fixed larger pump spot for the potential creation induce the mode selection determined by gain profile, group velocity, and potential distribution within the system. The localization of the exciton polariton condensate and its control are independent of the orientation of the potential lattice, thus, even in slightly disordered system, one can selectively excite such localized polariton condensates. Our results illuminate a path to the remote manipulation of exciton polariton bosonic condensates in fixed integrated photonic chips and circuits.

physics.optics↗

arXiv2023

TraffNet: Learning Causality of Traffic Generation for What-if Prediction

Real-time what-if traffic prediction is crucial for decision making in intelligent traffic management and control. Although current deep learning methods demonstrate significant advantages in traffic prediction, they are powerless in what-if traffic prediction due to their nature of correla-tion-based. Here, we present a simple deep learning framework called TraffNet that learns the mechanisms of traffic generation for what-if pre-diction from vehicle trajectory data. First, we use a heterogeneous graph to represent the road network, allowing the model to incorporate causal features of traffic flows, such as Origin-Destination (OD) demands and routes. Next, we propose a method for learning segment representations, which models the process of assigning OD demands onto the road network. The learned segment represen-tations effectively encapsulate the intricate causes of traffic generation, facilitating downstream what-if traffic prediction. Finally, we conduct experiments on synthetic datasets to evaluate the effectiveness of TraffNet. The code and datasets of TraffNet is available at https://github.com/iCityLab/TraffNet.

cs.LG↗