Abstract: Disclosed is a method for preparing a bimetallic perovskite loaded grapheme-like carbon nitride photocatalyst, comprising: 11) dissolving SbCl3 and AgCl in HCl solution under heating and constant stirring; then adding CsCl in the heated solution to form sediment on the bottom of the beaker; collecting the sediment and wash it with ethanol, and finally drying in an oven to obtain Cs2AgSbCl6 powder; 12) adding melamine into an aluminum oxide crucible and placing it into a muffle furnace for calcination and finally cooling to room temperature naturally to obtain g-C3N4 samples; 13) adding the Cs2AgSbCl6 bimetallic perovskite and the g-C3N4 into a solvent, and stirring after subjecting to ultrasound, and drying after centrifuging to obtain the photocatalyst. Provided is a new idea for the combination of bimetallic halide perovskite and photocatalytic material, and the preparation method has mild conditions, simple operation, and is favorable for large-scale production.

Abstract: A traffic flow forecasting method based on Deep graph Gaussian processes includes: S1, with respect to the dynamics existing in a spatial dependency, using an attention kernel function to describe a dynamic dependency among vertices on a topological graph, and using the attention kernel function as a covariance function in an Aggregation Gaussian process to extract dynamic spatial features; S2, obtaining a Temporal convolutional Gaussian process from weights at different times and a convolution function that obeys the Gaussian processes, and obtaining temporal features in traffic data by combining the Aggregation Gaussian process; S3, constructing a Deep graph Gaussian process method integrating a Gaussian process and a depth structure from the Aggregation Gaussian process, the Temporal convolutional Gaussian process and a Gaussian process with a linear kernel function, inputting a data sample to be forecasted into the Deep graph Gaussian process method to obtain a forecasted result.