通过异构数据融合降低海面高度的迁移学习增强生成对抗网络

Remote. Sens. Pub Date : 2024-02-22 DOI:10.3390/rs16050763
Qi Zhang, Wenjin Sun, Huaihai Guo, Changming Dong, Hong Zheng
{"title":"通过异构数据融合降低海面高度的迁移学习增强生成对抗网络","authors":"Qi Zhang, Wenjin Sun, Huaihai Guo, Changming Dong, Hong Zheng","doi":"10.3390/rs16050763","DOIUrl":null,"url":null,"abstract":"In recent decades, satellites have played a pivotal role in observing ocean dynamics, providing diverse datasets with varying spatial resolutions. Notably, within these datasets, sea surface height (SSH) data typically exhibit low resolution, while sea surface temperature (SST) data have significantly higher resolution. This study introduces a Transfer Learning-enhanced Generative Adversarial Network (TLGAN) for reconstructing high-resolution SSH fields through the fusion of heterogeneous SST data. In contrast to alternative deep learning approaches that involve directly stacking SSH and SST data as input channels in neural networks, our methodology utilizes bifurcated blocks comprising Residual Dense Module and Residual Feature Distillation Module to extract features from SSH and SST data, respectively. A pixelshuffle module-based upscaling block is then concatenated to map these features into a common latent space. Employing a hybrid strategy involving adversarial training and transfer learning, we overcome the limitation that SST and SSH data should share the same time dimension and achieve significant resolution enhancement in SSH reconstruction. Experimental results demonstrate that, when compared to interpolation method, TLGAN effectively reduces reconstruction errors and fusing SST data could significantly enhance in generating more realistic and physically plausible results.","PeriodicalId":20944,"journal":{"name":"Remote. Sens.","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2024-02-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"A Transfer Learning-Enhanced Generative Adversarial Network for Downscaling Sea Surface Height through Heterogeneous Data Fusion\",\"authors\":\"Qi Zhang, Wenjin Sun, Huaihai Guo, Changming Dong, Hong Zheng\",\"doi\":\"10.3390/rs16050763\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"In recent decades, satellites have played a pivotal role in observing ocean dynamics, providing diverse datasets with varying spatial resolutions. Notably, within these datasets, sea surface height (SSH) data typically exhibit low resolution, while sea surface temperature (SST) data have significantly higher resolution. This study introduces a Transfer Learning-enhanced Generative Adversarial Network (TLGAN) for reconstructing high-resolution SSH fields through the fusion of heterogeneous SST data. In contrast to alternative deep learning approaches that involve directly stacking SSH and SST data as input channels in neural networks, our methodology utilizes bifurcated blocks comprising Residual Dense Module and Residual Feature Distillation Module to extract features from SSH and SST data, respectively. A pixelshuffle module-based upscaling block is then concatenated to map these features into a common latent space. Employing a hybrid strategy involving adversarial training and transfer learning, we overcome the limitation that SST and SSH data should share the same time dimension and achieve significant resolution enhancement in SSH reconstruction. Experimental results demonstrate that, when compared to interpolation method, TLGAN effectively reduces reconstruction errors and fusing SST data could significantly enhance in generating more realistic and physically plausible results.\",\"PeriodicalId\":20944,\"journal\":{\"name\":\"Remote. Sens.\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2024-02-22\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Remote. Sens.\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.3390/rs16050763\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Remote. Sens.","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.3390/rs16050763","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

摘要

近几十年来,卫星在观测海洋动力学方面发挥了关键作用,提供了不同空间分辨率的各种数据集。值得注意的是,在这些数据集中,海面高度(SSH)数据的分辨率通常较低,而海面温度(SST)数据的分辨率则要高得多。本研究介绍了一种迁移学习增强生成对抗网络(TLGAN),用于通过融合异构 SST 数据重建高分辨率 SSH 场。与直接将 SSH 和 SST 数据作为神经网络输入通道进行堆叠的其他深度学习方法不同,我们的方法利用由残差密集模块和残差特征蒸馏模块组成的分叉模块,分别从 SSH 和 SST 数据中提取特征。然后,将基于像素洗牌模块的提升模块连接起来,将这些特征映射到一个共同的潜在空间中。利用对抗训练和迁移学习的混合策略,我们克服了 SST 和 SSH 数据应具有相同时间维度的限制,并显著提高了 SSH 重建的分辨率。实验结果表明,与插值法相比,TLGAN 能有效减少重建误差,融合 SST 数据能显著提高生成更真实、物理上更合理的结果的能力。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
A Transfer Learning-Enhanced Generative Adversarial Network for Downscaling Sea Surface Height through Heterogeneous Data Fusion
In recent decades, satellites have played a pivotal role in observing ocean dynamics, providing diverse datasets with varying spatial resolutions. Notably, within these datasets, sea surface height (SSH) data typically exhibit low resolution, while sea surface temperature (SST) data have significantly higher resolution. This study introduces a Transfer Learning-enhanced Generative Adversarial Network (TLGAN) for reconstructing high-resolution SSH fields through the fusion of heterogeneous SST data. In contrast to alternative deep learning approaches that involve directly stacking SSH and SST data as input channels in neural networks, our methodology utilizes bifurcated blocks comprising Residual Dense Module and Residual Feature Distillation Module to extract features from SSH and SST data, respectively. A pixelshuffle module-based upscaling block is then concatenated to map these features into a common latent space. Employing a hybrid strategy involving adversarial training and transfer learning, we overcome the limitation that SST and SSH data should share the same time dimension and achieve significant resolution enhancement in SSH reconstruction. Experimental results demonstrate that, when compared to interpolation method, TLGAN effectively reduces reconstruction errors and fusing SST data could significantly enhance in generating more realistic and physically plausible results.
求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
自引率
0.00%
发文量
0
期刊最新文献
Influences of Different Factors on Gravity Wave Activity in the Lower Stratosphere of the Indian Region Estimating Sugarcane Aboveground Biomass and Carbon Stock Using the Combined Time Series of Sentinel Data with Machine Learning Algorithms Dynamic Screening Strategy Based on Feature Graphs for UAV Object and Group Re-Identification The Expanding of Proglacial Lake Amplified the Frontal Ablation of Jiongpu Co Glacier since 1985 Investigation of Light-Scattering Properties of Non-Spherical Sea Salt Aerosol Particles at Varying Levels of Relative Humidity
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1