Convolutional Neural Network Modelling for MODIS Land Surface Temperature Super-Resolution
This work addresses the need for higher-resolution LST data for applications such as agricultural monitoring, but it is incremental as it modifies an existing U-Net architecture for a specific domain.
The paper tackles the problem of low spatial resolution in MODIS Land Surface Temperature (LST) data, which limits fine-scale analysis in heterogeneous environments like agricultural parcels, by introducing a Multi-residual U-Net deep learning algorithm that super-resolves images from 1km to 250m per pixel and outperforms other state-of-the-art methods.
Nowadays, thermal infrared satellite remote sensors enable to extract very interesting information at large scale, in particular Land Surface Temperature (LST). However such data are limited in spatial and/or temporal resolutions which prevents from an analysis at fine scales. For example, MODIS satellite provides daily acquisitions with 1Km spatial resolutions which is not sufficient to deal with highly heterogeneous environments as agricultural parcels. Therefore, image super-resolution is a crucial task to better exploit MODIS LSTs. This issue is tackled in this paper. We introduce a deep learning-based algorithm, named Multi-residual U-Net, for super-resolution of MODIS LST single-images. Our proposed network is a modified version of U-Net architecture, which aims at super-resolving the input LST image from 1Km to 250m per pixel. The results show that our Multi-residual U-Net outperforms other state-of-the-art methods.