PURPOSES : The purpose of this study was to develop techniques for forecasting black ice using historical pavement temperature data collected by patrol cars and concurrent atmospheric data provided by the Korea Meteorological Administration.
METHODS : To generate baseline data, the physical principle that ice forms when the pavement temperature is negative and lower than the dew-point temperature was exploited. To forecast frost-induced black ice, deep-learning algorithms were created using air, pavement, and dew point temperatures, as well as humidity, wind speed, and the z-value of the historical pavement temperature of the target segment.
RESULTS : The suggested forecasting models were evaluated against baseline data generated by the above-mentioned physical principle using pavement temperature and atmospheric data gathered on a national highway in the vicinity of Young-dong in the Chungcheongbukdo province. The accuracies of the forecasting models for the bridge and roadway segments were 94% and 90%, respectively, indicating satisfactory results.
CONCLUSIONS : Preventive anti-icing maintenance activities, such as applying anti-icing chemicals or activating road heating systems before roadways are covered with ice (frost), could be possible with the suggested methodologies. As a result, traffic safety on winter roads, especially at night, could be enhanced.

ABSTRACT
1. 서론
2. 방법론
    2.1. 도로살얼음 예측 방법론
    2.2. 도로살얼음 예측정보 평가를 위한 기준값 산출
3. 노면온도 데이터
    3.1. 데이터 수집
    3.2. 노면온도 데이터 특성 분석
4. 도로살얼음 예측
    4.1. 딥러닝 기반 예측모형 구축
    4.2. 예측모형 평가
5. 결론
REFERENCES

• 장진환(한국건설기술연구원 도로교통연구본부 연구위원) | Jang Jinhwan Corresponding Author