Super-Resolution of Landsat-8 Land Surface Temperature Using Kolmogorov–Arnold Networks with PlanetScope Imagery and UAV Thermal Data

Super-Resolution Land Surface Temperature (LST<sub>SR</sub>) 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-bo...

Full description

Saved in:
Bibliographic Details
Main Authors: Mahdiyeh Fathi, Hossein Arefi, Reza Shah-Hosseini, Armin Moghimi
Format: Article
Language:English
Published: MDPI AG 2025-04-01
Series:Remote Sensing
Subjects:
Online Access:https://www.mdpi.com/2072-4292/17/8/1410
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849715048945025024
author Mahdiyeh Fathi
Hossein Arefi
Reza Shah-Hosseini
Armin Moghimi
author_facet Mahdiyeh Fathi
Hossein Arefi
Reza Shah-Hosseini
Armin Moghimi
author_sort Mahdiyeh Fathi
collection DOAJ
description Super-Resolution Land Surface Temperature (LST<sub>SR</sub>) 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 LST<sub>SR</sub> maps by integrating Low-Resolution Landsat-8 LST (LST<sub>LR</sub>) with High-Resolution PlanetScope images (I<sub>HR</sub>) and UAV-derived thermal imagery (T<sub>HR</sub>) 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 LST<sub>SR</sub>. The multi-step process involves acquiring and co-registering T<sub>HR</sub> via the DJI Mavic 3 thermal (T) drone, I<sub>HR</sub> from Planet (3 m resolution), and LST<sub>LR</sub> from Landsat-8, with T<sub>HR</sub> serving as reference data while I<sub>HR</sub> and LST<sub>LR</sub> 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 I<sub>HR</sub>, significantly improving LST<sub>LR</sub>. 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.
format Article
id doaj-art-14bfbffe71164df1b81d3057a605b89a
institution DOAJ
issn 2072-4292
language English
publishDate 2025-04-01
publisher MDPI AG
record_format Article
series Remote Sensing
spelling doaj-art-14bfbffe71164df1b81d3057a605b89a2025-08-20T03:13:32ZengMDPI AGRemote Sensing2072-42922025-04-01178141010.3390/rs17081410Super-Resolution of Landsat-8 Land Surface Temperature Using Kolmogorov–Arnold Networks with PlanetScope Imagery and UAV Thermal DataMahdiyeh Fathi0Hossein Arefi1Reza Shah-Hosseini2Armin Moghimi3i3mainz, Institute for Spatial Information and Surveying Technology, Mainz University of Applied Sciences, 55128 Mainz, Germanyi3mainz, Institute for Spatial Information and Surveying Technology, Mainz University of Applied Sciences, 55128 Mainz, GermanySchool of Surveying and Geospatial Engineering, College of Engineering, University of Tehran, Tehran 14399-57131, IranDepartment of Photogrammetry and Remote Sensing, Geomatics Engineering Faculty, K. N. Toosi University of Technology, Tehran 19967-15433, IranSuper-Resolution Land Surface Temperature (LST<sub>SR</sub>) 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 LST<sub>SR</sub> maps by integrating Low-Resolution Landsat-8 LST (LST<sub>LR</sub>) with High-Resolution PlanetScope images (I<sub>HR</sub>) and UAV-derived thermal imagery (T<sub>HR</sub>) 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 LST<sub>SR</sub>. The multi-step process involves acquiring and co-registering T<sub>HR</sub> via the DJI Mavic 3 thermal (T) drone, I<sub>HR</sub> from Planet (3 m resolution), and LST<sub>LR</sub> from Landsat-8, with T<sub>HR</sub> serving as reference data while I<sub>HR</sub> and LST<sub>LR</sub> 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 I<sub>HR</sub>, significantly improving LST<sub>LR</sub>. 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.https://www.mdpi.com/2072-4292/17/8/1410super-resolutionLSTplanetUAVsKANs
spellingShingle Mahdiyeh Fathi
Hossein Arefi
Reza Shah-Hosseini
Armin Moghimi
Super-Resolution of Landsat-8 Land Surface Temperature Using Kolmogorov–Arnold Networks with PlanetScope Imagery and UAV Thermal Data
Remote Sensing
super-resolution
LST
planet
UAVs
KANs
title Super-Resolution of Landsat-8 Land Surface Temperature Using Kolmogorov–Arnold Networks with PlanetScope Imagery and UAV Thermal Data
title_full Super-Resolution of Landsat-8 Land Surface Temperature Using Kolmogorov–Arnold Networks with PlanetScope Imagery and UAV Thermal Data
title_fullStr Super-Resolution of Landsat-8 Land Surface Temperature Using Kolmogorov–Arnold Networks with PlanetScope Imagery and UAV Thermal Data
title_full_unstemmed Super-Resolution of Landsat-8 Land Surface Temperature Using Kolmogorov–Arnold Networks with PlanetScope Imagery and UAV Thermal Data
title_short Super-Resolution of Landsat-8 Land Surface Temperature Using Kolmogorov–Arnold Networks with PlanetScope Imagery and UAV Thermal Data
title_sort super resolution of landsat 8 land surface temperature using kolmogorov arnold networks with planetscope imagery and uav thermal data
topic super-resolution
LST
planet
UAVs
KANs
url https://www.mdpi.com/2072-4292/17/8/1410
work_keys_str_mv AT mahdiyehfathi superresolutionoflandsat8landsurfacetemperatureusingkolmogorovarnoldnetworkswithplanetscopeimageryanduavthermaldata
AT hosseinarefi superresolutionoflandsat8landsurfacetemperatureusingkolmogorovarnoldnetworkswithplanetscopeimageryanduavthermaldata
AT rezashahhosseini superresolutionoflandsat8landsurfacetemperatureusingkolmogorovarnoldnetworkswithplanetscopeimageryanduavthermaldata
AT arminmoghimi superresolutionoflandsat8landsurfacetemperatureusingkolmogorovarnoldnetworkswithplanetscopeimageryanduavthermaldata