A Spatiotemporal Consistency-Guided Global–Local Fusion Network for All-Weather LST Reconstruction

Land surface temperature (LST) serves as a key indicator for studying the thermal characteristics of the land–atmosphere interface. Nevertheless, cloud cover and atmospheric particulates frequently obstruct the thermal infrared (TIR) spectral range in satellite observations, leading to significant data missing in derived LST products. Multisource data fusion methods are the most effective means for all-weather TIR LST reconstruction. However, most of the existing multisource data fusion reconstruction methods only consider the spatial and temporal differences individually, which makes it challenging to ensure spatiotemporal consistency in LST gap-filling. In this study, a novel framework for LST reconstruction is proposed by constructing a spatio-temporal consistency-guided global–local fusion network (STCGL-Net) to fuse TIR and reanalysis data. Using a deep convolutional network architecture, the STCGL-Net efficiently captures the local spatial features and texture details of multisource observations. At the same time, spatiotemporal consistency transformer and coordinate attention mechanisms are cleverly embedded to capture the global spatiotemporal dependencies that drive changes in LST. Using spatiotemporal consistency as the core physical constraint to guide the STCGL-Net’s training process ensures that the reconstructed LST is not only numerically accurate but also evolves in accordance with physical laws. As a key input parameter, ERA5 surface net solar radiation (SSR) data quantitatively characterize solar forcing on land surface thermal dynamics and enhance LST reconstruction accuracy. Evaluation demonstrates that STCGL-Net achieves cloud-contaminated LST reconstruction with $R^{2} =0.87$ and mean absolute error (MAE) = 0.54 K. Comparative evaluations with three established classic methods confirm the STCGL-Net’s consistent performance across various spatial and temporal scales. Validation against surface radiation budget station LST confirms reconstruction robustness ( $R^{2}$ : 0.8–0.9, MAE: 3–5 K), establishing reliable all-weather LST generation capability.