Using Deep Learning to Predict the Amount of Chemicals Applied on the Wheel Track for Winter Road Maintenance

被引:2
|
作者
Hatamzad, Mahshid [1 ]
Polanco Pinerez, Geanette Cleotilde [1 ]
Casselgren, Johan [2 ]
机构
[1] UiT Arctic Univ Norway, Dept Ind Engn, N-8514 Narvik, Nordland, Norway
[2] Lulea Univ Technol, Dept Engn Sci & Math, S-97187 Lulea, Sweden
来源
APPLIED SCIENCES-BASEL | 2022年 / 12卷 / 07期
关键词
deep neural network; deep learning; intelligent road transportation; prediction model; salting; winter road maintenance; PAVEMENT; IMPACTS; SALT;
D O I
10.3390/app12073508
中图分类号
O6 [化学];
学科分类号
0703 ;
摘要
The decade of big data has emerged in recent years, which has led to entering the era of intelligent transportation. One of the main challenges to deploying intelligent transportation is dealing with winter roads in cold climate countries. Different operations can be used to protect the road from ice and snow, such as spreading chemicals (here salt) on the road surface. Using salt for de-icing and anti-icing increases road safety. However, the excess use of salt must be avoided since it is not cost-efficient and has negative impacts on the environment. Therefore, the accurate and timely prediction of salt quantity for winter road maintenance helps decision support systems to achieve effective and efficient winter road maintenance. Thus, this paper performs exploratory data analysis to determine the relationships among variables to find the best prediction model for this problem. Due to the stochastic nature of variables regarding weather and roads, a deep neural network/deep learning is selected to predict the amount of salt on the wheel track, using historical data measured by sensors and road weather stations. The results show that the proposed model performs perfectly to learn and predict the amount of salt on the wheel track, based on different metrics, including the loss function, scatter plot, mean absolute error, and explained variance.
引用
收藏
页数:14
相关论文
共 50 条
  • [21] Road surface condition classification using deep learning
    Cheng, Lushan
    Zhang, Xu
    Shen, Jie
    JOURNAL OF VISUAL COMMUNICATION AND IMAGE REPRESENTATION, 2019, 64
  • [22] Forest road detection using deep learning models
    Caliskan, Erhan
    Sevim, Yusuf
    GEOCARTO INTERNATIONAL, 2022, 37 (20) : 5875 - 5890
  • [23] Road Damage Detection using Deep Ensemble Learning
    Doshi, Keval
    Yilmaz, Yasin
    2020 IEEE INTERNATIONAL CONFERENCE ON BIG DATA (BIG DATA), 2020, : 5540 - 5544
  • [24] Using solar-induced chlorophyll fluorescence to predict winter wheat actual evapotranspiration through machine learning and deep learning methods
    Li, Yao
    Liu, Xuanang
    Zhang, Xuegui
    Gu, Xiaobo
    Yu, Lianyu
    Cai, Huanjie
    Peng, Xiongbiao
    AGRICULTURAL WATER MANAGEMENT, 2025, 309
  • [25] Assessing the safety impacts of winter road maintenance operations using connected vehicle data
    Oh, Minsoo
    Dong-O'Brien, Jing
    ACCIDENT ANALYSIS AND PREVENTION, 2025, 209
  • [26] A Hybrid Deep Learning Approach for Vehicle Wheel Slip Prediction in Off-Road Environments
    Basri, Mustofa
    Karapetyan, Areg
    Hassan, Bilal
    Khonji, Majid
    Dias, Jorge
    2022 IEEE INTERNATIONAL SYMPOSIUM ON ROBOTIC AND SENSORS ENVIRONMENTS (ROSE), 2022,
  • [27] Using deep learning to predict human decisions and using cognitive models to explain deep learning models
    Fintz, Matan
    Osadchy, Margarita
    Hertz, Uri
    SCIENTIFIC REPORTS, 2022, 12 (01)
  • [28] A Methodology for Maintenance Analysis and Modeling Using Deep Learning
    Okaro, Ikenna Anthony
    van der Burgt, Olaf
    2023 ANNUAL RELIABILITY AND MAINTAINABILITY SYMPOSIUM, RAMS, 2023,
  • [29] Deep Learning Using Electrocardiograms in Patients on Maintenance Dialysis
    Zheng, Zhong
    Soomro, Qandeel H.
    Charytan, David M.
    ADVANCES IN KIDNEY DISEASE AND HEALTH, 2023, 30 (01): : 61 - 68
  • [30] Using deep learning to predict human decisions and using cognitive models to explain deep learning models
    Matan Fintz
    Margarita Osadchy
    Uri Hertz
    Scientific Reports, 12