Estimating the impact of high-fidelity rainfall data on traffic conditions and traffic prediction
Accurate prediction of network-level traffic parameters during inclement weather conditions can greatly help in many transportation applications. Rainfall tends to have a quantifiable impact on driving behavior and traffic network performance. This impact is often studied for low-resolution rainfall...
| Main Authors: | , , , , , , |
|---|---|
| Other Authors: | |
| Format: | Journal Article |
| Language: | English |
| Published: |
2022
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/161883 |
| _version_ | 1811677200812867584 |
|---|---|
| author | Prokhorchuk, Anatolii Mitrovic, Nikola Muhammad Usman Stevanovic, Aleksandar Muhammad Tayyab Asif Dauwels, Justin Jaillet, Patrick |
| author2 | School of Electrical and Electronic Engineering |
| author_facet | School of Electrical and Electronic Engineering Prokhorchuk, Anatolii Mitrovic, Nikola Muhammad Usman Stevanovic, Aleksandar Muhammad Tayyab Asif Dauwels, Justin Jaillet, Patrick |
| author_sort | Prokhorchuk, Anatolii |
| collection | NTU |
| description | Accurate prediction of network-level traffic parameters during inclement weather conditions can greatly help in many transportation applications. Rainfall tends to have a quantifiable impact on driving behavior and traffic network performance. This impact is often studied for low-resolution rainfall data on small road networks, whereas this study investigates it in the context of a large traffic network and high-resolution rainfall radar images. First, the impact of rainfall intensity on traffic performance throughout the day and for different road categories is analyzed. Next, it is investigated whether including rainfall information can improve the predictive accuracy of the state-of-the-art traffic forecasting methods. Numerical results show that the impact of rainfall on traffic varies for different rainfall intensities as well as for different times of the day and days of the week. The results also show that incorporating rainfall data into prediction models improves their overall performance. The average reduction in mean absolute percentage error (MAPE) for models with rainfall data is 4.5%. Experiments with downsampled rainfall data were also performed, and it was concluded that incorporating higher resolution weather data does indeed lead to an increase in performance of traffic prediction models. |
| first_indexed | 2024-10-01T02:33:36Z |
| format | Journal Article |
| id | ntu-10356/161883 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2024-10-01T02:33:36Z |
| publishDate | 2022 |
| record_format | dspace |
| spelling | ntu-10356/1618832022-09-23T02:03:52Z Estimating the impact of high-fidelity rainfall data on traffic conditions and traffic prediction Prokhorchuk, Anatolii Mitrovic, Nikola Muhammad Usman Stevanovic, Aleksandar Muhammad Tayyab Asif Dauwels, Justin Jaillet, Patrick School of Electrical and Electronic Engineering Engineering::Electrical and electronic engineering Flow Speed Accurate prediction of network-level traffic parameters during inclement weather conditions can greatly help in many transportation applications. Rainfall tends to have a quantifiable impact on driving behavior and traffic network performance. This impact is often studied for low-resolution rainfall data on small road networks, whereas this study investigates it in the context of a large traffic network and high-resolution rainfall radar images. First, the impact of rainfall intensity on traffic performance throughout the day and for different road categories is analyzed. Next, it is investigated whether including rainfall information can improve the predictive accuracy of the state-of-the-art traffic forecasting methods. Numerical results show that the impact of rainfall on traffic varies for different rainfall intensities as well as for different times of the day and days of the week. The results also show that incorporating rainfall data into prediction models improves their overall performance. The average reduction in mean absolute percentage error (MAPE) for models with rainfall data is 4.5%. Experiments with downsampled rainfall data were also performed, and it was concluded that incorporating higher resolution weather data does indeed lead to an increase in performance of traffic prediction models. National Research Foundation (NRF) Singapore-MIT Alliance for Research and Technology (SMART) This work was partially supported by the Singapore National Research Foundation through the Singapore-MIT Alliance for Research and Technology (SMART) Centre for Future Urban Mobility (FM). 2022-09-23T02:03:52Z 2022-09-23T02:03:52Z 2021 Journal Article Prokhorchuk, A., Mitrovic, N., Muhammad Usman, Stevanovic, A., Muhammad Tayyab Asif, Dauwels, J. & Jaillet, P. (2021). Estimating the impact of high-fidelity rainfall data on traffic conditions and traffic prediction. Transportation Research Record, 2675(11), 1285-1300. https://dx.doi.org/10.1177/03611981211026309 0361-1981 https://hdl.handle.net/10356/161883 10.1177/03611981211026309 2-s2.0-85120048334 11 2675 1285 1300 en Transportation Research Record © 2021 National Academy of Sciences. All rights reserved. |
| spellingShingle | Engineering::Electrical and electronic engineering Flow Speed Prokhorchuk, Anatolii Mitrovic, Nikola Muhammad Usman Stevanovic, Aleksandar Muhammad Tayyab Asif Dauwels, Justin Jaillet, Patrick Estimating the impact of high-fidelity rainfall data on traffic conditions and traffic prediction |
| title | Estimating the impact of high-fidelity rainfall data on traffic conditions and traffic prediction |
| title_full | Estimating the impact of high-fidelity rainfall data on traffic conditions and traffic prediction |
| title_fullStr | Estimating the impact of high-fidelity rainfall data on traffic conditions and traffic prediction |
| title_full_unstemmed | Estimating the impact of high-fidelity rainfall data on traffic conditions and traffic prediction |
| title_short | Estimating the impact of high-fidelity rainfall data on traffic conditions and traffic prediction |
| title_sort | estimating the impact of high fidelity rainfall data on traffic conditions and traffic prediction |
| topic | Engineering::Electrical and electronic engineering Flow Speed |
| url | https://hdl.handle.net/10356/161883 |
| work_keys_str_mv | AT prokhorchukanatolii estimatingtheimpactofhighfidelityrainfalldataontrafficconditionsandtrafficprediction AT mitrovicnikola estimatingtheimpactofhighfidelityrainfalldataontrafficconditionsandtrafficprediction AT muhammadusman estimatingtheimpactofhighfidelityrainfalldataontrafficconditionsandtrafficprediction AT stevanovicaleksandar estimatingtheimpactofhighfidelityrainfalldataontrafficconditionsandtrafficprediction AT muhammadtayyabasif estimatingtheimpactofhighfidelityrainfalldataontrafficconditionsandtrafficprediction AT dauwelsjustin estimatingtheimpactofhighfidelityrainfalldataontrafficconditionsandtrafficprediction AT jailletpatrick estimatingtheimpactofhighfidelityrainfalldataontrafficconditionsandtrafficprediction |