Urban data prediction method based on a generative causal interpretation model

Abstract

An urban data prediction method based on a generative causal interpretation model is provided. The generative causal interpretation model includes exogenous variables, spatio-temporal conditional parent variables, controlled causal transition functions, and spatio-temporal mixing functions. By inferring the model's exogenous variables, causal descriptors, spatio-temporal conditional parent variables, and other causal latent variables from the observation data and fitting the corresponding functions such as the controlled causal transfer function and the spatio-temporal mixing function, the invention can predict the spatio-temporal data in city level based on the model. The observation data of the urban complex system can be decomposed into causal descriptors with physical meanings. Under the influence of stable causal structure, the robustness and applicability of the model can be improved, so that the prediction results are more in line with the operation of urban complex systems.