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.
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.
the Creative Commons Attribution 4.0 License.
Attention-driven and multi-scale feature integrated approach for earth surface temperature data reconstruction
Minghui Zhang
School of Mathematics and Statistics, Nanjing University of Information Science and Technology, Nanjing 210044, China
Yunjie Chen
CORRESPONDING AUTHOR
School of Mathematics and Statistics, Nanjing University of Information Science and Technology, Nanjing 210044, China
Fan Yang
School of Mathematics and Statistics, Nanjing University of Information Science and Technology, Nanjing 210044, China
Zhengkun Qin
School of Atmospheric Sciences, Nanjing University of information Science and Technology, Nanjing 210044, China
Related authors
No articles found.
Bing Zhang, Mingjian Zeng, Anning Huang, Zhengkun Qin, Couhua Liu, Wenru Shi, Xin Li, Kefeng Zhu, Chunlei Gu, and Jialing Zhou
Geosci. Model Dev., 17, 4579–4601, https://doi.org/10.5194/gmd-17-4579-2024, https://doi.org/10.5194/gmd-17-4579-2024, 2024
Short summary
Short summary
By directly analyzing the proximity of precipitation forecasts and observations, a precipitation accuracy score (PAS) method was constructed. This method does not utilize a traditional contingency-table-based classification verification; however, it can replace the threat score (TS), equitable threat score (ETS), and other skill score methods, and it can be used to calculate the accuracy of numerical models or quantitative precipitation forecasts.
Cited articles
Atlas, D., Srivastava, R., and Sekhon, R. S.: Doppler radar characteristics of precipitation at vertical incidence, Reviews of Geophysics, 11, 1–35, https://doi.org/10.1029/RG011i001p00001, 1973. a
Ballester, C., Bertalmio, M., Caselles, V., Sapiro, G., and Verdera, J.: Filling-in by joint interpolation of vector fields and gray levels, IEEE transactions on image processing, 10, 1200–1211, https://doi.org/10.1109/83.935036, 2001. a
Barnes, C., Shechtman, E., Finkelstein, A., and Goldman, D. B.: PatchMatch: A randomized correspondence algorithm for structural image editing, ACM Trans. Graph., 28, 24, https://doi.org/10.1145/1531326.1531330, 2009. a
Berman, D., Treibitz, T., and Avidan, S.: Non-local image dehazing, in: Proceedings of the IEEE conference on computer vision and pattern recognition, 1674–1682, https://doi.org/10.1109/CVPR.2016.185, 2016. a
Criminisi, A., Pérez, P., and Toyama, K.: Region filling and object removal by exemplar-based image inpainting, IEEE Transactions on image processing, 13, 1200–1212, https://doi.org/10.1109/TIP.2004.833105, 2004. a
Cui, J., Zhang, M., Song, D., Shan, X., and Wang, B.: MODIS land surface temperature product reconstruction based on the SSA-BiLSTM model, Remote Sensing, 14, 958, https://doi.org/10.3390/rs14040958, 2022. a
Deng, Y., Hui, S., Zhou, S., Meng, D., and Wang, J.: Learning contextual transformer network for image inpainting, in: Proceedings of the 29th ACM international conference on multimedia, 2529–2538, https://doi.org/10.1145/3474085.3475426, 2021. a
Deo, R. C. and Şahin, M.: Forecasting long-term global solar radiation with an ANN algorithm coupled with satellite-derived (MODIS) land surface temperature (LST) for regional locations in Queensland, Renewable and Sustainable Energy Reviews, 72, 828–848, https://doi.org/10.1016/j.rser.2017.01.114, 2017. a
Dosovitskiy, A.: An image is worth 16x16 words: Transformers for image recognition at scale, arXiv [preprint], https://doi.org/10.48550/arXiv.2010.11929, 2020. a
Dowd, P. A. and Pardo-Igúzquiza, E.: The many forms of co-kriging: A diversity of multivariate spatial estimators, Mathematical Geosciences, 56, 387–413, https://doi.org/10.1007/s11004-023-10104-7, 2024. a
Elharrouss, O., Almaadeed, N., Al-Maadeed, S., and Akbari, Y.: Image inpainting: A review, Neural Processing Letters, 51, 2007–2028, https://doi.org/10.1007/s11063-019-10163-0, 2020. a
Fleit, G.: Windowed anisotropic local inverse distance-weighted (WALID) interpolation method for riverbed mapping, Acta Geophysica, 1–15, https://doi.org/10.1007/s11600-024-01510-4, 2024. a
Geiss, A. and Hardin, J. C.: Inpainting radar missing data regions with deep learning, Atmos. Meas. Tech., 14, 7729–7747, https://doi.org/10.5194/amt-14-7729-2021, 2021. a
Gulrajani, I., Ahmed, F., Arjovsky, M., Dumoulin, V., and Courville, A. C.: Improved training of wasserstein gans, arXiv [preprint], https://doi.org/10.48550/arXiv.1704.00028, 2017. a
He, K., Zhang, X., Ren, S., and Sun, J.: Deep residual learning for image recognition, in: Proceedings of the IEEE conference on computer vision and pattern recognition, 770–778, https://doi.org/10.1109/CVPR.2016.90, 2016. a
Hore, A. and Ziou, D.: Image quality metrics: PSNR vs. SSIM, in: 2010 20th international conference on pattern recognition, IEEE, 2366–2369, https://doi.org/10.1109/ICPR.2010.579, 2010. a
Iizuka, S., Simo-Serra, E., and Ishikawa, H.: Globally and locally consistent image completion, ACM Transactions on Graphics (ToG), 36, 1–14, https://doi.org/10.1145/3072959.3073659, 2017. a, b
Johnson, J., Alahi, A., and Fei-Fei, L.: Perceptual losses for real-time style transfer and super-resolution, in: Computer Vision–ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, 11–14 October 2016, Proceedings, Part II 14, Springer, 694–711, https://doi.org/10.1007/978-3-319-46475-6_43, 2016. a
Kilibarda, M., Hengl, T., Heuvelink, G. B., Gräler, B., Pebesma, E., Perčec Tadić, M., and Bajat, B.: Spatio-temporal interpolation of daily temperatures for global land areas at 1 km resolution, Journal of Geophysical Research: Atmospheres, 119, 2294–2313, https://doi.org/10.1002/2013JD020803, 2014. a, b
King, M. D., Platnick, S., Menzel, W. P., Ackerman, S. A., and Hubanks, P. A.: Spatial and temporal distribution of clouds observed by MODIS onboard the Terra and Aqua satellites, IEEE transactions on geoscience and remote sensing, 51, 3826–3852, https://doi.org/10.1109/TGRS.2012.2227333, 2013. a
Lei Ba, J., Kiros, J. R., and Hinton, G. E.: Layer normalization, arXiv [preprint], https://doi.org/10.48550/arXiv.1607.06450, 2016. a
Lengfeld, K., Kirstetter, P.-E., Fowler, H. J., Yu, J., Becker, A., Flamig, Z., and Gourley, J.: Use of radar data for characterizing extreme precipitation at fine scales and short durations, Environmental Research Letters, 15, 085003, https://doi.org/10.1088/1748-9326/ab98b4, 2020. a
Lepetit, P., Ly, C., Barthès, L., Mallet, C., Viltard, N., Lemaitre, Y., and Rottner, L.: Using deep learning for restoration of precipitation echoes in radar data, IEEE Transactions on Geoscience and Remote Sensing, 60, 1–14, https://doi.org/10.1109/TGRS.2021.3052582, 2021. a
Li, J. and Heap, A. D.: Spatial interpolation methods applied in the environmental sciences: A review, Environmental Modelling & Software, 53, 173–189, https://doi.org/10.1016/j.envsoft.2013.12.008, 2014. a
Li, X., Shen, H., Zhang, L., Zhang, H., Yuan, Q., and Yang, G.: Recovering quantitative remote sensing products contaminated by thick clouds and shadows using multitemporal dictionary learning, IEEE Transactions on Geoscience and Remote Sensing, 52, 7086–7098, https://doi.org/10.1109/TGRS.2014.2307354, 2014. a
Liu, G., Reda, F. A., Shih, K. J., Wang, T.-C., Tao, A., and Catanzaro, B.: Image inpainting for irregular holes using partial convolutions, in: Proceedings of the European conference on computer vision (ECCV), 85–100, https://doi.org/10.1007/978-3-030-01252-6_6, 2018. a, b, c, d
Liu, H., Jiang, B., Song, Y., Huang, W., and Yang, C.: Rethinking image inpainting via a mutual encoder-decoder with feature equalizations, in: Computer Vision–ECCV 2020: 16th European Conference, Glasgow, UK, August 23–28, 2020, Proceedings, Part II 16, Springer, 725–741, https://doi.org/10.1007/978-3-030-58536-5_43, 2020. a
Liu, Z., Wu, P., Duan, S., Zhan, W., Ma, X., and Wu, Y.: Spatiotemporal reconstruction of land surface temperature derived from fengyun geostationary satellite data, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 10, 4531–4543, https://doi.org/10.1109/JSTARS.2017.2716376, 2017. a
Malek, S., Melgani, F., Bazi, Y., and Alajlan, N.: Reconstructing cloud-contaminated multispectral images with contextualized autoencoder neural networks, IEEE Transactions on Geoscience and Remote Sensing, 56, 2270–2282, https://doi.org/10.1109/TGRS.2017.2777886, 2017. a
Mirza, M. and Osindero, S.: Conditional generative adversarial nets, arXiv preprint arXiv:1411.1784, 2014. a
Mohanasundaram, S., Baghel, T., Thakur, V., Udmale, P., and Shrestha, S.: Reconstructing NDVI and land surface temperature for cloud cover pixels of Landsat-8 images for assessing vegetation health index in the Northeast region of Thailand, Environmental monitoring and assessment, 195, 211, https://doi.org/10.1007/s10661-022-10802-5, 2023. a
Pathak, D., Krahenbuhl, P., Donahue, J., Darrell, T., and Efros, A. A.: Context encoders: Feature learning by inpainting, in: Proceedings of the IEEE conference on computer vision and pattern recognition, 2536–2544, https://doi.org/10.1109/CVPR.2016.278, 2016. a
Petrovska, B., Zdravevski, E., Lameski, P., Corizzo, R., Štajduhar, I., and Lerga, J.: Deep learning for feature extraction in remote sensing: A case-study of aerial scene classification, Sensors, 20, 3906, https://doi.org/10.3390/s20143906, 2020. a
Ronneberger, O., Fischer, P., and Brox, T.: U-net: Convolutional networks for biomedical image segmentation, in: Medical image computing and computer-assisted intervention–MICCAI 2015: 18th international conference, Munich, Germany, 5–9 October 2015, proceedings, part III 18, Springer International Publishing, 234–241, https://doi.org/10.1007/978-3-319-24574-4_28, 2015. a
Saharia, C., Chan, W., Chang, H., Lee, C., Ho, J., Salimans, T., Fleet, D., and Norouzi, M.: Palette: Image-to-image diffusion models, in: ACM SIGGRAPH 2022 conference proceedings, 1–10, https://doi.org/10.1145/3528233.3530757, 2022. a, b, c, d
Scharlemann, J. P., Benz, D., Hay, S. I., Purse, B. V., Tatem, A. J., Wint, G. W., and Rogers, D. J.: Global data for ecology and epidemiology: a novel algorithm for temporal Fourier processing MODIS data, PloS one, 3, e1408, https://doi.org/10.1371/journal.pone.0001408, 2008. a
Simonyan, K.: Very deep convolutional networks for large-scale image recognition, arXiv [preprint], https://doi.org/10.48550/arXiv.1409.1556, 2014. a
Tan, S. and Chen, H.: A conditional generative adversarial network for weather radar beam blockage correction, IEEE Transactions on Geoscience and Remote Sensing, 61, 1–14, https://doi.org/10.1109/TGRS.2023.3286181, 2023. a
Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, L. U., and Polosukhin, I.: Attention is all you need, arXiv [preprint], https://doi.org/10.48550/arXiv.1706.03762, 2017. a, b, c
Wan, Z., Zhang, J., Chen, D., and Liao, J.: High-fidelity pluralistic image completion with transformers, in: Proceedings of the IEEE/CVF international conference on computer vision, 4692–4701, https://doi.org/10.1109/ICCV48922.2021.00465, 2021. a
Wang, P., Zheng, W., Chen, T., and Wang, Z.: Anti-oversmoothing in deep vision transformers via the fourier domain analysis: From theory to practice, arXiv [preprint], https://doi.org/10.48550/arXiv.2203.05962, 2022. a
Wang, X., Girshick, R., Gupta, A., and He, K.: Non-local neural networks, in: Proceedings of the IEEE conference on computer vision and pattern recognition, 7794–7803, https://doi.org/10.1109/CVPR.2018.00813, 2018. a
Wang, Y., Karimi, H. A., and Jia, X.: Reconstruction of Continuous High-Resolution Sea Surface Temperature Data Using Time-Aware Implicit Neural Representation, Remote Sensing, 15, 5646, https://doi.org/10.3390/rs15245646, 2023. a
Weiss, D. J., Mappin, B., Dalrymple, U., Bhatt, S., Cameron, E., Hay, S. I., and Gething, P. W.: Re-examining environmental correlates of Plasmodium falciparum malaria endemicity: a data-intensive variable selection approach, Malaria journal, 14, 1–18, https://doi.org/10.1186/s12936-015-0574-x, 2015. a
Wu, H., Xiao, B., Codella, N., Liu, M., Dai, X., Yuan, L., and Zhang, L.: Cvt: Introducing convolutions to vision transformers, in: Proceedings of the IEEE/CVF international conference on computer vision, 22–31, https://doi.org/10.1109/ICCV48922.2021.00009, 2021. a
Xie, C., Liu, S., Li, C., Cheng, M.-M., Zuo, W., Liu, X., Wen, S., and Ding, E.: Image inpainting with learnable bidirectional attention maps, in: Proceedings of the IEEE/CVF international conference on computer vision, 8858–8867, https://doi.org/10.1109/ICCV.2019.00895, 2019. a
Xie, E., Wang, W., Yu, Z., Anandkumar, A., Alvarez, J. M., and Luo, P.: SegFormer: Simple and efficient design for semantic segmentation with transformers, arXiv [preprint], https://doi.org/10.48550/arXiv.2105.15203, 2021. a
Xie, L., Zhao, Q., Huo, J., and Cheng, G.: A ground penetrating radar data reconstruction method based on generation networks, in: 2020 IEEE Radar Conference (RadarConf20), IEEE, 1–4, https://doi.org/10.1109/RadarConf2043947.2020.9266648, 2020. a
Xu, S., Wang, D., Liang, S., Liu, Y., and Jia, A.: Assessment of gridded datasets of various near surface temperature variables over Heihe River Basin: Uncertainties, spatial heterogeneity and clear-sky bias, International Journal of Applied Earth Observation and Geoinformation, 120, 103347, https://doi.org/10.1016/j.jag.2023.103347, 2023. a
Yan, Z., Li, X., Li, M., Zuo, W., and Shan, S.: Shift-net: Image inpainting via deep feature rearrangement, in: Proceedings of the European conference on computer vision (ECCV), 1–17, https://doi.org/10.1007/978-3-030-01264-9_1, 2018. a
Yi, Z., Tang, Q., Azizi, S., Jang, D., and Xu, Z.: Contextual residual aggregation for ultra high-resolution image inpainting, in: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, 7508–7517, https://doi.org/10.1109/CVPR42600.2020.00753, 2020. a
Yu, J., Lin, Z., Yang, J., Shen, X., Lu, X., and Huang, T. S.: Generative image inpainting with contextual attention, in: Proceedings of the IEEE conference on computer vision and pattern recognition, 5505–5514, https://doi.org/10.1109/CVPR.2018.00577, 2018. a
Yu, Y., Zhan, F., Wu, R., Pan, J., Cui, K., Lu, S., Ma, F., Xie, X., and Miao, C.: Diverse image inpainting with bidirectional and autoregressive transformers, in: Proceedings of the 29th ACM International Conference on Multimedia, 69–78, https://doi.org/10.1145/3474085.3475436, 2021. a
Zeng, Y., Fu, J., Chao, H., and Guo, B.: Learning pyramid-context encoder network for high-quality image inpainting, in: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, 1486–1494, https://doi.org/10.1109/CVPR.2019.00158, 2019. a
Zhang, G., Xiao, X., Dong, J., Kou, W., Jin, C., Qin, Y., Zhou, Y., Wang, J., Menarguez, M. A., and Biradar, C.: Mapping paddy rice planting areas through time series analysis of MODIS land surface temperature and vegetation index data, ISPRS Journal of Photogrammetry and Remote Sensing, 106, 157–171, https://doi.org/10.1016/j.isprsjprs.2015.05.011, 2015. a
Zhang, M., Chen, Y., Yang, F., and Qin, Z.: Attention-Driven and Multi-Scale Feature Integrated Approach for Earth Surface Temperature Data Reconstruction, Zenodo [code], https://doi.org/10.5281/zenodo.15273464, 2025a. a
Zhang, M., Chen, Y., Yang, F., and Qin, Z.: Attention-Driven and Multi-Scale Feature Integrated Approach for Earth Surface Temperature Data Reconstruction – ERA5, Zenodo [data set], https://doi.org/10.5281/zenodo.15734414, 2025b. a
Zhang, M., Chen, Y., Yang, F., and Qin, Z.: Attention-Driven and Multi-Scale Feature Integrated Approach for Earth Surface Temperature Data Reconstruction – FY-3D, Zenodo [data set], https://doi.org/10.5281/zenodo.15734212, 2025c. a
Zhao, S., Cui, J., Sheng, Y., Dong, Y., Liang, X., Chang, E. I., and Xu, Y.: Large scale image completion via co-modulated generative adversarial networks, arXiv [preprint], https://doi.org/10.48550/arXiv.2103.10428, 2021. a
Zhou, J., Liang, S., Cheng, J., Wang, Y., and Ma, J.: The GLASS land surface temperature product, IEEE Journal of selected topics in applied earth observations and remote sensing, 12, 493–507, https://doi.org/10.1109/JSTARS.2018.2870130, 2018. a
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.
Considering the crucial role of high-resolution surface observation temperature data in the...