Statistical Analysis and Machine Learning Prediction of Fog-Caused Low-Visibility Events at A-8 Motor-Road in Spain

This work presents a full statistical analysis and accurate prediction of low-visibility events due to fog, at the A-8 motor-road in Mondonedo (Galicia, Spain). The present analysis covers two years of study, considering visibility time series and exogenous variables collected in the zone affected the most by extreme low-visibility events. This paper has then a two-fold objective: first, we carry out a statistical analysis for estimating the fittest probability distributions to the fog event duration, using the Maximum Likelihood method and an alternative method known as the L-moments method. This statistical study allows association of the low-visibility depth with the event duration, showing a clear relationship, which can be modeled with distributions for extremes such as Generalized Extreme Value and Generalized Pareto distributions. Second, we apply a neural network approach, trained by means of the ELM (Extreme Learning Machine) algorithm, to predict the occurrence of low-visibility events due to fog, from atmospheric predictive variables. This study provides a full characterization of fog events at this motor-road, in which orographic fog is predominant, causing important traffic problems during all year. We also show how the ELM approach is able to obtain highly accurate low-visibility events predictions, with a Pearson correlation coefficient of 0.8, within a half-hour time horizon, enough to initialize some protocols aiming at reducing the impact of these extreme events in the traffic of the A-8 motor road.

[1]  M. Abdel-Aty,et al.  Analysis of the Impact of Fog-Related Reduced Visibility on Traffic Parameters , 2018 .

[2]  Hongming Zhou,et al.  Extreme Learning Machine for Regression and Multiclass Classification , 2012, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).

[3]  Long-term persistence, invariant time scales and on-off intermittency of fog events , 2021 .

[4]  L. L. Cam,et al.  Maximum likelihood : an introduction , 1990 .

[5]  B. Hayden,et al.  The North Atlantic subtropical anticyclone , 1997 .

[6]  Gary T. Weymouth,et al.  Fog Forecasting for Melbourne Airport Using a Bayesian Decision Network , 2015 .

[7]  Mohammad Bagher Menhaj,et al.  Training feedforward networks with the Marquardt algorithm , 1994, IEEE Trans. Neural Networks.

[8]  R. Rivett,et al.  A Fuzzy Logic Fog Forecasting Model for Perth Airport , 2012, Pure and Applied Geophysics.

[9]  F. Massey.  The Kolmogorov-Smirnov Test for Goodness of Fit , 1951 .

[10]  Hiroyuki Kusaka,et al.  A climatological study of fog in Japan based on event data , 2015 .

[11]  William J. Thompson,et al.  Estimating Marine Fog Probability Using a Model Output Statistics Scheme , 1983 .

[12]  J. Hosking.  L‐Moments: Analysis and Estimation of Distributions Using Linear Combinations of Order Statistics , 1990 .

[13]  Valuación de opciones de tipo de cambio asumiendo distribuciones α-estables , 2013 .

[14]  Sancho Salcedo-Sanz,et al.  Persistence Analysis and Prediction of Low-Visibility Events at Valladolid Airport, Spain , 2020, Symmetry.

[15]  K. Sudheesh,et al.  Statistical analysis on extreme wave height , 2012, Natural Hazards.

[16]  C. Román-Casćon,et al.  Observations and WRF simulations of fog events at the Spanish Northern Plateau , 2012 .

[17]  S. Dorling,et al.  Sub‐km scale numerical weather prediction model simulations of radiation fog , 2020, Quarterly Journal of the Royal Meteorological Society.

[18]  I. Gultepe,et al.  Influence of Quasi-Periodic Oscillation of Atmospheric Variables on Radiation Fog over A Mountainous Region of Korea , 2020, Atmosphere.

[19]  J. Sanz-Justo,et al.  Efficient Prediction of Low-Visibility Events at Airports Using Machine-Learning Regression , 2017, Boundary-Layer Meteorology.

[20]  V. Masson,et al.  Influence of aerosols on the life cycle of a radiation fog event. A numerical and observational study , 2015 .

[21]  Mohamed Abdel-Aty,et al.  Crash risk analysis during fog conditions using real-time traffic data. , 2017, Accident; analysis and prevention.

[22]  Ron Kohavi,et al.  A Study of Cross-Validation and Bootstrap for Accuracy Estimation and Model Selection , 1995, IJCAI.

[23]  Bernard Bobée,et al.  On the tails of extreme event distributions in hydrology , 2008 .

[24]  J. L. Nolan,et al.  Numerical calculation of stable densities and distribution functions: Heavy tails and highly volatil , 1997 .

[25]  Adriano Rogério Bruno Tech,et al.  Application of Artificial Neural Networks for Fog Forecast , 2015 .

[26]  M. Pagowski,et al.  Fog Research: A Review of Past Achievements and Future Perspectives , 2007 .

[27]  John P. Nolan,et al.  Financial modeling with heavy‐tailed stable distributions , 2014 .

[28]  Driss Bari,et al.  Machine-learning regression applied to diagnose horizontal visibility from mesoscale NWP model forecasts , 2020, SN Applied Sciences.

[29]  Jun Du,et al.  Forecast of Low Visibility and Fog from NCEP: Current Status and Efforts , 2012, Pure and Applied Geophysics.

[30]  V. Pisarenko,et al.  The Estimation of Probability of Extreme Events for Small Samples , 2017, Pure and Applied Geophysics.

[31]  Gary R. Weckman,et al.  Selective ensemble based on extreme learning machine and improved discrete artificial fish swarm algorithm for haze forecast , 2017, Applied Intelligence.

[32]  I. Watterson,et al.  Simulated changes due to global warming in daily precipitation means and extremes and their interpretation using the gamma distribution , 2003 .

[33]  Pedro Antonio Gutiérrez,et al.  Prediction of low-visibility events due to fog using ordinal classification , 2018, Atmospheric Research.

[34]  Hong-Jun Cho,et al.  Development of hazardous road fog index and its application , 2005 .

[35]  J. Price,et al.  The Use of Thermal Infra-Red Imagery to Elucidate the Dynamics and Processes Occurring in Fog , 2020, Atmosphere.

[36]  Leslie F Musk,et al.  Climate as a factor in the planning and design of new roads and motorways , 1991 .

[37]  César Hervás-Martínez,et al.  Efficient fog prediction with multi-objective evolutionary neural networks , 2018, Appl. Soft Comput..

[38]  Rory A. Fisher,et al.  Theory of Statistical Estimation , 1925, Mathematical Proceedings of the Cambridge Philosophical Society.

[39]  Olivier Liechti,et al.  Intercomparison of Single-Column Numerical Models for the Prediction of Radiation Fog , 2007 .

[40]  Richard de Dear,et al.  Application of Artificial Neural Network Forecasts to Predict Fog at Canberra International Airport , 2007 .

[41]  Gert-Jan Steeneveld,et al.  Modeling and Forecasting the Onset and Duration of Severe Radiation Fog under Frost Conditions , 2010 .

[42]  G. Katul,et al.  Similarity in Fog and Rainfall Intermittency , 2018, Geophysical Research Letters.

[43]  An Analysis of Fog in the Mainland Portuguese International Airports , 2020 .

[44]  Chee Kheong Siew,et al.  Extreme learning machine: Theory and applications , 2006, Neurocomputing.

[45]  Andrés Merino,et al.  Forecasting of poor visibility episodes in the vicinity of Tenerife Norte Airport , 2019, Atmospheric Research.

[46]  David Peón,et al.  Spread or backwash: The impact on population dynamics and business performance of a new road in a rural county of Galicia (Spain) , 2019, Papers in Regional Science.

[47]  M. Belo-Pereira,et al.  A persistent wintertime fog episode at Lisbon airport (Portugal): performance of ECMWF and AROME models , 2016 .