Downscaling land surface temperatures at regional scales with random forest regression
Abstract
Environmental monitoring with satellite data is facilitated by frequent observations at a fine spatial scale. As land surface temperature (LST) is one environmental key variable, we implemented a random forest (RF) regression approach to increase the spatial resolution of LST maps from ~1km, routinely available in daily repetition from the Moderate Resolution Imaging Spectroradiometer (MODIS), to ~250m. LST was downscaled based on its relationship to topographic variables derived from digital elevation data of the Shuttle Radar Topography Mission (SRTM), land cover data (MODIS product MCD12Q1), and surface reflectances in the visible red and near-infrared, which both are provided with the MODIS/Terra daily product MOD09GQ at ~250m resolution. The approach was tested for a complex landscape in the Eastern Mediterranean, the Jordan River Region, with LST fields from aggregated Landsat-7 ETM+ and MODIS (MODIS/Terra LST product MOD11A1) data; as reference at the finer scale, we used Landsat-7 derived LST data. For the ideal-case scenario with both degraded and reference values from the same sensor (Landsat-7 ETM+), root mean square errors (RMSE) of downscaled LSTs ranged from 1.02K to 1.43K for six different acquisition dates. When compared to the widely-adopted and in parallel applied TsHARP sharpening method, that is based on the relationship between NDVI and LST, downscaling accuracy with RF improved up to 19%. Applying the RF approach to MODIS LST products yielded RMSEs from…
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The machine learning models in kernel-driven methods are trained using coarse-scale data with inherently lower thermal contrast, and as a result, the models generally fail to fully recover the larger thermal contrast when applied at the finer scale.
“A possible explanation is that the machine learning models in kernel-driven methods are trained using coarse-scale data with inherently lower thermal contrast. As a result, the models generally fail to fully recover the larger thermal contrast when applied at the finer scale (Hutengs and Vohland, 2016; Yoo et al., 2020).”
From PGDM: Physically guided diffusion model for land surface temperature downscaling (2025) · cites this paper as Hutengs and Vohland, 2016
For both the kernel-driven and DCF models, the accuracy discrepancy between the linear and nonlinear variants is not significant.
“For both the kernel-driven and DCF models, the accuracy discrepancy between the linear and nonlinear variants is not significant, which is consistent with previous studies (Dong et al., 2020; Hutengs and Vohland, 2016).”
From PGDM: Physically guided diffusion model for land surface temperature downscaling (2025) · cites this paper as Hutengs and Vohland, 2016
Cites
Breiman, L. (2001) · Machine Learning · doi:10.1023/a:1010933404324 · Cited by 133,538 · see citing works
Flagged first, then by citations
Cited by
Sorted by citations
Evaluation of Machine Learning Algorithms in Spatial Downscaling of MODIS Land Surface Temperature
Li, W., Ni, L., Li, Z.-L., Duan, S.-B., & Wu, H. (2019) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2019.2896923 · Cited by 145 · see citing works
PGDM: Physically guided diffusion model for land surface temperature downscaling
Zhang, H., Tang, B.-H., Hu, T., Jiang, Y., & Li, Z.-L. (2025) · arXiv · doi:10.48550/arxiv.2511.05964 · Cited by 3 · see citing works
- Authors
- Hutengs, C., & Vohland, M.
- Affiliations
- Leipzig University (DE)
- Corresponding author
- Vohland, Michael
- ORCID
- Vohland, Michael
- Venue
- Remote Sensing of Environment
- Publisher
- Elsevier BV
- Published
- 2016-06
- Volume
- 178
- Pages
- 127-141
- ISSN
- 0034-4257 (ISSN-L)
- OpenAlex
- W2301692565
- Cited by
- 562
- References
- 1
- Citations by year
- 2026: 73 · 2025: 58 · 2024: 68 · 2023: 73 · 2022: 90 · 2021: 62 · 2020: 51 · 2019: 49 · 2018: 29 · 2017: 6 · 2016: 3
- FWCI
- 22.36
- Type
- journal article
- Language
- en
- Open access
- closed
- Locations
- Remote Sensing of Environment (publishedVersion)
- Funders
- GLOWA programme (GLOWA Jordan River Project) of the BMBF
- German Federal Ministry of Education and Research
- Topics
- Physical Sciences › Environmental Science › Ecology › Remote Sensing in Agriculture
- Physical Sciences › Environmental Science › Environmental Engineering › Urban Heat Island Mitigation
- Physical Sciences › Environmental Science › Environmental Engineering › Soil Moisture and Remote Sensing
- Keywords
- land surface temperature, spatial downscaling, random forest regression, MODIS LST, Landsat 7 ETM+, VIIRS, topographic variables, surface reflectance, land cover, Eastern Mediterranean, thermal contrast, satellite thermal imagery, environmental monitoring, Suomi NPP
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
