Boundary-Layer Meteorology

, Volume 165, Issue 2, pp 349–370 | Cite as

Efficient Prediction of Low-Visibility Events at Airports Using Machine-Learning Regression

  • L. Cornejo-Bueno
  • C. Casanova-Mateo
  • J. Sanz-Justo
  • E. Cerro-Prada
  • S. Salcedo-Sanz
Research Article


We address the prediction of low-visibility events at airports using machine-learning regression. The proposed model successfully forecasts low-visibility events in terms of the runway visual range at the airport, with the use of support-vector regression, neural networks (multi-layer perceptrons and extreme-learning machines) and Gaussian-process algorithms. We assess the performance of these algorithms based on real data collected at the Valladolid airport, Spain. We also propose a study of the atmospheric variables measured at a nearby tower related to low-visibility atmospheric conditions, since they are considered as the inputs of the different regressors. A pre-processing procedure of these input variables with wavelet transforms is also described. The results show that the proposed machine-learning algorithms are able to predict low-visibility events well. The Gaussian process is the best algorithm among those analyzed, obtaining over 98% of the correct classification rate in low-visibility events when the runway visual range is \({>}\)1000 m, and about 80% under this threshold. The performance of all the machine-learning algorithms tested is clearly affected in extreme low-visibility conditions (\({<}\)500 m). However, we show improved results of all the methods when data from a neighbouring meteorological tower are included, and also with a pre-processing scheme using a wavelet transform. Also presented are results of the algorithm performance in daytime and nighttime conditions, and for different prediction time horizons.


Airports Algorithms Fog prediction Low-visibility events Machine learning 



This work has been partially supported by Comunidad de Madrid, under the Project No. S2013/ICE-2933, and by Project TIN2014-54583-C2-2-R of the Spanish Ministerial Commission of Science and Technology (MICYT).


  1. AEMET (2015) Aeronautical climatology of valladolid/villanubla. Technical report, Agencia Estatal de MeteorologiaGoogle Scholar
  2. Ahmed MM, Abdel-Aty M, Lee J, Yu R (2014) Real-time assessment of fog-related crashes using airport weather data: a feasibility analysis. Accid Anal Prev 72:309–317CrossRefGoogle Scholar
  3. Bartok J, Bott A, Gera M (2012) Fog prediction for road traffic safety in a coastal desert region. Boundary-Layer Meteorol 145:485–506CrossRefGoogle Scholar
  4. Bergot T, Guedalia D (1994) Numerical forecasting of radiation fog. part i: numerical model and sensitivity tests. Mon Weather Rev 122:1218–1230CrossRefGoogle Scholar
  5. Bergot T, Terradellas-Jubanteny E, Cuxart-Rodamilans J, Mira A, Liechti O, Mueller M, Nielsen NW (2007) Intercomparison of single-column numerical models for the prediction of radiation fog. J Appl Meteorol Clim 46(4):504–521CrossRefGoogle Scholar
  6. Bishop CM (1995) Neural networks for pattern recognition. Oxford University Press, Oxford, 482 ppGoogle Scholar
  7. Boneh T, Weymouth G, Newham P, Potts R, Bally J, Nicholson A, Korb K (2015) Fog forecasting for Melbourne airport using a Bayesian decision network. Weather Forecast 30(5):1218–1233CrossRefGoogle Scholar
  8. Bott A, Trautmann T (2002) Pafog: a new efficient forecast model of radiation fog and low-level stratiform clouds. Atmos Res 64:191–203CrossRefGoogle Scholar
  9. Camps-Valls G (2015) Simple regression toolbox (simpleR).
  10. Chang C, Lin C (2011) Libsvm: a library for support vector machines. ACM Trans Intell Syst Technol 2(27):1–27CrossRefGoogle Scholar
  11. Colabone RO, Ferrari A, da Silva-Vecchia F, Bruno-Tech A (2015) Application of artificial neural networks for fog forecast. J Aerospace Technol Manag 7(2):240–246CrossRefGoogle Scholar
  12. Deo R, Wen X, Qi F (2016) A wavelet-coupled support vector machine model for forecasting global incident solar radiation using limited meteorological dataset. Appl Energy 168:568–593CrossRefGoogle Scholar
  13. Dutta D, Chaudhuri S (2015) Nowcasting visibility during wintertime fog over the airport of a metropolis of India: decision tree algorithm and artificial neural network approach. Nat Hazards 75:1349–1368CrossRefGoogle Scholar
  14. Duynkerke P (1998) Turbulence, radiation and fog in Dutch stable boundary layers. Boundary-Layer Meteorol 90:447–477CrossRefGoogle Scholar
  15. Fabbian D, De-Dear R, Lellyett S (2007) Application of artificial neural network forecasts to predict fog at Canberra international airport. Weather Forecast 22:372–381CrossRefGoogle Scholar
  16. Fedorova N, Levit V, Silva A, Santos D (2013) Low visibility formation and forecasting on the northern coast of Brazil. Pure Appl Geophys 170(4):689–709CrossRefGoogle Scholar
  17. Hagan MT, Menhaj MB (1994) Training feed forward network with the Marquardt algorithm. IEEE Trans Neural Nets 5(6):989–993CrossRefGoogle Scholar
  18. Haykin S (1998) Neural networks: a comprehensive foundation. Pearson, Cambridge, 842 ppGoogle Scholar
  19. Herman G, Schumacher R (2016) Using reforecasts to improve forecasting of fog and visibility for aviation. Weather Forecast 31:467–482CrossRefGoogle Scholar
  20. Huang G, Zhou H, Ding X, Zhang R (2012) Extreme learning machine for regression and multiclass classification. IEEE Trans Syst Man Cybern, Part B 42(2):513–529CrossRefGoogle Scholar
  21. Huang GB (2013) Extreme learning machine matlab code.
  22. Huang GB, Zhu QY (2006) Extreme learning machine: theory and applications. Neurocomput 70:489–501CrossRefGoogle Scholar
  23. Kanamitsu M, Alpert J, Campana K, Caplan P, Deaven D, Iredell M, Katz B, Pan H, Sela J, White G (1991) Recent changes implemented into the global forecast system at NMC. Weather Forecast 6(3):425–436CrossRefGoogle Scholar
  24. Koziara M, Robert J, Thompson W (1983) Estimating marine fog probability using a model output statistics scheme. Mon Weather Rev 111:2333–2340CrossRefGoogle Scholar
  25. Lázaro-Gredilla M, van Vaerenbergh S, Lawrence N (2012) Overlapping mixtures of gaussian processes for the data association problem. Pattern Recogn 45(4):1386–1395CrossRefGoogle Scholar
  26. LIBSVM (2015) LIBSVM—A library for support vector machines.
  27. Lorenz EN (1965) A study of the predictability of a 28-variable atmospheric model. Tellus 17:321–333CrossRefGoogle Scholar
  28. Mallat S (1998) A wavelet tour of signal processing. Academic Press, Cambridge, 620 ppGoogle Scholar
  29. MATLAB (2014) Multilevel 1-D wavelet decomposition. In: Wavelet toolboxGoogle Scholar
  30. Miao Y, Potts R, Huang X, Elliott G, Rivett R (2012) A fuzzy logic fog forecasting model for Perth Airport. Pure Appl Geophys 169:110–1119CrossRefGoogle Scholar
  31. Morales-Rodríguez C, Ortega-Villazán M (1994) Approximation to the study of fogs in middle Duero valley. Geogr Res 12:23–44Google Scholar
  32. Nourani V, Baghanam A, Adamowski J, Kisi O (2014) Applications of hybrid wavelet - artificial intelligence models in hydrology: a review. J Hydrol 514:358–377CrossRefGoogle Scholar
  33. Ortiz-García E, Salcedo-Sanz S, Pérez-Bellido A, Portilla-Figueras JA (2009) Improving the training time of support vector regression algorithms through novel hyper-parameters search space reductions. Neurocomput 72:3683–3691CrossRefGoogle Scholar
  34. Rasmussen CE, Williams KH (2006) Gaussian processes for machine learning. MIT Press, CambridgeGoogle Scholar
  35. Rebollo JJ, Balakrishnan H (2014) Characterization and prediction of air traffic delays. Trans Res C Emerging Technol 44:231–241CrossRefGoogle Scholar
  36. Roman-Gascón C, Yagüe C, Sastre M, Maqueda G, Salamanca F, Viana S (2012) Observations and WRF simulations of fog events at the Spanish northern plateau. Adv Sci Res 8:11–18CrossRefGoogle Scholar
  37. Román-Gascón C, Steeneveld G, Yagüe C, Sastre M, Arrillaga J, Maqueda G (2016) Forecasting radiation fog at climatologically contrasting sites: evaluation of statistical methods and WRF. Q J R Meteorol Soc 142:1048–1063CrossRefGoogle Scholar
  38. Salcedo-Sanz S, Rojo JL, Martínez-Ramón M, Camps-Valls G (2014) Support vector machines in engineering: an overview. WIREs Data-Mining Knowl Discov 4(3):234–267CrossRefGoogle Scholar
  39. Sanderson J (2015) EASA ATPL meteorology manual, Jeppesen PressGoogle Scholar
  40. Simmons AJ, Burridge DM, Jarraud M, Girard C, Wergen W (1989) The ECMWF medium-range prediction models: development of the numerical formulations and the impact of increased resolution. Meteorol Atmos Phys 40:28–60CrossRefGoogle Scholar
  41. Skamarock W, Klemp J, Dudhia J, Gill D, Barker D, Duda M, Huang X, Wang W, Powers W (2008) A description of the advanced research WRF, Version 3. NCAR Technical NoteGoogle Scholar
  42. Smola AJ, Schölkopf B (2004) A tutorial on support vector regression. Stat Comput 14:199–222CrossRefGoogle Scholar
  43. Steeneveld G, Ronda R, Holtslag A (2015) The challenge of forecasting the onset and development of radiation fog using mesoscale atmospheric models. Boundary-Layer Meteorol 154:265–289CrossRefGoogle Scholar
  44. Terradellas E, Cano D (2006) Assessment of the fog and low clouds forecasts produced by the h1d single column model. In: Abstract, sixth annual meeting of the European Meteorological Society, 4–8 September 2006, Ljubljana, SloveniaGoogle Scholar
  45. Undén P (2002) HIRLAM-5 scientific documentation. HIRLAM ConsortiumGoogle Scholar
  46. Van der Velde I, Steeneveld G, Wichers-Schreur B, Holtslag A (2010) Modeling and forecasting the onset and duration of severe radiation fog under frost conditions. Mon Weather Rev 138:4237–4253CrossRefGoogle Scholar
  47. WMO (2011) Manual on codes, international codes. Technical report, World Meteorological OrganizationGoogle Scholar
  48. Zhou B, Du J (2010) Fog prediction from a multimodel mesoscale ensemble prediction system. Weather Forecast 25:303–322CrossRefGoogle Scholar
  49. Zhou B, Du J, Gultepe I, Dimego G (2011) Forecast of low visibility and fog from NCEP: current status and efforts. Pure Appl Geophys 169:895–909CrossRefGoogle Scholar

Copyright information

© Springer Science+Business Media B.V. 2017

Authors and Affiliations

  • L. Cornejo-Bueno
    • 1
  • C. Casanova-Mateo
    • 2
    • 3
  • J. Sanz-Justo
    • 2
  • E. Cerro-Prada
    • 3
  • S. Salcedo-Sanz
    • 1
  1. 1.Department of Signal Processing and CommunicationsUniversidad de AlcaláAlcalá de HenaresSpain
  2. 2.LATUV Remote Sensing LaboratoryUniversidad de ValladolidValladolidSpain
  3. 3.Department of Civil Engineering: Construction, Infrastructure and TransportUniversidad Politécnica de MadridMadridSpain

Personalised recommendations