EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Downscaling MODIS land surface temperature to 90 m using random forest regression to assess transferability

Pallab Kumar Das, Indrajit Mukherjee, Pankaj Prasad, Shashank Pushkar

PeerJ Computer Science · 05.11.2025 · 11 · e3246

DOI: 10.7717/peerj-cs.3246 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PeerJ Computer Science, online erschienen am 05.11.2025. Verfasst von Pallab Kumar Das und 3 weiteren Autor:innen. Die Arbeit wurde bisher 8-mal zitiert (Crossref) und nennt 51 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Anusandhan National Research Foundation, Department of Science and Technology, Government of India, under the Core Research Grant.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The observable spatiotemporal trade-offs among different satellite sensors necessitate the downscaling of optical and thermal data to identify Earth’s surface features and analyze temperature variations at finer scales. This study employs a random forest (RF) regression model to downscale Moderate Resolution Imaging Spectroradiometer (MODIS) land surface temperature (LST) data from a 1-km spatial resolution to 90 m. The model is trained on a primary region and applied to a spatially distinct secondary region to evaluate its transferability. Six acquisition dates, each representing a different month, were selected for downscaling. For contextual performance assessment, eXtreme Gradient Boosting (XGBoost) and Categorical Boosting (CatBoost) models were also trained and evaluated using the same setup. In the primary region, the RF model showed minimal root mean square error (RMSE) deviation across all acquisition dates, underscoring the importance of incorporating multiple variables. Comparable performance was observed with XGBoost and CatBoost in the primary region. In the secondary region, RF demonstrated strong generalizability, with the lowest RMSEs recorded in November (0.85) and February (0.96), and R 2 values of 0.65 or higher across all months. In contrast, XGBoost and CatBoost exhibited inconsistencies in the secondary region, with CatBoost failing notably in June, further highlighting RF’s robustness in transferability. The study’s outcomes suggest that RF regression is a promising and effective method for downscaling coarse-resolution LST data in similar geo-environmental conditions.

Förderung

  • Anusandhan National Research Foundation
  • Department of Science and Technology
  • Government of India, under the Core Research Grant

Zitieren

APA

Das, P. K., Mukherjee, I., Prasad, P., & Pushkar, S. (2025). Downscaling MODIS land surface temperature to 90 m using random forest regression to assess transferability. PeerJ Computer Science, 11, e3246. https://doi.org/10.7717/peerj-cs.3246

Vancouver

Das PK, Mukherjee I, Prasad P, Pushkar S. Downscaling MODIS land surface temperature to 90 m using random forest regression to assess transferability. PeerJ Computer Science. 2025;11:e3246. doi:10.7717/peerj-cs.3246

BibTeX
@article{Das2025,
  author = {Das, Pallab Kumar and Mukherjee, Indrajit and Prasad, Pankaj and Pushkar, Shashank},
  title = {Downscaling MODIS land surface temperature to 90 m using random forest regression to assess transferability},
  journal = {PeerJ Computer Science},
  year = {2025},
  volume = {11},
  pages = {e3246},
  doi = {10.7717/peerj-cs.3246}
}
Kostenlos starten →