Hyperspectral Vision Transformers for Greenhouse Gas Estimations from Space
This work addresses the problem of limited spatial and temporal coverage in hyperspectral imaging for atmospheric monitoring, offering an incremental improvement by combining multispectral and hyperspectral strengths.
The study tackled the trade-off between spectral resolution and coverage in greenhouse gas monitoring by proposing a spectral transformer model that synthesizes hyperspectral data from multispectral inputs, resulting in improved GHG prediction accuracy compared to using multispectral data alone.
Hyperspectral imaging provides detailed spectral information and holds significant potential for monitoring of greenhouse gases (GHGs). However, its application is constrained by limited spatial coverage and infrequent revisit times. In contrast, multispectral imaging offers broader spatial and temporal coverage but often lacks the spectral detail that can enhance GHG detection. To address these challenges, this study proposes a spectral transformer model that synthesizes hyperspectral data from multispectral inputs. The model is pre-trained via a band-wise masked autoencoder and subsequently fine-tuned on spatio-temporally aligned multispectral-hyperspectral image pairs. The resulting synthetic hyperspectral data retain the spatial and temporal benefits of multispectral imagery and improve GHG prediction accuracy relative to using multispectral data alone. This approach effectively bridges the trade-off between spectral resolution and coverage, highlighting its potential to advance atmospheric monitoring by combining the strengths of hyperspectral and multispectral systems with self-supervised deep learning.