Remote Sensing (Apr 2025)
Super-Resolution of Landsat-8 Land Surface Temperature Using Kolmogorov–Arnold Networks with PlanetScope Imagery and UAV Thermal Data
Abstract
Super-Resolution Land Surface Temperature (LSTSR) maps are essential for urban heat island (UHI) analysis and temperature monitoring. While much of the literature focuses on improving the resolution of low-resolution LST (e.g., MODIS-derived LST) using high-resolution space-borne data (e.g., Landsat-derived LST), Unmanned Aerial Vehicles (UAVs)/drone thermal imagery are rarely used for this purpose. Additionally, many deep learning (DL)-based super-resolution approaches, such as Convolutional Neural Networks (CNNs) and Generative Adversarial Networks (GANs), require significant computational resources. To address these challenges, this study presents a novel approach to generate LSTSR maps by integrating Low-Resolution Landsat-8 LST (LSTLR) with High-Resolution PlanetScope images (IHR) and UAV-derived thermal imagery (THR) using the Kolmogorov–Arnold Network (KAN) model. The KAN efficiently integrates the strengths of splines and Multi-Layer Perceptrons (MLPs), providing a more effective solution for generating LSTSR. The multi-step process involves acquiring and co-registering THR via the DJI Mavic 3 thermal (T) drone, IHR from Planet (3 m resolution), and LSTLR from Landsat-8, with THR serving as reference data while IHR and LSTLR are used as input features for the KAN model. The model was trained at two sites in Germany (Oberfischbach and Mittelfischbach) and tested at Königshain, achieving reasonable performance (RMSE: 4.06 °C, MAE: 3.09 °C, SSIM: 0.83, PSNR: 22.22, MAPE: 9.32%), and outperforming LightGBM, XGBoost, ResDensNet, and ResDensNet-Attention. These results demonstrate the KAN’s superior ability to extract fine-scale temperature patterns (e.g., edges and boundaries) from IHR, significantly improving LSTLR. This advancement can enhance UHI analysis, local climate monitoring, and LST modeling, providing a scalable solution for urban heat mitigation and broader environmental applications. To improve scalability and generalizability, KAN models benefit from training on a more diverse set of UAV thermal imagery, covering different seasons, land use types, and regions. Despite this, the proposed approach is effective in areas with limited UAV data availability.
Keywords