Downscaling MODIS spectral bands using deep learning

MODIS sensors are widely used in a broad range of environmental studies, many of which involve joint analysis of multiple MODIS spectral bands acquired at disparate spatial resolutions. To extract land surface information from multi-resolution MODIS spectral bands, existing studies often downscale lower resolution (LR) bands to match the higher resolution (HR) bands based on simple interpolation or more advanced statistical modeling. Statistical downscaling methods rely on the functional relationship between the LR spectral bands and HR spatial information, which may vary across different land surface types, making statistical downscaling methods less robust. In this paper, we propose an alternative approach based on deep learning to downscale 500 m and 1000 m spectral bands of MODIS to 250 m without additional spatial information. We employ a superresolution architecture based on an encoder decoder network. This deep learning-based method uses a custom loss function and a self-attention layer to preserve local and global spatial relationships of the predictions. We compare our approach with a statistical method specifically developed for downscaling MODIS spectral bands, an interpolation method widely used for downscaling multi-resolution spectral bands, and a deep learning superresolution architecture previously used for downscaling satellite imagery. Results show that our deep learning method outperforms on almost all spectral bands both quantitatively and qualitatively. In particular, our deep learning-based method performs very well on the thermal bands due to the larger scale difference between the input and target resolution. This study demonstrates that our proposed deep learning-based downscaling method can maintain the spatial and spectral fidelity of satellite images and contribute to the integration and enhancement of multi-resolution satellite imagery.

Automated summary

MODIS sensors are widely used in environmental studies and many involve joint analysis of multiple spectral bands acquired at different spatial resolutions. This paper presents a deep learning-based method to downscale MODIS 500m and 1000m spectral bands to 250m without additional spatial information, outperforming statistical and interpolation methods in both quantitative and qualitative terms. The deep learning approach shows particularly strong performance on thermal bands due to the larger scale difference between input and target resolutions.