Flow-Data-Based Global Spatial Autocorrelation Measurements for Evaluating Spatial Interactions
Spatial autocorrelation analysis is essential for understanding the distribution patterns of spatial flow data. Existing methods focus mainly on the origins and destinations of flow units and the relationships between them. These methods measure the autocorrelation of gravity or the positional and d...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-09-01
|
| Series: | ISPRS International Journal of Geo-Information |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2220-9964/12/10/396 |
| _version_ | 1797626666009231360 |
|---|---|
| author | Shuai Sun Haiping Zhang |
| author_facet | Shuai Sun Haiping Zhang |
| author_sort | Shuai Sun |
| collection | DOAJ |
| description | Spatial autocorrelation analysis is essential for understanding the distribution patterns of spatial flow data. Existing methods focus mainly on the origins and destinations of flow units and the relationships between them. These methods measure the autocorrelation of gravity or the positional and directional autocorrelations of flow units that are treated as objects. However, the intrinsic complexity of actual flow data necessitates the consideration of not only gravity, positional, and directional autocorrelations but also the autocorrelations of the variables of interest. This study proposes a global spatial autocorrelation method to measure the variables of interest of flow data. This method mainly consists of three steps. First, the proximity constraints of the origin and destination of a flow unit are defined to ensure similarity of flow units in terms of direction, distance, and position. This undertaking aims to determine the neighborhood of flow units and generate their adjacent matrices. Second, a spatial autocorrelation measurement model for flow data is constructed on the basis of the adjacent matrix generated. Artificial data sets are also employed to test the validity of the model. Finally, the proposed method is applied to the flow data analysis of population migration in central and eastern China to prove the practical application value of the model. The proposed method is universal and can be generalized to the global spatial autocorrelation analysis of any type of flow data. |
| first_indexed | 2024-03-11T10:13:26Z |
| format | Article |
| id | doaj.art-0cb027d2060a4a4b97cda62de2e34f1c |
| institution | Directory Open Access Journal |
| issn | 2220-9964 |
| language | English |
| last_indexed | 2024-03-11T10:13:26Z |
| publishDate | 2023-09-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | ISPRS International Journal of Geo-Information |
| spelling | doaj.art-0cb027d2060a4a4b97cda62de2e34f1c2023-11-16T10:30:33ZengMDPI AGISPRS International Journal of Geo-Information2220-99642023-09-01121039610.3390/ijgi12100396Flow-Data-Based Global Spatial Autocorrelation Measurements for Evaluating Spatial InteractionsShuai Sun0Haiping Zhang1School of Architecture and Art, North China University of Technology, Rd.5 Jinyuanzhuang, Beijing 100144, ChinaSchool of Geographic Science, Nanjing Normal University, Nanjing 210023, ChinaSpatial autocorrelation analysis is essential for understanding the distribution patterns of spatial flow data. Existing methods focus mainly on the origins and destinations of flow units and the relationships between them. These methods measure the autocorrelation of gravity or the positional and directional autocorrelations of flow units that are treated as objects. However, the intrinsic complexity of actual flow data necessitates the consideration of not only gravity, positional, and directional autocorrelations but also the autocorrelations of the variables of interest. This study proposes a global spatial autocorrelation method to measure the variables of interest of flow data. This method mainly consists of three steps. First, the proximity constraints of the origin and destination of a flow unit are defined to ensure similarity of flow units in terms of direction, distance, and position. This undertaking aims to determine the neighborhood of flow units and generate their adjacent matrices. Second, a spatial autocorrelation measurement model for flow data is constructed on the basis of the adjacent matrix generated. Artificial data sets are also employed to test the validity of the model. Finally, the proposed method is applied to the flow data analysis of population migration in central and eastern China to prove the practical application value of the model. The proposed method is universal and can be generalized to the global spatial autocorrelation analysis of any type of flow data.https://www.mdpi.com/2220-9964/12/10/396spatial flow dataglobal spatial autocorrelationspatial patternspatial statisticgeographical interaction |
| spellingShingle | Shuai Sun Haiping Zhang Flow-Data-Based Global Spatial Autocorrelation Measurements for Evaluating Spatial Interactions ISPRS International Journal of Geo-Information spatial flow data global spatial autocorrelation spatial pattern spatial statistic geographical interaction |
| title | Flow-Data-Based Global Spatial Autocorrelation Measurements for Evaluating Spatial Interactions |
| title_full | Flow-Data-Based Global Spatial Autocorrelation Measurements for Evaluating Spatial Interactions |
| title_fullStr | Flow-Data-Based Global Spatial Autocorrelation Measurements for Evaluating Spatial Interactions |
| title_full_unstemmed | Flow-Data-Based Global Spatial Autocorrelation Measurements for Evaluating Spatial Interactions |
| title_short | Flow-Data-Based Global Spatial Autocorrelation Measurements for Evaluating Spatial Interactions |
| title_sort | flow data based global spatial autocorrelation measurements for evaluating spatial interactions |
| topic | spatial flow data global spatial autocorrelation spatial pattern spatial statistic geographical interaction |
| url | https://www.mdpi.com/2220-9964/12/10/396 |
| work_keys_str_mv | AT shuaisun flowdatabasedglobalspatialautocorrelationmeasurementsforevaluatingspatialinteractions AT haipingzhang flowdatabasedglobalspatialautocorrelationmeasurementsforevaluatingspatialinteractions |