Predicting combined tidal and pluvial flood inundation using a machine learning surrogate model
Flooding increases in recent years, in particular for coastal communities facing sea level rise, have brought renewed attention to real-time, street-scale flood forecasting. Such flood models using conventional physics-based modeling approaches are often unrealistic for real-time decision support us...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2022-06-01
|
| Series: | Journal of Hydrology: Regional Studies |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2214581822001008 |
| _version_ | 1818253999563866112 |
|---|---|
| author | Faria T. Zahura Jonathan L. Goodall |
| author_facet | Faria T. Zahura Jonathan L. Goodall |
| author_sort | Faria T. Zahura |
| collection | DOAJ |
| description | Flooding increases in recent years, in particular for coastal communities facing sea level rise, have brought renewed attention to real-time, street-scale flood forecasting. Such flood models using conventional physics-based modeling approaches are often unrealistic for real-time decision support use cases due to their long model runtime. Machine learning offers an alternative strategy whereby a surrogate model can be trained to mimic relationships present within the physics-based model and, after training, can run in seconds rather than hours. This study used the Random Forest (RF) algorithm to emulate a 1D/2D physics-based model simulating surface water depths in an urban coastal watershed in Norfolk, Virginia. Environmental features from a selected set of pluvial and tidal flood events and topographic information of the roadway were the input variables to train the surrogate model. Results show the potential for the surrogate model to predict flood extent and depth for both pluvial and tidal flood events. Furthermore, the surrogate model can differentiate between flooding locations dominated by pluvial or tidal flooding or impacted by both flooding mechanisms. Flood reports from the mobile app Waze were used for model validation and show 90% agreement with flooding locations from the surrogate model. Finally, feature importance methods were investigated to interpret the performance of the RF models and understand the contribution of different physical features to localized flooding. |
| first_indexed | 2024-12-12T16:49:00Z |
| format | Article |
| id | doaj.art-6a8440e849fb4073bef669d2ad831514 |
| institution | Directory Open Access Journal |
| issn | 2214-5818 |
| language | English |
| last_indexed | 2024-12-12T16:49:00Z |
| publishDate | 2022-06-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Journal of Hydrology: Regional Studies |
| spelling | doaj.art-6a8440e849fb4073bef669d2ad8315142022-12-22T00:18:25ZengElsevierJournal of Hydrology: Regional Studies2214-58182022-06-0141101087Predicting combined tidal and pluvial flood inundation using a machine learning surrogate modelFaria T. Zahura0Jonathan L. Goodall1Department of Engineering Systems and Environment, University of Virginia, 151 Engineers Way, Charlottesville, VA 22904, USA; Link Lab, School of Engineering and Applied Sciences, University of Virginia, Charlottesville, VA, USADepartment of Engineering Systems and Environment, University of Virginia, 151 Engineers Way, Charlottesville, VA 22904, USA; Link Lab, School of Engineering and Applied Sciences, University of Virginia, Charlottesville, VA, USA; Correspondence to: Link Lab, 2nd floor of Olsson Hall, 151 Engineers Way, Charlottesville, VA 22904, USA.Flooding increases in recent years, in particular for coastal communities facing sea level rise, have brought renewed attention to real-time, street-scale flood forecasting. Such flood models using conventional physics-based modeling approaches are often unrealistic for real-time decision support use cases due to their long model runtime. Machine learning offers an alternative strategy whereby a surrogate model can be trained to mimic relationships present within the physics-based model and, after training, can run in seconds rather than hours. This study used the Random Forest (RF) algorithm to emulate a 1D/2D physics-based model simulating surface water depths in an urban coastal watershed in Norfolk, Virginia. Environmental features from a selected set of pluvial and tidal flood events and topographic information of the roadway were the input variables to train the surrogate model. Results show the potential for the surrogate model to predict flood extent and depth for both pluvial and tidal flood events. Furthermore, the surrogate model can differentiate between flooding locations dominated by pluvial or tidal flooding or impacted by both flooding mechanisms. Flood reports from the mobile app Waze were used for model validation and show 90% agreement with flooding locations from the surrogate model. Finally, feature importance methods were investigated to interpret the performance of the RF models and understand the contribution of different physical features to localized flooding.http://www.sciencedirect.com/science/article/pii/S2214581822001008Coastal floodingMachine learningSurrogate modelingFlood modeling |
| spellingShingle | Faria T. Zahura Jonathan L. Goodall Predicting combined tidal and pluvial flood inundation using a machine learning surrogate model Journal of Hydrology: Regional Studies Coastal flooding Machine learning Surrogate modeling Flood modeling |
| title | Predicting combined tidal and pluvial flood inundation using a machine learning surrogate model |
| title_full | Predicting combined tidal and pluvial flood inundation using a machine learning surrogate model |
| title_fullStr | Predicting combined tidal and pluvial flood inundation using a machine learning surrogate model |
| title_full_unstemmed | Predicting combined tidal and pluvial flood inundation using a machine learning surrogate model |
| title_short | Predicting combined tidal and pluvial flood inundation using a machine learning surrogate model |
| title_sort | predicting combined tidal and pluvial flood inundation using a machine learning surrogate model |
| topic | Coastal flooding Machine learning Surrogate modeling Flood modeling |
| url | http://www.sciencedirect.com/science/article/pii/S2214581822001008 |
| work_keys_str_mv | AT fariatzahura predictingcombinedtidalandpluvialfloodinundationusingamachinelearningsurrogatemodel AT jonathanlgoodall predictingcombinedtidalandpluvialfloodinundationusingamachinelearningsurrogatemodel |