Land Surface Temperature Super-Resolution With a Scale-Invariance-Free Neural Approach: Application to MODIS

Due to the tradeoff between the temporal and spatial resolution of thermal spaceborne sensors, super-resolution methods have been developed to provide fine-scale Land Surface Temperature (LST) maps. Most of them are trained at low resolution but applied at fine resolution, and so they require a scale-invariance hypothesis that is not always adapted. The main contribution of this work is the introduction of a Scale-Invariance-Free approach for training neural network (NN) models, and the implementation of two NN models, called Scale-Invariance-Free Convolutional Neural Network for Super-Resolution (SIF-CNN-SR) for the super-resolution of MODIS LST products. The Scale-Invariance-Free approach consists on training the models in order to provide LST maps at high spatial resolution that recover the initial LST when they are degraded at low resolution and that contain fine-scale textures informed by the high resolution NDVI. The second contribution of this work is the release of an evaluation database with ASTER LST images concomitant with MODIS ones that can be used for evaluation of super-resolution algorithms. We compare the two proposed models, SIF-CNN-SR1 and SIF-CNN-SR2, with four state-of-the-art methods: Bicubic, Data Mining Sharpener, ATPRK and Tsharp, and a CNN sharing the same architecture as SIF-CNN-SR but trained under the scale-invariance hypothesis. We show that SIF-CNN-SR1 outperforms the state-of-the-art methods and the other two CNN models when evaluated with LPIPS and Fourier space metrics that focus on the analysis of textures. These results and the available ASTER-MODIS database for evaluation are promising for future studies on super-resolution of LST.