Enhancing Weather Predictions: Super-Resolution via Deep Diffusion Models

被引:1
|
作者
Martinu, Jan Matyas [1 ]
Simanek, Petr [1 ]
机构
[1] Czech Tech Univ, Fac Informat Technol, Prague 16000, Czech Republic
来源
ARTIFICIAL NEURAL NETWORKS AND MACHINE LEARNING-ICANN 2024, PT IX | 2024年 / 15024卷
关键词
Weather modelling; Super-resolution; Denoising diffusion probabilistic models;
D O I
10.1007/978-3-031-72356-8_13
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
This study investigates the application of deep-learning diffusion models for the super-resolution of weather data, a novel approach aimed at enhancing the spatial resolution and detail of meteorological variables. Leveraging the capabilities of diffusion models, specifically the SR3 and ResDiff architectures, we present a methodology for transforming low-resolution weather data into high-resolution outputs. Our experiments, conducted using the WeatherBench dataset, focus on the super-resolution of the two-meter temperature variable, demonstrating the models' ability to generate detailed and accurate weather maps. The results indicate that the ResDiff model, further improved by incorporating physics-based modifications, significantly outperforms traditional SR3 methods in terms of Mean Squared Error (MSE), Structural Similarity Index (SSIM), and Peak Signal-to-Noise Ratio (PSNR). This research highlights the potential of diffusion models in meteorological applications, offering insights into their effectiveness, challenges, and prospects for future advancements in weather prediction and climate analysis.
引用
收藏
页码:186 / 197
页数:12
相关论文
共 50 条
  • [31] Orthoimage Super-Resolution via Deep Convolutional Neural Networks
    Berezovsky, Vladimir
    Bai, Yunfeng
    Sharshov, Ivan
    Aleshko, Roman
    Shoshina, Kseniya
    Vasendina, Irina
    2022 IEEE 20TH INTERNATIONAL CONFERENCE ON INDUSTRIAL INFORMATICS (INDIN), 2022, : 263 - 268
  • [32] Image Super-Resolution via Deep Recursive Residual Network
    Tai, Ying
    Yang, Jian
    Liu, Xiaoming
    30TH IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2017), 2017, : 2790 - 2798
  • [33] A Multi-Scale Deep Back-Projection Backbone for Face Super-Resolution with Diffusion Models
    Gao, Juhao
    Tang, Ni
    Zhang, Dongxiao
    APPLIED SCIENCES-BASEL, 2023, 13 (14):
  • [34] Deep Super-Resolution Network for Single Image Super-Resolution with Realistic Degradations
    Umer, Rao Muhammad
    Foresti, Gian Luca
    Micheloni, Christian
    ICDSC 2019: 13TH INTERNATIONAL CONFERENCE ON DISTRIBUTED SMART CAMERAS, 2019,
  • [35] Structure via super-resolution
    de Souza, Natalie
    NATURE METHODS, 2018, 15 (01) : 30 - 30
  • [36] Structure via super-resolution
    Natalie de Souza
    Nature Methods, 2018, 15 : 30 - 30
  • [37] ACDMSR: Accelerated Conditional Diffusion Models for Single Image Super-Resolution
    Niu, Axi
    Pham, Trung X.
    Zhang, Kang
    Sun, Jinqiu
    Zhu, Yu
    Yan, Qingsen
    Kweon, In So
    Zhang, Yanning
    IEEE TRANSACTIONS ON BROADCASTING, 2024, 70 (02) : 492 - 504
  • [38] Wind speed super-resolution and validation: from ERA5 to CERRA via diffusion models
    Merizzi, Fabio
    Asperti, Andrea
    Colamonaco, Stefano
    Neural Computing and Applications, 2024, 36 (34) : 21899 - 21921
  • [39] Regularized super-resolution for diffusion MRI
    Nedjati-Gilani, Shahrum
    Alexander, Daniel C.
    Parker, Geoff J. M.
    2008 IEEE INTERNATIONAL SYMPOSIUM ON BIOMEDICAL IMAGING: FROM NANO TO MACRO, VOLS 1-4, 2008, : 875 - +
  • [40] Deep Depth Super-Resolution: Learning Depth Super-Resolution Using Deep Convolutional Neural Network
    Song, Xibin
    Dai, Yuchao
    Qin, Xueying
    COMPUTER VISION - ACCV 2016, PT IV, 2017, 10114 : 360 - 376