1.中国地质大学(武汉)地理与信息工程学院,湖北 武汉,430074
2.陕西省建筑职工大学,陕西 西安,710043
3.中铁第四勘察设计院集团有限公司,湖北 武汉,430061
张唯,博士,副教授,主要从事地理信息科学相关研究。weizhang@cug.edu.cn
收稿:2023-05-23,
纸质出版:2025-10-05
移动端阅览
张唯,吉宸佳,李文凯,等.降水融合数据特征驱动下基于GAN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),2025,50(10):2035-2047.
ZHANG Wei,JI Chenjia,LI Wenkai,et al.Spatial Super-Resolution Reconstruction of Remote Sensing Precipitation Products Using GAN by Multi-source Fused Precipitation Data Features[J].Geomatics and Information Science of Wuhan University,2025,50(10):2035-2047.
张唯,吉宸佳,李文凯,等.降水融合数据特征驱动下基于GAN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),2025,50(10):2035-2047. DOI:10.13203/j.whugis20230013
ZHANG Wei,JI Chenjia,LI Wenkai,et al.Spatial Super-Resolution Reconstruction of Remote Sensing Precipitation Products Using GAN by Multi-source Fused Precipitation Data Features[J].Geomatics and Information Science of Wuhan University,2025,50(10):2035-2047. DOI:10.13203/j.whugis20230013
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。充分利用中国智能网格实况分析产品中的降水融合数据(China’s Meteorological Administration (CMA) multi-source precipitation analysis,CMPA)的高空间分辨率(5 km)特征,构建基于生成对抗网络(generative adversarial network,GAN)的两倍超分辨率重建模型,分别应用于全球降水观测计划多卫星集成反演产品(integrated multi-satellite retrievals for GPM,IMERG)日降水数据和第五代欧洲中期数值预报中心大气再分析数据集(The fifth generation ECMWF atmospheric reanalysis,ERA5)日降水数据的空间降尺度,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)所构建的模型能够有效保留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产品的应用效果明显优于EAR5产品。(4)所构建的GAN模型在IMERG日降水数据上的适用性优于多重分形模型和随机森林模型,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3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。
Objectives
2
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
2
We make full use of the high spatial resolution (5 km) feature of the fused precipitation data (China's Meteorological Administration (CMA) multi-source precipitation analysis
CMPA) from the national intelligent grid live analysis product to construct a two sets of super-resolution reconstruction model based on generative adversarial networks(GAN)
which is applied to the spatial downscaling of the integrated multi-satellite retrievals for GPM (IMERG) daily precipitation data and the fifth generation ECMWF atmospheric reanalysis (ERA5) 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
2
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 the correlation coefficient
probability of detection 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 constructed GAN model outperforms the multifractal and random forest 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
2
Therefore
the constructed GAN model is able to provide a more refined precipitation distribution and is of some research value.
张寒博 , 徐勇 , 窦世卿 , 等 . 基于GWR模型的长江流域TRMM数据降尺度 [J]. 水土保持研究 , 2021 , 28 ( 3 ): 149 - 155 .
ZHANG Hanbo , XU Yong , DOU Shiqing , et al . TRMM Downscaling Data of Yangtze Based on GWR Model [J]. Research of Soil and Water Conservation , 2021 , 28 ( 3 ): 149 - 155 .
李国平 , 陈娇娜 , 郝丽萍 . 基于GPS-PWV的不同云系降水个例的综合分析 [J]. 武汉大学学报(信息科学版) , 2011 , 36 ( 4 ): 384 - 388 .
LI Guoping , CHEN Jiaona , HAO Liping . Case Study of the Rainfall Processes in Different Cloud Systems Based on GPS-PWV Data in Chengdu Plain [J]. Geomatics and Information Science of Wuhan University , 2011 , 36 ( 4 ): 384 - 388 .
刘舒雅 , 郑胜杰 , 张唯 . 时序变差函数特征驱动下的月平均降水空间分布模拟 [J]. 武汉大学学报(信息科学版) , 2022 , 47 ( 7 ): 1043 - 1051 .
LIU Shuya , ZHENG Shengjie , ZHANG Wei . Simulation of Spatial Distribution of Monthly Average Precipitation Driven by Temporal Variation Function [J]. Geomatics and Information Science of Wuhan University , 2022 , 47 ( 7 ): 1043 - 1051 .
DUAN Z , LIU J Z , TUO Y , et al . Evaluation of Eight High Spatial Resolution Gridded Precipitation Products in Adige Basin (Italy) at Multiple Temporal and Spatial Scales [J]. Science of the Total Environment , 2016 , 573 : 1536 - 1553 .
LI Z , YANG D W , GAO B , et al . Multiscale Hydrologic Applications of the Latest Satellite Precipitation Products in the Yangtze River Basin Using a Distributed Hydrologic Model [J]. Journal of Hydrometeorology , 2015 , 16 ( 1 ): 407 - 426 .
唐国强 . 卫星遥感降水在全球及典型区域的检验、应用和改进 [D]. 北京 : 清华大学 , 2019 .
TANG Guoqiang . Validation, Application and Improvement of Satellite Remote Sensing Precipitation in the Globe and Typical Regions [D]. Beijing : Tsinghua University , 2019 .
HU Q F , LI Z , WANG L Z , et al . Rainfall Spatial Estimations: A Review from Spatial Interpolation to Multi-source Data Merging [J]. Water , 2019 , 11 ( 3 ): 579 .
汤秋鸿 , 张学君 , 戚友存 , 等 . 遥感陆地水循环的进展与展望 [J]. 武汉大学学报(信息科学版) , 2018 , 43 ( 12 ): 1872 - 1884 .
TANG Qiuhong , ZHANG Xuejun , QI Youcun , et al . Remote Sensing of the Terrestrial Water Cycle: Progress and Perspectives [J]. Geomatics and Information Science of Wuhan University , 2018 , 43 ( 12 ): 1872 - 1884 .
JOYCE R J , JANOWIAK J E , ARKIN P A , et al . CMORPH: A Method that Produces Global Precipitation Estimates from Passive Microwave and Infrared Data at High Spatial and Temporal Resolution [J]. Journal of Hydrometeorology , 2004 , 5 ( 3 ): 487 - 503 .
MANTAS V M , LIU Z , CARO C , et al . Validation of TRMM Multi-satellite Precipitation Analysis (TMPA) Products in the Peruvian Andes [J]. Atmospheric Research , 2015 , 163 : 132 - 145 .
ADLER R F , HUFFMAN G J , CHANG A , et al . The Version-2 Global Precipitation Climatology Project (GPCP) Monthly Precipitation Analysis (1979-Present) [J]. Journal of Hydrometeorology , 2003 , 4 ( 6 ): 1147 - 1167 .
TANG G Q , WAN W , ZENG Z Y , et al . An Overview of the Global Precipitation Measurement(GPM)Mission and It's Latest Development [J]. Remote Sensing Technology and Application , 2015 , 30 ( 4 ): 607 - 615 .
王彧蓉 , 周建中 , 杨鑫 , 等 . 再分析降水资料的适用性评估与偏差校正: 以长江中下游地区为例 [J]. 人民长江 , 2021 , 52 ( 9 ): 93 - 100 .
WANG Yurong , ZHOU Jianzhong , YANG Xin , et al . Applicability Evaluation and Deviation Correction of Reanalysis Precipitation Data: Case of Middle and Lower Reaches of Changjiang River [J]. Yangtze River , 2021 , 52 ( 9 ): 93 - 100 .
史岚 , 何其全 , 杨娇 , 等 . 闽浙赣地区GPM IMERG降水产品降尺度建模与比较分析 [J]. 地球信息科学学报 , 2019 , 21 ( 10 ): 1642 - 1652 .
SHI Lan , HE Qiquan , YANG Jiao , et al . Downscaling Modeling of the GPM IMERG Precipitation Product and Comparative Analysis in the Fujian-Zhejiang-Jiangxi Region [J]. Journal of Geo-Information Science , 2019 , 21 ( 10 ): 1642 - 1652 .
WRIGHT D B , KNUTSON T R , SMITH J A . Regional Climate Model Projections of Rainfall from U.S. Landfalling Tropical Cyclones [J]. Climate Dynamics , 2015 , 45 ( 11 ): 3365 - 3379 .
CHEN F R , LIU Y , LIU Q , et al . Spatial Downscaling of TRMM 3B43 Precipitation Considering Spatial Heterogeneity [J]. International Journal of Remote Sensing , 2014 , 35 ( 9 ): 3074 - 3093 .
WANG M M , HE G J , ZHANG Z M , et al . Comparison of Spatial Interpolation and Regression Analysis Models for an Estimation of Monthly Near Surface Air Temperature in China [J]. Remote Sensing , 2017 , 9 ( 12 ): 1278 .
ZHAN C S , HAN J , HU S , et al . Spatial Downscaling of GPM Annual and Monthly Precipitation Using Regression-Based Algorithms in a Mountainous Area [J]. Advances in Meteorology , 2018 , 2018 ( 1 ): 1506017 .
MA Z Q , HE K , TAN X , et al . Comparisons of Spatially Downscaling TMPA and IMERG over the Tibetan Plateau [J]. Remote Sensing , 2018 , 10 ( 12 ): 1883 .
程建新 . 基于深度学习超分辨率的气象预报系统研究 [D]. 武汉 : 武汉大学 , 2021 .
CHENG Jianxin . Research on Meteorological Forecast System Based on Deep Learning Super Resolution [D]. Wuhan : Wuhan University , 2021 .
JIANG Y Z , YANG K , SHAO C K , et al . A Downscaling Approach for Constructing High-Resolution Precipitation Dataset over the Tibetan Plateau from ERA5 Reanalysis [J]. Atmospheric Research , 2021 , 256 : 105574 .
VANDAL T , KODRA E , GANGULY S , et al . Deepsd: Generating High Resolution Climate Change Projections Through Single Image Super-Resolution [C]// The 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining , Halifax, NS, Canada, 2017 .
师春香 , 谷军霞 , 韩帅 , 等 . 全国智能网格实况融合分析产品进展 [C]// 第35届中国气象学会年会 , 中国合肥 , 2018 .
SHI Chunxiang , GU Junxia , HAN Shuai , et al . Advances in National Intelligent Grid Live Fusion Analysis Products [C]// The 35th Annual Meeting of the Chinese Meteorological Society , Hefei, China , 2018 .
卢新玉 . 融合多源遥感数据与地面观测的新疆地区降水量估算方法研究 [D]. 南京 : 南京信息工程大学 , 2019 .
LU Xinyu . Merging Method of Precipitation based on Multi-source Remote Sensing Data and Ground Observation in Xinjiang [D]. Nanjing : Nanjing University of Information Science and Technology , 2019 .
许智铭 , 王正涛 . 联合GRACE和水文数据探测松花江流域地下水时空变化 [J]. 武汉大学学报(信息科学版) , 2023 , 48 ( 9 ): 1409 - 1415 .
XU Zhiming , WANG Zhengtao . Detect Songhua River Basin Groundwater Spatiotemporal Variation Characteristics by GRACE and Multi-source Hydrological Data [J]. Geomatics and Information Science of Wuhan University , 2023 , 48 ( 9 ): 1409 - 1415 .
CHEN F R , GAO Y Q , WANG Y G , et al . Downscaling Satellite-Derived Daily Precipitation Products with an Integrated Framework [J]. International Journal of Climatology , 2019 , 39 ( 3 ): 1287 - 1304 .
GEMITZI A , KOUTSIAS N , LAKSHMI V . A Spatial Downscaling Methodology for GRACE Total Water Storage Anomalies Using GPM IMERG Precipitation Estimates [J]. Remote Sensing , 2021 , 13 ( 24 ): 5149 .
叶梦姝 . 中国大气再分析资料降水产品在天气和气候中的适用性研究 [D]. 兰州 : 兰州大学 , 2018 .
YE Mengshu . Reasearch on the Applicability of Precipitation Reanalysis Data in CRA-Interim of Climate and Weather Characters in China [D]. Lanzhou : Lanzhou University , 2018 .
鹿璇 , 汪鼎文 , 石文轩 . 利用在线字典学习实现图像超分辨率重建的算法 [J]. 武汉大学学报(信息科学版) , 2018 , 43 ( 5 ): 719 - 725 .
LU Xuan , WANG Dingwen , SHI Wenxuan . Image Super-Resolution with On-Line Dictionary Learning [J]. Geomatics and Information Science of Wuhan University , 2018 , 43 ( 5 ): 719 - 725 .
陈行 , 罗斌 . 利用动态上采样滤波深度网络进行多角度遥感影像超分辨率重建 [J]. 武汉大学学报(信息科学版) , 2021 , 46 ( 11 ): 1716 - 1726 .
CHEN Hang , LUO Bin . Multi-angle Remote Sensing Images Super-Resolution Reconstruction Using Dynamic Upsampling Filter Deep Network [J]. Geomatics and Information Science of Wuhan University , 2021 , 46 ( 11 ): 1716 - 1726 .
DONG C , LOY C C , HE K M , et al . Image Super-Resolution Using Deep Convolutional Networks [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence , 2016 , 38 ( 2 ): 295 - 307 .
GOODFELLOW I , POUGET-ABADIE J , MIRZA M , et al . Generative Adversarial Nets [C]// The 28th International Conference on Neural Information Processing Systems , Bali, Indonesia , 2022 .
陆川伟 , 孙群 , 赵云鹏 , 等 . 一种基于条件生成式对抗网络的道路提取方法 [J]. 武汉大学学报(信息科学版) , 2021 , 46 ( 6 ): 807 - 815 .
LU Chuanwei , SUN Qun , ZHAO Yunpeng , et al . A Road Extraction Method Based on Conditional Generative Adversarial Nets [J]. Geomatics and Information Science of Wuhan University , 2021 , 46 ( 6 ): 807 - 815 .
宇如聪 , 李建 , 陈昊明 , 等 . 中国降水日变化 [M]. 北京 : 科学出版社 , 2021 : 148 - 149 .
YU Rucong , LI Jian , CHEN Haoming , et al . Daily Variation of Precipitation in China [M]. Beijing : Scien‑ce Press , 2021 : 148 - 149 .
谭伟伟 . 长江经济带卫星遥感降水数据空间降尺度研究 [D]. 武汉 : 武汉大学 , 2020 .
TAN Weiwei . Spatial Downscaling of Satellite-Based Precipitation Data over the Yangtze River Economic Belt [D]. Wuhan : Wuhan University , 2020 .
0
浏览量
0
下载量
0
CSCD
关联资源
相关文章
相关作者
相关机构
京公网安备11010802024621