Advancing Aviation Meteorology: Airport Visibility Prediction Using Random Forest Regressor On Integrated Metar Parameters
Abstract
To provide accurate and reliable visibility information in support of aviation safety at Soekarno-Hatta International Airport, a visibility prediction system was developed using the Random Forest Regressor algorithm based on 2024 METAR data. Visibility is a critical parameter for flight safety, particularly under adverse weather conditions. The dataset includes wind direction and speed, temperature, dew point, air pressure, weather phenomena, and cloud parameters that were numerically encoded. After preprocessing and quality control, the data was input into a Random Forest model optimized using Grid Search. Evaluation results show strong predictive performance with an R² value of 0.8736, MAE of 607.45 m, and RMSE of 772.29 m. Feature importance analysis identified haze, temperature, and mist as the most influential factors affecting visibility. These findings demonstrate that integrating meteorological observational data with machine learning approaches can provide accurate visibility predictions to support aviation operational decision-making.
Full Text:
PDF (Bahasa Indonesia)References
A. Kwasiborska, M. Grabowski, A. N. Sedláčková, and A. Novák, “The influence of visibility on the opportunity to perform flight operations with various categories of the instrument landing system,” Sensors, vol. 23, no. 18, p. 7953, 2023.
K. Ait Ouadil, S. Idbraim, T. Bouhsine, N. Carla Bouaynaya, H. Alfergani, and C. Cliff Johnson, “Atmospheric visibility estimation: a review of deep learning approach,” Multimed Tools Appl, vol. 83, no. 12, pp. 36261–36286, 2024.
S. G. Benjamin et al., “A North American hourly assimilation and model forecast cycle: The Rapid Refresh,” Mon Weather Rev, vol. 144, no. 4, pp. 1669–1694, 2016.
T. Arcomano, I. Szunyogh, J. Pathak, A. Wikner, B. R. Hunt, and E. Ott, “A machine learning‐based global atmospheric forecast model,” Geophys Res Lett, vol. 47, no. 9, p. e2020GL087776-e2020GL087776, 2020.
Y. Zhang, Y. Wang, Y. Zhu, L. Yang, L. Ge, and C. Luo, “Visibility prediction based on machine learning algorithms,” Atmosphere (Basel), vol. 13, no. 7, p. 1125, 2022.
J. Y.-L. Chan et al., “Mitigating the multicollinearity problem and its machine learning approach: a review,” Mathematics, vol. 10, no. 8, p. 1283, 2022.
D. Nyberg, “Development of weather services for aviation personnel,” 2021.
S. H. Alhathloul, A. K. Mishra, and A. A. Khan, “Low visibility event prediction using random forest and K-nearest neighbor methods,” Theor Appl Climatol, vol. 155, no. 2, pp. 1289–1300, 2024.
N. Penov and G. Guerova, “Sofia airport visibility estimation with two machine-learning techniques,” Remote Sens (Basel), vol. 15, no. 19, p. 4799, 2023.
L. Breiman, “Random Forests,” Mach Learn, vol. 45, no. 1, pp. 5–32, 2001, doi: 10.1023/A:1010933404324.
P. Probst, M. N. Wright, and A. Boulesteix, “Hyperparameters and tuning strategies for random forest,” Wiley Interdiscip Rev Data Min Knowl Discov, vol. 9, no. 3, p. e1301, 2019.
C. J. Willmott and K. Matsuura, “Advantages of the mean absolute error (MAE) over the root mean square error (RMSE) in assessing average model performance,” Clim Res, vol. 30, no. 1, pp. 79–82, 2005.
T. Chai and R. R. Draxler, “Root mean square error (RMSE) or mean absolute error (MAE)? – Arguments against avoiding RMSE in the literature,” Geosci Model Dev, vol. 7, no. 3, pp. 1247–1250, Jun. 2014, doi: 10.5194/gmd-7-1247-2014.
D. Chicco, M. J. Warrens, and G. Jurman, “The coefficient of determination R-squared is more informative than SMAPE, MAE, MAPE, MSE and RMSE in regression analysis evaluation,” PeerJ Comput Sci, vol. 7, p. e623, 2021.
I. Gultepe et al., “A Review of High Impact Weather for Aviation Meteorology,” Pure Appl Geophys, vol. 176, no. 5, pp. 1869–1921, 2019, doi: 10.1007/s00024-019-02168-6.
I. Gultepe et al., “Fog research: A review of past achievements and future perspectives,” Pure Appl Geophys, vol. 164, no. 6, pp. 1121–1159, 2007.
D. Bari, T. Bergot, and R. Tardif, “Fog decision support systems: A review of the current perspectives,” Atmosphere (Basel), vol. 14, no. 8, p. 1314, 2023.
Z. Yu, Y. Qu, Y. Wang, J. Ma, and Y. Cao, “Application of machine-learning-based fusion model in visibility forecast: A case study of Shanghai, China,” Remote Sens (Basel), vol. 13, no. 11, p. 2096, 2021.
M. Zhen et al., “Application of a fusion model based on machine learning in visibility prediction,” Remote Sens (Basel), vol. 15, no. 5, p. 1450, 2023.
K. Chandu, A. Dharmaraju, S. V. J. Kumar, Gc. Satyanarayana, and M. Dasari, “Determinants and impact of fog, mist and haze phenomena: the case of Rajiv Gandhi International Airport, Hyderabad,” Mausam, vol. 74, no. 1, pp. 19–28, 2023.
N. Ravshanov, T. R. Shafiev, and S. Daliev, “Study of the main factors affecting the spread of aerosol particles in the atmosphere,” in Journal of Physics: Conference Series, IOP Publishing, 2021, p. 12083.
J. He, W. Wang, M. Fu, and Y. Wang, “Insights into global visibility patterns: Spatiotemporal distributions revealed by satellite remote sensing,” J Clean Prod, vol. 468, p. 143069, 2024.
A. Gul, M. Mohsin, M. Adil, and M. Ali, “A modified truncated distribution for modeling the heavy tail, engineering and environmental sciences data,” PLoS One, vol. 16, no. 4, pp. e0249001–e0249001, 2021.
S. Jewson, T. Sweeting, and L. Jewson, “Reducing reliability bias in assessments of extreme weather risk using calibrating priors,” Adv Stat Climatol Meteorol Oceanogr, vol. 11, no. 1, pp. 1–22, 2025.
C. Zhang et al., “Weather visibility prediction based on multimodal fusion,” IEEE Access, vol. 7, pp. 74776–74786, 2019.
M. Zarei, M. Najarchi, and R. Mastouri, “Bias correction of global ensemble precipitation forecasts by Random Forest method,” Earth Sci Inform, vol. 14, no. 2, pp. 677–689, 2021.
M. Wasikowski and X. Chen, “Combating the small sample class imbalance problem using feature selection,” IEEE Trans Knowl Data Eng, vol. 22, no. 10, pp. 1388–1400, 2009.
L. Wang, M. Han, X. Li, N. Zhang, and H. Cheng, “Review of classification methods on unbalanced data sets,” Ieee Access, vol. 9, pp. 64606–64628, 2021.
J. Cherian, I. Gibbs, and E. Candes, “Large language model validity via enhanced conformal prediction methods,” Adv Neural Inf Process Syst, vol. 37, pp. 114812–114842, 2024.
H. Khandor, R. Y. Dhurandhar, D. Shah, and N. Batra, “Distribution-Free Uncertainty Quantification and Calibration for Energy Disaggregation,” ACM Journal on Computing and Sustainable Societies, 2025.
A. Shankar and B. C. Sahana, “Early warning of low visibility using the ensembling of machine learning approaches for aviation services at Jay Prakash Narayan International (JPNI) Airport Patna,” SN Appl Sci, vol. 5, no. 5, p. 132, 2023.
A. Murad, F. A. Kraemer, K. Bach, and G. Taylor, “Probabilistic deep learning to quantify uncertainty in air quality forecasting,” Sensors, vol. 21, no. 23, p. 8009, 2021.
M. A. Rehman, N. Abd Rahman, A. N. H. Ibrahim, N. A. Kamal, and A. Ahmad, “Estimation of soil erodibility in Peninsular Malaysia: A case study using multiple linear regression and artificial neural networks,” Heliyon, vol. 10, no. 7, 2024.
DOI: https://doi.org/10.24198/jiif.v9i2.65464
Refbacks
- There are currently no refbacks.
