Predicting road flooding risk with crowdsourced reports and fine-grained traffic data
Abstract The objective of this study is to predict road flooding risks based on topographic, hydrologic, and temporal precipitation features using machine learning models. Existing road inundation studies either lack empirical data for model validations or focus mainly on road inundation exposure as...
Main Authors: | , , , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Springer
2023-03-01
|
Series: | Computational Urban Science |
Subjects: | |
Online Access: | https://doi.org/10.1007/s43762-023-00082-1 |
_version_ | 1797865295371567104 |
---|---|
author | Faxi Yuan Cheng-Chun Lee William Mobley Hamed Farahmand Yuanchang Xu Russell Blessing Shangjia Dong Ali Mostafavi Samuel D. Brody |
author_facet | Faxi Yuan Cheng-Chun Lee William Mobley Hamed Farahmand Yuanchang Xu Russell Blessing Shangjia Dong Ali Mostafavi Samuel D. Brody |
author_sort | Faxi Yuan |
collection | DOAJ |
description | Abstract The objective of this study is to predict road flooding risks based on topographic, hydrologic, and temporal precipitation features using machine learning models. Existing road inundation studies either lack empirical data for model validations or focus mainly on road inundation exposure assessment based on flood maps. This study addresses this limitation by using crowdsourced and fine-grained traffic data as an indicator of road inundation, and topographic, hydrologic, and temporal precipitation features as predictor variables. Two tree-based machine learning models (random forest and AdaBoost) were then tested and trained for predicting road inundations in the contexts of 2017 Hurricane Harvey and 2019 Tropical Storm Imelda in Harris County, Texas. The findings from Hurricane Harvey indicate that precipitation is the most important feature for predicting road inundation susceptibility, and that topographic features are more critical than hydrologic features for predicting road inundations in both storm cases. The random forest and AdaBoost models had relatively high AUC scores (0.860 and 0.810 for Harvey respectively and 0.790 and 0.720 for Imelda respectively) with the random forest model performing better in both cases. The random forest model showed stable performance for Harvey, while varying significantly for Imelda. This study advances the emerging field of smart flood resilience in terms of predictive flood risk mapping at the road level. In particular, such models could help impacted communities and emergency management agencies develop better preparedness and response strategies with improved situational awareness of road inundation likelihood as an extreme weather event unfolds. |
first_indexed | 2024-04-09T23:06:31Z |
format | Article |
id | doaj.art-9fe750a8adfa429197bf4a1a973f2fe5 |
institution | Directory Open Access Journal |
issn | 2730-6852 |
language | English |
last_indexed | 2024-04-09T23:06:31Z |
publishDate | 2023-03-01 |
publisher | Springer |
record_format | Article |
series | Computational Urban Science |
spelling | doaj.art-9fe750a8adfa429197bf4a1a973f2fe52023-03-22T10:41:59ZengSpringerComputational Urban Science2730-68522023-03-013111610.1007/s43762-023-00082-1Predicting road flooding risk with crowdsourced reports and fine-grained traffic dataFaxi Yuan0Cheng-Chun Lee1William Mobley2Hamed Farahmand3Yuanchang Xu4Russell Blessing5Shangjia Dong6Ali Mostafavi7Samuel D. Brody8Advanced Analytics, MAPFRE InsuranceZachry Department of Civil and Environmental Engineering, Urban Resilience.AI Lab, Texas A&M UniversityDepartment of Marine Sciences, Texas A&M University at GalvestonZachry Department of Civil and Environmental Engineering, Urban Resilience.AI Lab, Texas A&M UniversityZachry Department of Civil and Environmental Engineering, Urban Resilience.AI Lab, Texas A&M UniversityDepartment of Marine Sciences, Texas A&M University at GalvestonDepartment of Civil and Environmental Engineering, University of DelawareZachry Department of Civil and Environmental Engineering, Urban Resilience.AI Lab, Texas A&M UniversityDepartment of Marine and Coastal Environmental Science, Texas A&M University at GalvestonAbstract The objective of this study is to predict road flooding risks based on topographic, hydrologic, and temporal precipitation features using machine learning models. Existing road inundation studies either lack empirical data for model validations or focus mainly on road inundation exposure assessment based on flood maps. This study addresses this limitation by using crowdsourced and fine-grained traffic data as an indicator of road inundation, and topographic, hydrologic, and temporal precipitation features as predictor variables. Two tree-based machine learning models (random forest and AdaBoost) were then tested and trained for predicting road inundations in the contexts of 2017 Hurricane Harvey and 2019 Tropical Storm Imelda in Harris County, Texas. The findings from Hurricane Harvey indicate that precipitation is the most important feature for predicting road inundation susceptibility, and that topographic features are more critical than hydrologic features for predicting road inundations in both storm cases. The random forest and AdaBoost models had relatively high AUC scores (0.860 and 0.810 for Harvey respectively and 0.790 and 0.720 for Imelda respectively) with the random forest model performing better in both cases. The random forest model showed stable performance for Harvey, while varying significantly for Imelda. This study advances the emerging field of smart flood resilience in terms of predictive flood risk mapping at the road level. In particular, such models could help impacted communities and emergency management agencies develop better preparedness and response strategies with improved situational awareness of road inundation likelihood as an extreme weather event unfolds.https://doi.org/10.1007/s43762-023-00082-1Smart resilienceRoad flood riskMachine learningBig dataUrban flood |
spellingShingle | Faxi Yuan Cheng-Chun Lee William Mobley Hamed Farahmand Yuanchang Xu Russell Blessing Shangjia Dong Ali Mostafavi Samuel D. Brody Predicting road flooding risk with crowdsourced reports and fine-grained traffic data Computational Urban Science Smart resilience Road flood risk Machine learning Big data Urban flood |
title | Predicting road flooding risk with crowdsourced reports and fine-grained traffic data |
title_full | Predicting road flooding risk with crowdsourced reports and fine-grained traffic data |
title_fullStr | Predicting road flooding risk with crowdsourced reports and fine-grained traffic data |
title_full_unstemmed | Predicting road flooding risk with crowdsourced reports and fine-grained traffic data |
title_short | Predicting road flooding risk with crowdsourced reports and fine-grained traffic data |
title_sort | predicting road flooding risk with crowdsourced reports and fine grained traffic data |
topic | Smart resilience Road flood risk Machine learning Big data Urban flood |
url | https://doi.org/10.1007/s43762-023-00082-1 |
work_keys_str_mv | AT faxiyuan predictingroadfloodingriskwithcrowdsourcedreportsandfinegrainedtrafficdata AT chengchunlee predictingroadfloodingriskwithcrowdsourcedreportsandfinegrainedtrafficdata AT williammobley predictingroadfloodingriskwithcrowdsourcedreportsandfinegrainedtrafficdata AT hamedfarahmand predictingroadfloodingriskwithcrowdsourcedreportsandfinegrainedtrafficdata AT yuanchangxu predictingroadfloodingriskwithcrowdsourcedreportsandfinegrainedtrafficdata AT russellblessing predictingroadfloodingriskwithcrowdsourcedreportsandfinegrainedtrafficdata AT shangjiadong predictingroadfloodingriskwithcrowdsourcedreportsandfinegrainedtrafficdata AT alimostafavi predictingroadfloodingriskwithcrowdsourcedreportsandfinegrainedtrafficdata AT samueldbrody predictingroadfloodingriskwithcrowdsourcedreportsandfinegrainedtrafficdata |