A bivariate spatio-temporal association analysis method for aggregated flows

doi:10.11947/j.AGCS.2025.20240011

Abstract

Abstract:

Aggregated flows can reflect the spatio-temporal interactions between different spatial areas from the group perspective, and often contain non-spatial attributes that describe quantitative characteristics, such as the migratory intensity of population flows. Analyzing the spatio-temporal association between two non-spatial attributes of aggregated flows can reveal the interaction patterns between different flow attributes, which helps to understand the intrinsic occurrence mechanisms of dynamic interaction phenomena in geographic space. However, there is still a lack of spatio-temporal statistical indicators to evaluate the association degree between two flow attributes, and the understanding of the asymmetry and spatio-temporal heterogeneity of the association remains inadequate. Therefore, this paper proposes a bivariate spatio-temporal association analysis method for aggregated flows. It establishes spatio-temporal weights for aggregated flows to express their spatio-temporal adjacency relationships. Then, it constructs the global and local bivariate flow spatio-temporal Moran's I to assess the asymmetric spatio-temporal association degree between two flow attributes, and identify the local spatio-temporal association patterns and their dynamic variations. The synthetic test results verify that the method can effectively uncover the global and local spatio-temporal association patterns between two flow attributes, and the appropriate scale of spatio-temporal association analysis is also identified through parameter sensitivity tests. The practical application results reveal the spatio-temporal associations between intercity search behavior and travel activities in Shandong, which can provide a theoretical basis for in-depth analysis of urban attractiveness from virtual and real perspectives.

Key words: aggregated flow, spatio-temporal association, bivariate spatio-temporal Moran's I, spatio-temporal weight

CLC Number:

P208

Qingyang FU, Mengjie ZHOU, Yige LI, Weitao CHEN. A bivariate spatio-temporal association analysis method for aggregated flows[J]. Acta Geodaetica et Cartographica Sinica, 2025, 54(3): 552-562.

Figures/Tables 9

Fig. 1

Fig. 2

Fig. 3

Tab. 1

Fig. 4

Fig. 5

Tab. 2

Fig. 6

Tab. 3

References 34

[1]	刘瑜, 姚欣, 龚咏喜, 等. 大数据时代的空间交互分析方法和应用再论[J]. 地理学报, 2020, 75(7): 1523-1538.
	LIU Yu, YAO Xin, GONG Yongxi, et al. Analytical methods and applications of spatial interactions in the era of big data[J]. Acta Geographica Sinica, 2020, 75(7): 1523-1538.
[2]	裴韬, 舒华, 郭思慧, 等. 地理流的空间模式：概念与分类[J]. 地球信息科学学报, 2020, 22(1): 30-40.
	PEI Tao, SHU Hua, GUO Sihui, et al. The concept and classification of spatial patterns of geographical flow[J]. Journal of Geo-Information Science, 2020, 22(1): 30-40.
[3]	刘耀林, 陈龙, 安子豪, 等. 基于公交刷卡数据的武汉市职住通勤特征研究[J]. 经济地理, 2019, 39(2): 93-102.
	LIU Yaolin, CHEN Long, AN Zihao, et al. Research on job-housing and commuting in Wuhan based on bus smart card data[J]. Economic Geography, 2019, 39(2): 93-102.
[4]	BAUER S, HOYEB J. Migratory animals couple biodiversity and ecosystem functioning worldwide[J]. Science, 2014, 344(6179): 1242552.
[5]	石岩, 王达, 陈袁芳, 等. 流空间邻近关系约束下的流行病分布空间异常探测方法[J]. 测绘学报, 2021, 50(6): 777-788. DOI:. doi: 10.11947/j.AGCS.2021.20200350
	SHI Yan, WANG Da, CHEN Yuanfang, et al. An anomaly detection approach from spatio distributions of epidemic based on adjacency constraints in flow space[J]. Acta Geodaetica et Cartographica Sinica, 2021, 50(6): 777-788. DOI:. doi: 10.11947/j.AGCS.2021.20200350
[6]	秦昆, 喻雪松, 周扬, 等. 全球尺度地理多元流的网络化挖掘及关联分析研究[J]. 地球信息科学学报, 2022, 24(10): 1911-1924.
	QIN Kun, YU Xuesong, ZHOU Yang, et al. Networked mining and association analysis of geographical multiple flows at a global scale[J]. Journal of Geo-Information Science, 2022, 24(10): 1911-1924.
[7]	TAO R, THILL J C. Spatial cluster detection in spatial flow data[J]. Geographical Analysis, 2016, 48(4): 355-372.
[8]	董超, 修春亮, 魏冶. 基于通信流的吉林省流空间网络格局[J]. 地理学报, 2014, 69(4): 510-519.
	DONG Chao, XIU Chunliang, WEI Ye. Network structure of ‘space of flows’ in Jilin province based on telecommunication flows[J]. Acta Geographica Sinica, 2014, 69(4): 510-519.
[9]	ABEL GUY J, COHEN JOEL E. Bilateral international migration flow estimates updated and refined by sex[J]. Scientific Data, 2022, 9(1): 173.
[10]	TAO R, THILL J-C. Flow cross K-function: a bivariate flow analytical method[J]. International Journal of Geographical Information Science, 2019, 33(10): 2055-2071.
[11]	ZHANG W, ZHAO J, LIU W, et al. Geographically weighted flow cross K-function for network-constrained flow data[J]. Applied Sciences, 2022, 12(24): 12796.
[12]	ZHOU M, YANG M, CHEN Z. Flow colocation quotient: measuring bivariate spatial association for flow data[J]. Computers, Environment and Urban Systems, 2023, 99: 101916.
[13]	ZHANG H, ZHOU X, TANG G, et al. Detecting colocation flow patterns in the geographical interaction data[J]. Geographical Analysis, 2022, 54(1): 84-103.
[14]	CAI J, KWAN M-P. Discovering co-location patterns in multivariate spatial flow data[J]. International Journal of Geographical Information Science, 2022, 36(4): 720-748.
[15]	TAO Ran, THILL J C. BiFlowLISA: measuring spatial association for bivariate flow data[J]. Computers, Environment and Urban Systems, 2020, 83: 101519.
[16]	LIU Q, YANG J, DENG M, et al. BiFlowAMOEBA for the identification of arbitrarily shaped clusters in bivariate flow data[J]. International Journal of Geographical Information Science, 2022, 36(9): 1784-1808.
[17]	XU Y, ZHANG H, LI Z, et al. Integration of migration and attention flow data to reveal association of virtual-real dual intercity network structure[J]. Cities, 2023, 143: 104614.
[18]	马丽亚, 修春亮, 冯兴华. 多元流视角下东北城市网络特征分析[J]. 经济地理, 2019, 39(8): 51-58.
	MA Liya, XIU Chunliang, FENG Xinghua. Analysis of network characteristics of northeast cities from the perspective of multi-flow[J]. Economic Geography, 2019, 39(8): 51-58.
[19]	周梦杰, 阳孟杰, 陈慧颖, 等. 面向地理流的时空交叉K函数方法[J]. 测绘学报, 2024, 53(8): 1644-1655. DOI:. doi: 10.11947/j.AGCS.2024.20230258
	ZHOU Mengjie, YANG Mengjie, CHEN Huiying, et al. Spatio-temporal cross K-function for geographical flows[J]. Acta Geodaetica et Cartographica Sinica, 2024, 53(8): 1644-1655. DOI:. doi: 10.11947/j.AGCS.2024.20230258
[20]	王钰辉, 阳孟杰, 周梦杰, 等. 面向地理流的双变量时空扫描统计方法[J]. 测绘科学, 2024, 49(1): 204-215.
	WANG Yuhui, YANG Mengjie, ZHOU Mengjie, et al. A bivariate spatiotemporal scan statistics method for geographical flows[J]. Science of Surveying and Mapping, 2024, 49(1): 204-215.
[21]	TAO R, CHEN Y, THILL J-C. A space-time flow LISA approach for panel flow data[J]. Computers, Environment and Urban Systems, 2023, 106: 102042.
[22]	FU Q, ZHOU M, LI Y, et al. Flow spatio-temporal Moran's I: measuring the spatio-temporal autocorrelation of flow data[J]. Geographical Analysis, 2024, 56(4): 799-824.
[23]	SHI Y, DENG M, XUEXI Y, et al. Detecting anomalies in spatio-temporal flow data by constructing dynamic neighbourhoods[J]. Computers, Environment and Urban Systems, 2018, 67: 80-96.
[24]	ZHANG H, ZHOU X, YE X, et al. Strength-weighted flow cluster method considering spatiotemporal contiguity to reveal interregional association patterns[J]. GIScience & Remote Sensing, 2023, 60(1): 2252923.
[25]	HILL JASON M, RENFREW ROSALIND B. Migratory patterns and connectivity of two North American grassland bird species[J]. Ecology and Evolution, 2019, 9(1): 680-692.
[26]	LIU X, PEI T, WANG X, et al. Travel flow patterns of diverse population groups and influencing built environment factors: a case study of Beijing[J]. Cities, 2024, 151: 105096.
[27]	DUBÉ J, LEGROS D. A spatio-temporal measure of spatial dependence: an example using real estate data[J]. Papers in Regional Science, 2011, 92: 19-30.
[28]	LEE J, LI S. Extending Moran's index for measuring spatiotemporal clustering of geographic events[J]. Geographical Analysis, 2017, 49(1): 36-57.
[29]	WANG Z, LAM N S. Extending getis-ord statistics to account for local space-time autocorrelation in spatial panel data[J]. The Professional Geographer, 2020, 72(3): 411-420.
[30]	DACEY M. A review on measures of contiguity for two and K-color maps[M]. Evanston: Department of Geography, Northwestern University, 1965: 31-32.
[31]	CLIFF A D, ORD J K. Spatial autocorrelation[M]. London: Pion, 1973: 173-176.
[32]	ROGERSON P, YAMADA I. Statistical detection and surveillance of geographic clusters[M]. New York: Boca Raton, Chapman & Hall/CRC, 2008: 32-57.
[33]	ANSELIN L, SYABRI I, SMIRNOV O. Visualizing multivariate spatial correlation with dynamically linked windows[C]//Proceedings of 2002 CSISS Workshop on New Tools for Spatial Data Analysis. Santa Barbara: Citeseer, 2002: 1-19.
[34]	CHEN Y, GONG Z, MA Q, et al. Exploring the spatiotemporal relationships between search flows and travel flows[J]. Transactions in GIS, 2023, 27(5): 1338-1356.

局部聚合流	t₁₀	t₂₀
F₁	HH聚类	LH异常
F₂	LL聚类	HH聚类
F₃	LH异常	HL异常
F₄	HL异常	LL聚类

全局结果	时间阈值
全局结果	1	2	3	4	5	6	7
BiFSTI^出行	0.247	0.244	0.241	0.238	0.236	0.234	0.232
BiFSTI^搜索	0.243	0.234	0.229	0.225	0.223	0.221	0.219
BiSTI^出行起点	0.435	0.429	0.423	0.418	0.414	0.410	0.407
BiSTI^搜索起点	0.412	0.393	0.381	0.372	0.366	0.361	0.357
BiSTI^出行终点	0.304	0.299	0.293	0.287	0.283	0.279	0.275
BiSTI^搜索终点	0.285	0.270	0.260	0.253	0.248	0.244	0.240

城际流	起点的局部双变量时空莫兰指数			终点的局部双变量时空莫兰指数
城际流	城市	日期	局部时空关联模式	城市	日期	局部时空关联模式
出行流	济南	2023-04-29	HH聚类	淄博	2023-04-29	HH聚类
	青岛	2023-04-29		淄博	2023-04-30
	青岛	2023-04-30		济南	2023-04-30
	烟台	2023-04-11	LH异常	威海	2023-04-14	LH异常
	烟台	2023-04-18		威海	2023-04-26
	烟台	2023-04-25		威海	2023-04-27
搜索流	青岛	2023-04-29	HH聚类	淄博	2023-04-28	HH聚类
	青岛	2023-04-30		淄博	2023-04-29
	济南	2023-04-30		淄博	2023-04-30
	泰安	2023-04-02	LH异常	泰安	2023-03-19	LH异常
	泰安	2023-04-30		泰安	2023-04-08
	日照	2023-04-30		德州	2023-04-30