Development of black ice prediction model using GIS-based multi-sensor model validation

Abstract

Abstract. Fog, freezing rain, and snow (melt) quickly condense on road surfaces, forming black ice that is difficult to identify and causes major accidents on highways. As a countermeasure to prevent icing car accidents, it is necessary to predict the amount and location of black ice. This study advanced previous models through machine learning and multi-sensor-verified results. Using spatial (hill shade, river system, bridge, and highway) and meteorological (air temperature, cloudiness, vapour pressure, wind speed, precipitation, snow cover, specific heat, latent heat, and solar radiation energy) data from the study area (Suncheon–Wanju Highway in Gurye-gun, Jeollanam-do, South Korea), the amount and location of black ice were modelled based on system dynamics to predict black ice and then simulated with a geographic information system in units of square metres. The intermediate factors calculated as input factors were road temperature and road moisture, modelled using a deep neural network (DNN) and numerical methods. Considering the results of the DNN, the root mean square error was improved by 148.6 % and reliability by 11.43 % compared to a previous study (linear regression). Based on the model results, multiple sensors were buried at four selected points in the study area. The model was compared with sensor data and verified with the upper-tailed test (with a significance level of 0.05) and fast Fourier transform (freezing does not occur when frequency = 0.00001 Hz). Results of the verified simulation can provide valuable data for government agencies like road traffic authorities to prevent traffic accidents caused by black ice.

Predicting black ice-related accidents with probabilistic modeling using GIS-based Monte Carlo simulation

“…By analyzing various contextual elements over time, the likelihood of black ice formation at specific times and locations can be predicted more precisely. Examples include "risk management through the analysis of similarities in context history [ 49 ], predictive models in a computing environment based on context history data [ 13 , 14 , 50 ], techniques for searching and monitoring sequential patterns in a context history database [ 51 ], and studies supporting the development of individual worker competencies based on context history [ 52 ]." Such approaches offer new strategies for road safety management related to black ice.…”

“…Each corresponding factor, denoted as AT N , CL N , HS N , and BL N , was normalized and input into the function. The parameters W1, W2, W3, and b were multiplied by each input factor (AT, CL, and HS) and determined based on Hong et al [ 13 ]. In this study, we established a regression equation for the road temperature using the air temperature, cloud cover, and hill shade as input factors.…”

“…They provided intuitive prediction data regarding black ice events using a GIS [ 14 ]. In addition, following their study [ 14 ] estimated the number of black ice occurrences based on system dynamics, Hong et al further refined their model by adding specific heat, latent heat, solar radiation (per hour), and snow (melted amount) as input factors to the numerical model and incorporating the concept of artificial neural networks for estimating the road temperature [ 13 ]. After analyzing prior studies, it was found that, overall, predictions for accidents caused by black ice are scarce and weather factors are limited by their dependence on time.…”

“…The aim of this study is to predict black ice accidents at each point through a Monte Carlo simulation on a GIS and to analyze the degree of the likelihood of an accident occurrence for each black ice incident. Unlike in previous studies, time-independent results were derived using Monte Carlo simulations based on random variables [ 13 ]. In contrast to a previous black ice study [ 14 ] that used fixed-time data for predictions, in this study, the results were derived over a broader time range owing to time invariance.…”