A Spatiotemporal Autocorrelation Analysis Method for Geographic Multivariate Flow Data Based on Cellular Automata

Abstract

The present invention provides a time-space autocorrelation analysis method for geographical multi-stream data based on cellular automata. The improved cellular automata dynamic model is used to express the space-time and complexity of geographical data, and the cellular (geographic Region) transformation rules and spatial heterogeneity of asynchronous evolution can more accurately analyze non-linear structural geographic multivariate flow data based on complex networks. The present invention analyzes the cellular unit and extracts various influencing factors, so that the model parameters of the cellular automata can be obtained more accurately, which is accurate and efficient; the conversion rules obtained by using the ANN algorithm are more dynamic than the fixed conversion rules of the entire model. It is more descriptive and conforms to the actual transformation of cells; according to Moran's I, the correlation between cells is expressed, which better and more clearly reflects the spatial and temporal distribution of geographical data, so that it is more convenient to carry out subsequent spatiotemporal data models Simulation and forecasting, making simulation and forecasting more accurate.

Description

technical field [0001] The invention belongs to the statistical analysis method of geographic space, and specifically relates to the fields of cellular automata, geographic multivariate flow data processing, geographic spatial correlation analysis and the like. Background technique [0002] In recent years, with the continuous development and popularization of geographic information technology, remote sensing technology, Internet of Things, and mobile terminals, multivariate geographic data with spatial reference has undergone rapid evolution for decades, forming massive geographic multivariate stream data. These streaming data have the characteristics of sequential, massive, fast, and continuous arrival, and can be aggregated into a dynamic data set that grows infinitely over time. They can also be called spatio-temporal streaming data, such as traffic data, real-time temperature monitoring data, etc. . [0003] At present, the spatial autocorrelation analysis technology c...

AI Technical Summary

Problems solved by technology

However, from the research literature of scholars from various countries, it can be found that the model of geographic multivariate flow data is mainly based on time series model construction, which only considers temporal autocorrelation, and does not take into account geospatial heterogeneity and correlation between multivariate variables.

Images