Preprint Article Version 1 Preserved in Portico This version is not peer-reviewed

Multi-Scale Recursive Identification of Urban Functional Areas Based on Multi-Source Data

Version 1 : Received: 8 August 2023 / Approved: 8 August 2023 / Online: 9 August 2023 (02:45:19 CEST)

A peer-reviewed article of this Preprint also exists.

Liu, T.; Cheng, G.; Yang, J. Multi-Scale Recursive Identification of Urban Functional Areas Based on Multi-Source Data. Sustainability 2023, 15, 13870. Liu, T.; Cheng, G.; Yang, J. Multi-Scale Recursive Identification of Urban Functional Areas Based on Multi-Source Data. Sustainability 2023, 15, 13870.

Abstract

In recent years, the emergence of spatiotemporal big data has made the transition of functional identification from the physical dimension to socioeconomic or human activities becoming more common. In the identification of urban functional areas, most studies considered only a single data source and a single division scale, the research results have problems such as low update frequency or incomplete information in a single data set, and overfitting or underfitting in a single spatial resolution. Using taxi trajectory data and point of interest (POI) data as the main data source, this study proposes a multi-scale recursive identification method for urban functional areas based on cross-validation. First, used the dynamic time warping (DTW) algorithm generates a time series similarity matrix, the CA-RFM model combines the clustering algorithm and random forest model is constructed, the model uses a clustering algorithm (K-MEDOIDS) to extract sig-nificant feature regions as input, which are imported into the random forest model for UFZ identification. Then, to overcome the shortcomings of single scale in expressing urban structural characteristics, a recursive model of different levels of urban road networks is established to classify multi-scale functional areas. Finally, cross-validation using the CA-RFM model and POI quantitative identification method, obtains the final identification results of urban functional areas. This paper selects Shenzhen as the study area for the case study, the results show that the com-bination of clustering algorithm and random forest model greatly reduces the error of manual selection of training samples. In addition, the research shows the superiority of the multi-scale recursive identification method that fuses multi-source data and performs cross-validation from two aspects, that is, the division speed of urban functional area identification results is accelerated and the accuracy is improved.

Keywords

Urban Functional Area; CA-RFM Model; Multi-scale recursive recognition; POI quantitative identification

Subject

Environmental and Earth Sciences, Geography

Comments (0)

We encourage comments and feedback from a broad range of readers. See criteria for comments and our Diversity statement.

Leave a public comment
Send a private comment to the author(s)
* All users must log in before leaving a comment
Views 0
Downloads 0
Comments 0


×
Alerts
Notify me about updates to this article or when a peer-reviewed version is published.
We use cookies on our website to ensure you get the best experience.
Read more about our cookies here.