O-D space-time distribution prediction method based on variable-scale geographic weighted regression model

Abstract

The invention relates to an O-D space-time distribution prediction method based on a variable-scale geographic weighted regression model, belonging to the technical field of urban traffic planning andmanagement as well as traffic systems. A built environment is used as a explanatory variable of O-D spatial and temporal distribution, and the interpretation of the built environment to the spatial and temporal distribution of O-D is proved by a case. A method for quantifying the spatial heterogeneity of O-D spatiotemporal distribution in urban built environment is presented. The effect and benefit of the present invention is to explain the spatial heterogeneity effect of the built environment on the temporal and spatial distribution of O-D, and a set of quantitative analysis methods suitable for traffic cells of different scales is provided, which can improve the accuracy of urban O-D spatial and temporal distribution prediction results.

Description

technical field [0001] The invention belongs to the technical field of urban traffic planning and management, relates to the field of origin-destination (O-D) time-space distribution and ITS intelligent transportation system, and is especially suitable for explaining O-D time-space distribution and O-D time-space based on the urban built environment Distribution prediction method. Background technique [0002] The existing Geographically weighted regression (GWR) model is widely used in the fields of economics, sociology and ecology, and its application in the field of transportation planning has gradually begun to be valued. Wang used the GWR model to explore the impact of urban built environment on road travel time, and concluded that the impact of built environment attributes on road travel time in different road sections is different, and there are spatial heterogeneity characteristics. Dziauddin studied how light rail transit stations in Kuala Lumpur, Malaysia, affect ...

AI Technical Summary

Problems solved by technology

Dziauddin studied how light rail transit stations in Kuala Lumpur, Malaysia, affect housing values ​​by introducing GWR. The results show that light rail transit stations can have an impact on residential values, but there are considerable spatial differences in geographical regions. Significant effect on housing values ​​in income neighborhoods, but not so much in high-income neighborhoods

[0003] In the traditional GWR model, the optimal average scale method is adopted to deal with the problem that some parameters have a larger scale of influence and other parameters have a smaller scale, that is, it is assumed that all parameters in the GWR model remain at the same scale, But that's obviously unrealistic

Images