A novel approach for downscaling land surface temperature from 30 m to 10 m using land features multi-interaction
This paper explores the potential of downscaling Land Surface Temperature, LST, based on land features multi-interaction with a spatial regression multi-modelling. The Radiative Transfer Equation first helped to create an LST 15 m layer over Landsat-OLI/TIRS. Next, a bilinear assessment of LST is co...
Uloženo v:
| Vydáno v: | Annals of GIS Ročník 31; číslo 3; s. 449 - 472 |
|---|---|
| Hlavní autoři: | , , , , , , |
| Médium: | Journal Article |
| Jazyk: | angličtina |
| Vydáno: |
Taylor & Francis
03.07.2025
Taylor & Francis Group |
| Témata: | |
| ISSN: | 1947-5683, 1947-5691 |
| On-line přístup: | Získat plný text |
| Tagy: |
Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
|
| Shrnutí: | This paper explores the potential of downscaling Land Surface Temperature, LST, based on land features multi-interaction with a spatial regression multi-modelling. The Radiative Transfer Equation first helped to create an LST
15 m
layer over Landsat-OLI/TIRS. Next, a bilinear assessment of LST is conducted over elevation and hillshade, so to adjust shadow/brightness. Then, interactions are modelled on a feature-to-feature linear basis between spectral indices, SI's, representing vegetation, built-up, soil, water and shadow. A multilinear regression model is further built between combined pairs of interactions and LST
15 m
. The first principal Component, PC1, of all subtractions of each pair of interactions from others is stacked with individual SI's, to build another multi-regression model around LST
15 m
. Each of the three models is individually subtracted from LST
15 m
, normalized, [0-1], and their sum serves as the residuals layer. The downscaling step uses coefficients of the interactions model with PC1 over the corresponding Sentinel2-MSI 10 m SI's, and adds back the gaussian-kernel of residuals. The Normalized Urban-High Spatial Resolution-Land Surface Temperature, NU-HSR-LST
10 m
, is the final product, that sharpens hot/cold spots, with a highly spread of values among land features. As supporting results, directions of relations with vegetation and built-up were improved, while unexpected relations were alternatively revealed (water) or reversed (soil, shadow); determination coefficients, R
2
, shows a strong correlation of NU-HSR-LST
10 m
to LST
30 m
(R
2
:[0.7304-0.9844]), even stronger with a closest model (R
2
:[0.85-0.99]); a variance analysis between NU-HSR-LST
10 m
and LST
30 m
is quasi-insignificant between [0.0002-0.00297]; and a root mean square error computed in a war-disturbed urban context, was lower for NU-HSR-LST
10 m
, [0.057-0.096], than for LST
30 m
,[0.106-0.151], as stability in dynamics depiction. Finally, the machine learning algorithm of random forest based on different seeds achieved overall accuracy between [0.92-1]. From these results, the downscaling process is efficient in better distinguishing contributions per land feature in diverse urban environments, while more cross-validation based on meteorological stations is still needed. |
|---|---|
| ISSN: | 1947-5683 1947-5691 |
| DOI: | 10.1080/19475683.2025.2525333 |