Figures & data
Figure 1. The study area and the spatial distribution of metro stations in the main urban area of Wuhan.
![Figure 1. The study area and the spatial distribution of metro stations in the main urban area of Wuhan.](/cms/asset/9d8b26e0-4143-4f83-943e-e84529e3d38c/tgsi_a_2137857_f0001_c.jpg)
Table 1. Example of users’ records.
Figure 3. (a) Schematic diagram of inside flow, inflow, and outflow of a station; (b) Workday rhythm of and the corresponding spectrum diagrams of FFT; (c) Schematic diagram of convergence-divergence during a day.
![Figure 3. (a) Schematic diagram of inside flow, inflow, and outflow of a station; (b) Workday rhythm of ftotal and the corresponding spectrum diagrams of FFT; (c) Schematic diagram of convergence-divergence during a day.](/cms/asset/d41f3148-fe31-41f7-9549-eab9eeb19f5a/tgsi_a_2137857_f0003_c.jpg)
Table 2. Factors and collinearity diagnosis.
Figure 4. Illustration of DTW distance: (a) Optimal path (black) between time series (red) and time series
(blue); (b) a distance matrix showing the process of finding the optimal path and the DTW distance is the sum of distances (orange).
![Figure 4. Illustration of DTW distance: (a) Optimal path (black) between time series S1 (red) and time series S2 (blue); (b) a distance matrix showing the process of finding the optimal path and the DTW distance is the sum of distances (orange).](/cms/asset/a06c3713-a57f-4e72-92c1-98fae288ee60/tgsi_a_2137857_f0004_c.jpg)
Figure 5. SSE and silhouette for different numbers of clusters (a) on weekdays (the elbow is at 6.) and (b) on weekends (the elbow is at 4.).
![Figure 5. SSE and silhouette for different numbers of clusters (a) on weekdays (the elbow is at 6.) and (b) on weekends (the elbow is at 4.).](/cms/asset/709e9cdc-f921-4ed1-aeaa-45e8db201956/tgsi_a_2137857_f0005_c.jpg)
Table 3. Usage patterns for weekdays and weekends.
Figure 6. Metro station distribution of different patterns and corresponding hourly profiles of (black) and
(red) on weekdays.
![Figure 6. Metro station distribution of different patterns and corresponding hourly profiles of ftotal (black) and fnet (red) on weekdays.](/cms/asset/47a54188-fea6-4d25-b027-9a75e51b1742/tgsi_a_2137857_f0006_c.jpg)
Figure 8. Metro station distribution of different patterns and corresponding hourly profiles of (black) and
(red) on weekends.
![Figure 8. Metro station distribution of different patterns and corresponding hourly profiles of ftotal (black) and fnet (red) on weekends.](/cms/asset/142358c5-5064-4661-8600-b72b556a0e23/tgsi_a_2137857_f0008_c.jpg)
Table 4. Relative importance of variables.
Figure 10. Nonlinear associations between the top five key variables and usage patterns on weekdays.
![Figure 10. Nonlinear associations between the top five key variables and usage patterns on weekdays.](/cms/asset/2d9beb38-a3af-4c28-a749-2a3d54cad58b/tgsi_a_2137857_f0010_c.jpg)
Data availability statement
Restrictions apply to the availability of these data. The data are not publicly available due to Mobike’s contract and privacy policy.