Fig 1.
Framework of STH-Trans model, from the multi-source data as fundamental input (bottom of the entire framework) to the spatiotemporal views adjustment (top of the framework).
Fig 2.
Multi spatiotemporal perspective adjustment.
Fig 3.
Distance from target watershed (Shi Shi as the example) to all selected stations.
(The figure was generated by Python with basemap toolkit. The map source and license are accessible from https://github.com/matplotlib/basemap.).
Fig 4.
Distance from target watershed (Shi Shi as the example) to all selected stations.
Fig 5.
Geometric distance from target watershed (Shi Shi as the example) to all selected stations.
Fig 6.
Topographic index distance between target watershed and all stations.
Table 1.
Station topographic index.
Fig 7.
Comprehensive geographical distance between target watershed and all stations.
Fig 8.
Selected source basins used in the transfer learning (in red triangles) after filtering out stations with missing data.
(The figure was generated by Python with basemap toolkit. The map source and license are accessible from https://github.com/matplotlib/basemap.).
Fig 9.
Daily runoff of Shi Shi and Shang Gao in 2008.
Fig 10.
Annual rainfall map of Jiangxi Province.
(The figure was generated by Python with basemap toolkit. The map source and license are accessible from https://github.com/matplotlib/basemap.).
Fig 11.
Digital elevation map of Jiangxi Province.
(The red triangles refer to all stations within 100 km from the target basin (indicated as the black triangle). The figure was generated by Python with basemap toolkit. The map source and license are accessible from https://github.com/matplotlib/basemap.).
Table 2.
Altitude and distance between each station and target station.
Fig 12.
Vegetation coverage over the surrounding area of Jiangxi Province.
(The red triangles refer to all stations within 100km from the target basin (indicated as the black triangle).) (The figure was generated by Python with basemap toolkit. The map source and license are accessible from https://github.com/matplotlib/basemap.).
Table 3.
Watershed area, watershed length and vegetation coverage of each station.
Fig 13.
Influence of parameter b in the model.
Fig 14.
Influence of parameter a in the model.
Fig 15.
Initial model prediction results.
Fig 16.
Results of Trans and H-Trans model.
Fig 17.
Results of ST-Trans model and STH-Trans model.
Fig 18.
Model results with temporal features.
Fig 19.
Results of CoH-Trans model and STH-Trans model.
Table 4.
Comparison of various transfer models from different perspectives.
Table 5.
Comparison of transfer model results of one flood process.