张唯, 吉宸佳, 李文凯, 孙晓娜, 梁天欣, 韩松洁, 卫鸿飞. 降水融合数据特征驱动下基于生成对抗网络的遥感降水产品空间超分辨率重建[J]. 武汉大学学报 ( 信息科学版). DOI: 10.13203/j.whugis20230013
引用本文: 张唯, 吉宸佳, 李文凯, 孙晓娜, 梁天欣, 韩松洁, 卫鸿飞. 降水融合数据特征驱动下基于生成对抗网络的遥感降水产品空间超分辨率重建[J]. 武汉大学学报 ( 信息科学版). DOI: 10.13203/j.whugis20230013
Zhang Wei, Ji Chenjia, Li Wenkai, Sun Xiaona, Liang Tianxin, Han Songjie, Wei Hongfei. Spatial Super-Resolution Reconstruction of Remote Sensing Precipitation Products Using Generative Adversarial Network by Multi-Source Fused Precipitation Data Features[J]. Geomatics and Information Science of Wuhan University. DOI: 10.13203/j.whugis20230013
Citation: Zhang Wei, Ji Chenjia, Li Wenkai, Sun Xiaona, Liang Tianxin, Han Songjie, Wei Hongfei. Spatial Super-Resolution Reconstruction of Remote Sensing Precipitation Products Using Generative Adversarial Network by Multi-Source Fused Precipitation Data Features[J]. Geomatics and Information Science of Wuhan University. DOI: 10.13203/j.whugis20230013

降水融合数据特征驱动下基于生成对抗网络的遥感降水产品空间超分辨率重建

Spatial Super-Resolution Reconstruction of Remote Sensing Precipitation Products Using Generative Adversarial Network by Multi-Source Fused Precipitation Data Features

  • 摘要: 高分辨率降水资料是研究区域尺度水和能量循环的重要基础数据之一,但现有降水产品的空间分辨率尚无法满足区域精细化研究的需要。本文充分利用全国智能网格实况分析产品中的降水融合数据(CMPA)的高空间分辨率(5 km)特征,构建基于生成对抗神经网络的两倍超分辨率重建模型,分别应用于IMERG(The Integrated Multi-satellite Retrievals forGPM)日降水数据和ERA5(The fifth generation ECMWF atmospheric reanalysis)日降水再分析资料的空间降尺度,得到高分辨率的IMERG日降水产品(0.05°)和ERA5日降水产品(0.125°),并使用实测气象站点数据对降尺度后的两种数据进行精度评价。结果表明:(1)基于CMPA的超分辨率重建模型能够用于其他降水产品的空间降尺度。重建后的IMERG和ERA5产品的各项精度指标均有不同程度的提升。(2)模型能够有效保留CMPA数据的基本数据特征。重建后的IMERG产品和ERA5产品在相似性、命中率和偏差方面都更贴合CMPA数据,整体准确性更高。(3)模型重建效果受原始数据的空间分辨率、精度以及与CMPA数据的相关性等因素的影响。原始空间分辨率和精度越高,与训练数据集的相关性越好,降尺度效果也更佳。因而,IMERG产品上的应用效果明显优于EAR5产品。(4)本文构建的GAN模型在IMERG日降水数据上的适用性优于MF和RF模型,细节重建效果更好。相较于原始的IMERG数据,GAN重建后的日降水在年、季、月三个时间维度上的精度统计结果大多有所改善,模型稳定性较强。

     

    Abstract: Objectives: High-resolution precipitation data is one of the important basic data for studying water and energy cycles at regional scales, but the spatial resolution of existing precipitation products cannot yet meet the needs of regional refinement studies. Methods: This paper makes full use of the high spatial resolution (5 km) feature of the fused precipitation data (CMPA) from the National Intelligent Grid Live Analysis product to construct a two sets of superresolution reconstruction model based on Generative Adversarial Networks, which is applied to the spatial downscaling of the IMERG (The Integrated Multi-satellite Retrievals for GPM) daily precipitation data and ERA5 (The fifth generation ECMWF atmospheric reanalysis) daily precipitation reanalysis data, respectively. The final high-resolution IMERG daily precipitation product (0.05°) and ERA5 daily precipitation product (0.125°) were obtained and the accuracy of both downscaled data was evaluated using measured meteorological station data. Results: The results show that (1) The super-resolution reconstruction model based on CMPA data can be used for spatial downscaling of other precipitation products. The reconstructed IMERG products and ERA5 products show different degrees of improvement in all accuracy indicators. (2) The model is able to effectively retain the essential data characteristics of the CMPA data. The reconstructed IMERG product and ERA5 product are more closely matched to the CMPA data in terms of CC, POD and Bias, with higher overall accuracy. (3) The effect of model reconstruction is influenced by the spatial resolution and accuracy of the original data, as well as the correlation between the original data and the CMPA data. The higher the spatial resolution and accuracy of the raw data, the better the correlation between the raw data and the training data set, and the better the downscaling effect. As a result, the application on the IMERG product is significantly better than the EAR5 product. (4) The GAN model constructed in this paper outperforms the MF and RF models in terms of applicability to IMERG daily precipitation data, and its detailed reconstruction is better. Compared with the original IMERG data, the accuracy statistics of the GAN reconstructed daily precipitation in the three time dimensions of year, season and month are mostly improved, which indicates better model stability. Conclusions: Therefore, the GAN model constructed in this paper is able to provide a more refined precipitation distribution and is of some research value.

     

/

返回文章
返回