Estimation of Planetary Boundary Layer Height from Surface Meteorological Observation Using Random Forest
Abstract
The Planetary Boundary Layer (PBL) is the lowest layer of the atmosphere that directly interacts with earth surface and plays a crucial role in momentum exchange and particle dispersion. Conventional observations of the PBL are limited by spatial coverage, operational costs, and temporal availability. Therefore, this study aims to develop a Random Forest model for estimating the PBL Height (PBLH) using surface meteorological observations. This research was conducted in Central Kalimantan during the dry season (June – November) from 2018 to 2024. Surface meteorological observation was used as input variables, while PBLH from ERA5 served as the target variable and PBLH of radiosonde role as independent validation. The result show that the developed model successfully represents the data distribution and variability of PBLH, achieving a Pearson correlation of 0.7409 (p < 0.001), an R2 of 0.5474, RMSE of 107.59 m, and MAE 83.81. Feature importance analysis indicates that relative humidity, wind direction, and wind speed are the most influential variables for PBLH estimation that consistent with the physical processes governing turbulence within the PBL. Temporal validation further demonstrates that the model effectively captures the temporal variability of PBLH. However, the model is unable to accurately estimate the extreme values observed from radiosonde and generally follows the temporal pattern of PBLH ERA5. Overall, the proposed model provides reliable PBLH estimates during the dry season using surface meteorological observations and has the potential to serve as an alternative approach for operational PBLH estimation with limited radiosonde observations.
Full Text:
PDFReferences
R. B. Stull, An Introduction to Boundary Layer Meteorology. Dordrecht: Kluwer Academic Publishers, 1988.
S. Liu and X.-Z. Liang, “Observed Diurnal Cycle Climatology of Planetary Boundary Layer Height,” J. Clim., vol. 23, no. 21, pp. 5790–5809, 2010.
J. M. Wallace and P. V Hobbs, Atmospheric Science: an Introductory Survey, vol. 92. Elsevier, 2006.
J. A. Mantovani Júnior, J. A. Aravéquia, R. G. Carneiro, and G. Fisch, “Evaluation of PBL Parameterization Schemes in WRF Model Predictions During the Dry Season of the Central Amazon Basin,” Atmosphere (Basel)., vol. 14, no. 5, p. 850, 2023.
J. Gu, Y. Zhang, N. Yang, and R. Wang, “Diurnal Variability of The Planetary Boundary Layer Height Estimated from Radiosonde Data,” Earth and Planetary Physics, vol. 4, no. 5, pp. 479–492, 2020.
D. J. Seidel, C. O. Ao, and K. Li, “Estimating Climatological Planetary Boundary Layer Heights from Radiosonde Observations: Comparison of Methods and Uncertainty Analysis,” Journal of Geophysical Research: Atmospheres, vol. 115, no. D16, 2010.
P. R. P. Silva, R. G. Carneiro, A. O. Moraes, C. Q. Dias-Junior, and G. Fisch, “Estimating Planetary Boundary Layer Height over Central Amazonia Using Random Forest,” Atmosphere (Basel)., vol. 16, no. 8, p. 941, 2025, doi: 10.3390/atmos16080941.
F. Molero, R. Barragán, and B. Artíñano, “Estimation of The Atmospheric Boundary Layer Height by Means of Machine Learning Techniques Using Ground-Level Meteorological Data,” Atmos. Res., vol. 279, p. 106401, 2022.
X. Xi et al., “Evaluation of the Planetary Boundary Layer Height from ERA5 Reanalysis with MOSAiC Observations over the Arctic Ocean,” Journal of Geophysical Research: Atmospheres, vol. 129, no. 12, p. e2024JD040779, 2024.
R. Krishnamurthy, R. K. Newsom, L. K. Berg, H. Xiao, P.-L. Ma, and D. D. Turner, “On The Estimation of Boundary Layer Heights: A Machine Learning Approach,” Atmospheric Measurement Techniques Discussions, vol. 2020, pp. 1–34, 2020, doi: 10.5194/amt-14-4403-2021.
J. Guo et al., “A Merged Continental Planetary Boundary Layer Height Dataset Based on High-Resolution Radiosonde Measurements, ERA5 Reanalysis, and GLDAS,” Earth Syst. Sci. Data, vol. 16, no. 1, pp. 1–14, 2024.
L. Breiman, “Random Forests,” Mach. Learn., vol. 45, no. 1, pp. 5–32, 2001, doi: 10.1023/A:1010933404324.
J. T. Lestari, E. H. Sujiono, and M. Arsyad, “Analisis Hubungan Ketinggian Planetary Boundary Layer (PBL) dengan Surface Flux di Makassar dan Sekitarnya,” Jurnal Fisika Unand, vol. 13, no. 4, pp. 459–468, 2024.
A. Stapleton et al., “Intercomparison of Machine Learning Models to Determine The Planetary Boundary Layer Height Over Central Amazonia,” Journal of Geophysical Research: Atmospheres, vol. 130, no. 6, p. e2024JD042488, 2025.
D. H. P. Vogelezang and A. A. M. Holtslag, “Evaluation and Model Impacts of Alternative Boundary-Layer Height Formulations,” Boundary. Layer. Meteorol., vol. 81, no. 3, pp. 245–269, 1996.
European Centre for Medium-Range Weather Forecasts, “IFS Documentation CY49R1: Part IV – Physical Processes,” ECMWF, 2024, doi: https://doi.org/10.21957/c731ee1102.
Z. Li et al., “A Temperature Refinement Method Using the ERA5 Reanalysis Data,” Atmosphere (Basel)., vol. 13, no. 10, p. 1622, 2022.
M. Komorowski, D. Marshall, J. Salciccioli, and Y. Crutain, “Exploratory Data Analysis,” in Secondary Analysis of Electronic Health Records, 2016, pp. 185–203. doi: 10.1007/978-3-319-43742-2_15.
K. Peng et al., “Machine Learning Model to Accurately Estimate The Planetary Boundary Layer Height of Beijing Urban Area with ERA5 Data,” Atmos. Res., vol. 293, p. 106925, 2023.
D. Zhang et al., “Best Estimate of The Planetary Boundary Layer Height from Multiple Remote Sensing Measurements,” Atmos. Meas. Tech., vol. 18, no. 14, pp. 3453–3475, 2025.
T. Akiba, S. Sano, T. Yanase, T. Ohta, and M. Koyama, “Optuna: A Next-Generation Hyperparameter Optimization Framework,” in Proceedings of the 25th ACM SIGKDD international conference on knowledge discovery & data mining, 2019, pp. 2623–2631.
R. L. Wasserstein and N. A. Lazar, “The ASA Statement on p-values: Context, Process, and Purpose,” 2016, Taylor & Francis.
G. James, D. Witten, T. Hastie, and R. Tibshirani, An Introduction to Statistical Learning: with Applications in R, vol. 103. Springer, 2013.
D. Wilks, Statistical Methods in the Atmospheric Sciences Second Edition. Oxford: Elsevier, 2006.
DOI: https://doi.org/10.24198/jiif.v10i2.71592
Refbacks
- There are currently no refbacks.
