Attention-driven and multi-scale feature integrated approach for earth surface temperature data reconstruction

Zhang, Minghui; Chen, Yunjie; Yang, Fan; Qin, Zhengkun

doi:10.5194/gmd-19-73-2026

Articles | Volume 19, issue 1

https://doi.org/10.5194/gmd-19-73-2026

© Author(s) 2026. This work is distributed under
the Creative Commons Attribution 4.0 License.

https://doi.org/10.5194/gmd-19-73-2026

© Author(s) 2026. This work is distributed under
the Creative Commons Attribution 4.0 License.

Articles | Volume 19, issue 1

Development and technical paper

|

06 Jan 2026

Development and technical paper |

| 06 Jan 2026

Attention-driven and multi-scale feature integrated approach for earth surface temperature data reconstruction

Minghui Zhang, Yunjie Chen, Fan Yang, and Zhengkun Qin

Data sets

Attention-Driven and Multi-Scale Feature Integrated Approach for Earth Surface Temperature Data Reconstruction——FY-3D Minghui Zhang https://doi.org/10.5281/zenodo.15734212

Attention-Driven and Multi-Scale Feature Integrated Approach for Earth Surface Temperature Data Reconstruction——ERA5 Minghui Zhang https://doi.org/10.5281/zenodo.15734414

Model code and software

Attention-Driven and Multi-Scale Feature Integrated Approach for Earth Surface Temperature Data Reconstruction Minghui Zhang https://doi.org/10.5281/zenodo.15273464

Short summary

Considering the crucial role of high-resolution surface observation temperature data in the study of surface atmospheric temperature in Marine areas, we propose a new two-stage deep learning model. This model is used to fill in the ocean surface temperature data that is missing in satellite observations due to the orbital gap of polar-orbiting satellites.