Abstract
Providing reliable and accurate high-resolution meteorological data is very significant to guide the rapid response to extreme weather conditions. However, due to the constraints of computing power and simulation time, the spatial resolution of existing all global climate models is low, and it is unable to provide meteorological data with more precise resolution at local scale. In this research, a deep learning downscaling model called two-stage multi-scale feature extraction network (TSMFN) is proposed. By combining ERA5 reanalysis data and terrain data, spatial downscaling of global precipitation measurement mission precipitation data is carried out. Specifically, in the first stage of the network, several multi-scale residual Inception blocks are used to extract multi-scale features of low-resolution precipitation data; several residual-based residual multi-scale cross blocks are used to fully excavate multi-scale features after the fusion of multiple data. In the second stage of the TSMFN, the output feature map after the fusion of the previous stage is fused with the high-resolution monthly average precipitation data, and several progressive multistage Swin Transformer blocks are constructed to overcome the problems that the reconstructed image of a general convolutional neural network is smooth and cannot reflect the real spatial distribution of precipitation. Finally, a hybrid loss function combining \(L_{1}\) loss function and focal frequency loss function is proposed to alleviate the ill-posedness of the downscaling. By comparing the proposed algorithm with some advanced deep learning downscaling algorithms, the results of the experiment show that the TSMFN model is significantly better in terms of generated image quality and multiple evaluation indexes, and the model has stronger generalization ability.
Similar content being viewed by others
Data availability
All the data used can be downloaded from the official websites provided in the paper, and the processing code of relevant data can be obtained by contacting the author.
References
Karl, T.R., Trenberth, K.E.: Modern global climate change. Science 302(5651), 1719–1723 (2003)
Liu, Y., Ganguly, A.R., Dy, J.: Climate downscaling using YNet: A deep convolutional network with skip connections and fusion. In: Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining. pp. 3145–3153 (2020)
Misra, V., Dirmeyer, P.A., Kirtman, B.P.: Dynamic downscaling of seasonal simulations over South America. J. Clim. 16(1), 103–117 (2003)
Vandal, T., Kodra, E., Ganguly, S., et al.: DeepSD: Generating high resolution climate change projections through single image super-resolution. In: Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery & Data Mining. pp. 1663–1672 (2017)
Kim, J., Lee, M., Han, H., et al.: Case study: aevelopment of the CNN model considering teleconnection for spatial downscaling of precipitation in a climate change scenario. Sustainability. 14(8), 4719 (2022)
Cheng, W.C., Shi, X.K., Zhang, W.J., et al.: An NWP precipitation products downscaling method based on deep learning. J. Trop. Meteorol. 36, 307–316 (2020)
Wu, Y., Zhang, Z., Crabbe, M.J.C., et al.: Statistical learning-based spatial downscaling models for precipitation distribution. Adv. Meteorol. (2022). https://doi.org/10.1155/2022/3140872
Sathianarayanan, M., Hsu, P.H.: Spatial downscaling of Gpm imerg v06 gridded precipitation using machine learning algorithms. Int. Arch. Photogramm. Remote. Sens. Spat. Inf. Sci. 48, 327–332 (2023)
Muqi, Z., Xinyu, W., Yun, B., et al.: Statistical downscaled climate projection dataset for China using artificial neural network. Beijing Da Xue Xue Bao. 58(2), 221–233 (2022)
Sulaiman, N.A., Shaharudin, S.M., Zainuddin, N.H., et al.: Improving support vector machine rainfall classification accuracy based on Kernel parameters optimization for statistical downscaling approach. Int. J. (2020). https://doi.org/10.30534/ijatcse/2020/9191.42020
Yu, F.C., Zhu, S.Y., Zhang, G.X., et al.: A downscaling method for land surface air temperature of ERA5 reanalysis dataset under complex terrain conditions in mountainous areas. J. Geo-inf. Sci. 24(4), 750–765 (2022)
Lu, Z., Chen, Y.: Single image super-resolution based on a modified U-net with mixed gradient loss. Signal Image Video Proc. 16, 1–9 (2022)
Accarino, G., Chiarelli, M., Immorlano, F., et al.: MSG-GAN-SD: a multi-scale gradients GAN for statistical downscaling of 2-meter temperature over the EURO-CORDEX domain. AI. 2(4), 600–620 (2021)
Fang, J., Lin, H., Chen, X., et al.: A hybrid network of cnn and transformer for lightweight image super-resolution. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. pp. 1103–1112 (2022)
Höhlein, K., Kern, M., Hewson, T., et al.: A comparative study of convolutional neural network models for wind field downscaling. Meteorol. Appl. 27(6), e1961 (2020)
Wang, X., Chan, K.C.K., Yu, K., et al.: EDVR: Video restoration with enhanced deformable convolutional networks. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops. pp. 0–0 (2019)
Dong, C., Loy, C.C., He, K., et al.: Learning a deep convolutional network for image super-resolution. In: Computer Vision–ECCV 2014: 13th European Conference, Zurich, Switzerland, September 6–12, 2014, Proceedings, Part IV 13. Springer International Publishing. pp. 184–199 (2014)
Kim, J., Lee, J.K., Lee, K.M.: Accurate image super-resolution using very deep convolutional networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp. 1646–1654 (2016)
Lai, W.S., Huang, J.B., Ahuja, N., et al.: Deep laplacian pyramid networks for fast and accurate super-resolution. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp. 624–632 (2017)
Lim, B., Son, S., Kim, H., et al.: Enhanced deep residual networks for single image super-resolution. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp.136–144 (2017)
Tong, T., Li, G., Liu, X., et al.: Image super-resolution using dense skip connections. In: Proceedings of the IEEE International Conference on Computer Vision. pp. 4799–4807 (2017)
Li, J., Fang, F., Mei, K., et al.: Multi-scale residual network for image super-resolution. In: Proceedings of the European Conference on Computer Vision (ECCV). pp. 517–532 (2018)
Zhang, Y., Li, K., Li, K., et al.: Image super-resolution using very deep residual channel attention networks. In: Proceedings of the European Conference on Computer Vision (ECCV). pp. 286–301 (2018)
Fang, F., Li, J., Zeng, T.: Soft-edge assisted network for single image super-resolution. IEEE Trans. Image Process. 29, 4656–4668 (2020)
Li, J., Fang, F., Li, J., et al.: MDCN: Multi-scale dense cross network for image super-resolution. IEEE Trans. Circuits Syst. Video Technol. 31(7), 2547–2561 (2020)
Mei, Y., Fan, Y., Zhou, Y.: Image super-resolution with non-local sparse attention. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. pp. 3517–3526 (2021)
Chen, J., Huang, D., Zhu, X., et al.: Gradient-guided and multi-scale feature network for image super-resolution. Appl. Sci. 12(6), 2935 (2022)
Liang, J., Cao, J., Sun, G., et al.: SwinIR: Image Restoration Using Swin Transformer. In: 2021 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW). IEEE, pp. 1833–1844 (2021)
Cheng, J., Kuang, Q., Shen, C., et al.: ResLap: generating high-resolution climate prediction through image super-resolution. IEEE Access. 8, 39623–39634 (2020)
Sha, Y., Gagne, D.J., II., West, G., et al.: Deep-learning-based gridded downscaling of surface meteorological variables in complex terrain. Part II: Daily precipitation. J. Appl. Meteorol. Climatol. 59(12), 2075–2092 (2020)
Sharma, S.C.M., Mitra, A.: ResDeepD: a residual super-resolution network for deep downscaling of daily precipitation over India. Environ. Data Sci. 1, e19 (2022)
Harilal, N., Singh, M., Bhatia, U.: Augmented convolutional LSTMs for generation of high-resolution climate change projections. IEEE Access. 9, 25208–25218 (2021)
Wang, J., Liu, Z., Foster, I., et al.: Fast and accurate learned multiresolution dynamical downscaling for precipitation. Geosci. Model Dev. 14(10), 6355–6372 (2021)
Kumar, B., Atey, K., Singh, B.B., et al.: On the modern deep learning approaches for precipitation downscaling. Earth Sci. Inf. 16, 1–14 (2023)
Xiang, L., Xiang, J., Guan, J., et al.: A novel reference-based and gradient-guided deep learning model for daily precipitation downscaling. Atmosphere 13(4), 511 (2022)
Singh, M., Acharya, N., Jamshidi, S., et al.: DownScaleBench for developing and applying a deep learning based urban climate downscaling-first results for high-resolution urban precipitation climatology over Austin, Texas. Comput. Urban Sci. 3(1), 22 (2023)
Huffman, G.J., Bolvin, D.T., Braithwaite, D., et al.: Integrated multi-satellite retrievals for the global precipitation measurement (GPM) mission (IMERG). Satell. Precip. Meas. 1, 343–353 (2020)
Hersbach, H., Bell, B., Berrisford, P., et al.: The ERA5 global reanalysis. Q. J. R. Meteorol. Soc. 146(730), 1999–2049 (2020)
Shi, W., Caballero, J., Huszár, F., et al.: Real-time single image and video super-resolution using an efficient sub-pixel convolutional neural network. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp. 1874–1883 (2016)
Vaswani, A., Shazeer, N., Parmar, N., et al.: Attention is all you need]. Adv. Neural Inf. Proc. Syst. pp.30 (2017)
Liu, Z., Lin, Y., Cao, Y., et al.: Swin transformer: Hierarchical vision transformer using shifted windows. In: Proceedings of the IEEE/CVF International Conference on Computer Vision. pp. 10012–10022 (2021)
Jiang, L., Dai, B., Wu, W., et al.: Focal frequency loss for image reconstruction and synthesis. In: Proceedings of the IEEE/CVF International Conference on Computer Vision. pp. 13919–13929 (2021)
Zhu, X., Hu, H., Lin, S., et al.: Deformable convnets v2: More deformable, better results. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. pp. 9308–9316 (2019)
Maggioni, V., Meyers, P.C., Robinson, M.D.: A review of merged high-resolution satellite precipitation product accuracy during the tropical rainfall measuring mission (TRMM) era. J. Hydrometeorol. 17(4), 1101–1117 (2016)
Ji, Y., Sun, X., Xu, Y., et al.: Summer regional pentad extreme precipitation in eastern China and their possible causes. Front. Earth Sci. 8, 598025 (2021)
Zhou, K., Sun, J., Zheng, Y., et al.: Quantitative precipitation forecast experiment based on basic NWP variables using deep learning. Adv. Atmos. Sci. 39(9), 1472–1486 (2022)
Chen, H., Qin, H., Dai, Y.: FC-ZSM: spatiotemporal downscaling of rain radar data using feature constrained zooming slow-mo network. Front. Earth Sci. 10, 756 (2022)
Cai, R., Ding, Y., Lu, H.: FreqNet: A frequency-domain image super-resolution network with dicrete cosine transform. arXiv preprint arXiv. pp. 2111.10800, (2021)
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
We declare that we have no conflict of interest with anyone and any institution.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Lei, W., Qin, H., Hou, X. et al. A two-stage model for spatial downscaling of daily precipitation data. Vis Comput (2024). https://doi.org/10.1007/s00371-023-03236-8
Accepted:
Published:
DOI: https://doi.org/10.1007/s00371-023-03236-8