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

2025-02-03

AI Summary

MODIS land surface temperature (LST) data suffer from limited spatiotemporal resolution, and conventional super-resolution (SR) methods rely on the scale-invariance assumption—often invalid for LST due to its strong spatial heterogeneity and physical nonlinearity. Method: We propose a scale-invariance-free neural network SR framework that directly learns the nonlinear mapping from coarse-resolution MODIS LST to fine-resolution LST. Our approach incorporates high-resolution NDVI as texture guidance and introduces two novel CNN architectures—SIF-CNN-SR1 and SIF-CNN-SR2—incorporating multi-scale texture constraints and Fourier-domain loss. To enable rigorous evaluation, we construct the first paired ASTER–MODIS LST benchmark dataset. Contribution/Results: Experiments demonstrate that SIF-CNN-SR1 significantly outperforms bicubic interpolation, DMS, ATPRK, Tsharp, and scale-invariant CNN baselines in perceptual quality (LPIPS) and spectral fidelity, enabling physically consistent, high-fidelity LST reconstruction without assuming scale invariance.

Technology Category

• Computer Vision: Multi-modal Vision
• Machine Learning: Multimodal Learning
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

Due to the trade-off between the temporal and spatial resolution of thermal spaceborne sensors, super-resolution methods have been developed to provide fine-scale Land SurfaceTemperature (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. Themain 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, calledScale-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 ontraining 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 texturesinformed by the high resolution NDVI. The second contribution of this work is the release of a test database with ASTER LST images concomitant with MODIS ones that can be usedfor 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, DMS, ATPRK, 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 as evaluated with LPIPS and Fourier space metrics focusing 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.

Problem

• Super-resolution
• MODIS satellite data
• Surface temperature imagery

Innovation

• Scale-Invariant Training
• Super-Resolution
• MODIS Surface Temperature