arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2511.18521cs.LGastro-ph.EPastro-ph.IM
收藏

超光谱变分自编码器用于联合数据压缩和成分提取

Hyperspectral Variational Autoencoders for Joint Data Compression and Component Extraction

Core Francisco Park 1,2,3,4(Core Francisco Park 团队);Manuel Pérez-Carrasco 3(Manuel Pérez-Carrasco 团队);Caroline Nowlan 3(Caroline Nowlan 团队);Cecilia Garraffo 3,4(Cecilia Garraffo 团队)

Core Francisco Park, Manuel Perez-Carrasco, Caroline Nowlan, Cecilia Garraffo

AI总结:

本文提出基于变分自编码器的超光谱数据压缩与成分提取方法,实现数据压缩的同时保留大气信息,解决地球观测系统的关键瓶颈。

摘要:

静止轨道超光谱卫星每天产生数TB的数据,给存储、传输和向科学界分发造成重大挑战。我们提出了一种变分自编码器(VAE)方法,实现了对NASA TEMPO卫星超光谱观测(1028个通道,290-490nm)的x514压缩,其重建误差比信号在所有波长上低1-2个数量级。这种大幅的数据体积减少使卫星观测的存档和分享变得高效,同时保持了光谱保真度。除了压缩,我们还探讨压缩潜在空间中保留了多少大气信息,通过训练线性和非线性探针提取Level-2产品(NO2、O3、HCHO、云分数)。云分数和总臭氧分别达到强提取性能(R²=0.93和0.81),尽管这些代表相对简单的检索,因为它们有明显的光谱特征。相比之下,对流层痕量气体的提取面临真正的挑战(NO2 R²=0.20,HCHO R²=0.51),反映它们较弱的信号和复杂的大气相互作用。关键的是,我们发现VAE以半线性的方式编码大气信息——非线性探针显著优于线性探针——并且训练期间显式的潜在监督提供最小的改进,揭示了某些产品根本的编码挑战。这项工作表明,神经压缩可以大幅减少超光谱数据体积,同时保留关键的大气信号,解决下一代地球观测系统的关键瓶颈。代码 - https://github.com/cfpark00/Hyperspectral-VAE

英文摘要:

Geostationary hyperspectral satellites generate terabytes of data daily, creating critical challenges for storage, transmission, and distribution to the scientific community. We present a variational autoencoder (VAE) approach that achieves x514 compression of NASA's TEMPO satellite hyperspectral observations (1028 channels, 290-490nm) with reconstruction errors 1-2 orders of magnitude below the signal across all wavelengths. This dramatic data volume reduction enables efficient archival and sharing of satellite observations while preserving spectral fidelity. Beyond compression, we investigate to what extent atmospheric information is retained in the compressed latent space by training linear and nonlinear probes to extract Level-2 products (NO2, O3, HCHO, cloud fraction). Cloud fraction and total ozone achieve strong extraction performance (R^2 = 0.93 and 0.81 respectively), though these represent relatively straightforward retrievals given their distinct spectral signatures. In contrast, tropospheric trace gases pose genuine challenges for extraction (NO2 R^2 = 0.20, HCHO R^2 = 0.51) reflecting their weaker signals and complex atmospheric interactions. Critically, we find the VAE encodes atmospheric information in a semi-linear manner - nonlinear probes substantially outperform linear ones - and that explicit latent supervision during training provides minimal improvement, revealing fundamental encoding challenges for certain products. This work demonstrates that neural compression can dramatically reduce hyperspectral data volumes while preserving key atmospheric signals, addressing a critical bottleneck for next-generation Earth observation systems. Code - https://github.com/cfpark00/Hyperspectral-VAE

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑