Intercomparison of Machine Learning Models to Determine the Planetary Boundary Layer Height Over Central Amazonia
Journal of Geophysical Research: Atmospheres · 28.03.2025 · 130 (6)
DOI: 10.1029/2024jd042488 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Geophysical Research: Atmospheres, online erschienen am 24.03.2025. Verfasst von Adam Stapleton und 7 weiteren Autor:innen. Die Arbeit wurde bisher 9-mal zitiert (Crossref) und nennt 75 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Science Foundation Ireland, Insight SFI Research Centre for Data Analytics, Bundesministerium für Bildung und Forschung.
Abstract (Originalsprache)
The planetary boundary layer height ( zi ) is a key parameter in meteorology and climatology, influencing weather prediction, cloud formation, and the vertical transport of scalars and energy near Earth's surface. This study compares multiple machine learning (ML) models that predict zi from surface measurements at two sites in Central Amazonia—the Amazon Tall Tower Observatory (ATTO) and the Manacapuru site of the GoAmazon experiment (T3). Models were trained on ceilometer data with radiosonde measurements used for validation. We evaluated model performance by withholding approximately 10% of the data (as complete months) for testing, comparing predictions against ERA‐5 reanalysis data using RMSE , nRMSE , and R 2 metrics. Our results show that gradient boosted ensemble models using all available features perform best. A modified recursive feature elimination algorithm identified minimal sets of 5–7 surface measurements sufficient for accurate zi prediction, demonstrating potential for wider spatial monitoring using cost‐effective sensors. The study revealed previously unrecognized variables influential in determining zi , such as deep soil temperature measurements (40 cm), suggesting new avenues for investigating land‐atmosphere interactions. This study demonstrates the applicability of ML models to model zi .
Förderung
- Science Foundation Ireland
- Insight SFI Research Centre for Data Analytics
- Bundesministerium für Bildung und Forschung
Zitieren
APA
Stapleton, A., Dias‐Junior, C. Q., Randow, C. V., D'Oliveira, F. A. F., Pöhlker, C., Araújo, A. C. D., Roantree, M., & Eichelmann, E. (2025). Intercomparison of Machine Learning Models to Determine the Planetary Boundary Layer Height Over Central Amazonia. Journal of Geophysical Research: Atmospheres, 130(6). https://doi.org/10.1029/2024jd042488
Vancouver
Stapleton A, Dias‐Junior CQ, Randow CV, D'Oliveira FAF, Pöhlker C, Araújo ACD, et al. Intercomparison of Machine Learning Models to Determine the Planetary Boundary Layer Height Over Central Amazonia. Journal of Geophysical Research: Atmospheres. 2025;130(6). doi:10.1029/2024jd042488
BibTeX
@article{Stapleton2025,
author = {Stapleton, Adam and Dias‐Junior, Cléo Quaresma and Randow, Celso Von and D'Oliveira, Flávio Augusto Farias and Pöhlker, Christopher and Araújo, Alessandro C. de and Roantree, Mark and Eichelmann, Elke},
title = {Intercomparison of Machine Learning Models to Determine the Planetary Boundary Layer Height Over Central Amazonia},
journal = {Journal of Geophysical Research: Atmospheres},
year = {2025},
volume = {130},
number = {6},
doi = {10.1029/2024jd042488}
}
EUVIMED