Evaluation of residential building damage for the July 2021 flood in Westport, New Zealand
Abstract Reliable flood damage models are informed by detailed damage assessments. Damage models are critical in flood risk assessments, representing an elements vulnerability to damage. This study evaluated residential building damage for the July 2021 flood in Westport, New Zealand. We report on f...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
SpringerOpen
2024-03-01
|
| Series: | Geoscience Letters |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s40562-024-00323-z |
| _version_ | 1827310167681662976 |
|---|---|
| author | Ryan Paulik Alec Wild Conrad Zorn Liam Wotherspoon Shaun Williams |
| author_facet | Ryan Paulik Alec Wild Conrad Zorn Liam Wotherspoon Shaun Williams |
| author_sort | Ryan Paulik |
| collection | DOAJ |
| description | Abstract Reliable flood damage models are informed by detailed damage assessments. Damage models are critical in flood risk assessments, representing an elements vulnerability to damage. This study evaluated residential building damage for the July 2021 flood in Westport, New Zealand. We report on flood hazard, exposure and damage features observed for 247 residential buildings. Damage samples were applied to evaluate univariable and multivariable model performance using different variable sample sizes and regression-based supervised learning algorithms. Feature analysis for damage prediction showed high importance of water depth variables and low importance for commonly observed building variables such as structural frame and storeys. Overfitting occurred for most models evaluated when more than 150 samples were used. This resulted from limited damage heterogeneity observed, and variables of low importance affecting model learning. The Random Forest algorithm, which considered multiple important variables (water depth above floor level, area and floor height) improved predictive precision by 17% relative to other models when over 150 damage samples were considered. Our findings suggest the evaluated model performance could be improved by incorporating heterogeneous damage samples from similar flood contexts, in turn increasing capacity for reliable spatial transfer. |
| first_indexed | 2024-04-24T19:55:19Z |
| format | Article |
| id | doaj.art-c73bf949b847499b8f036fdf74b5cecc |
| institution | Directory Open Access Journal |
| issn | 2196-4092 |
| language | English |
| last_indexed | 2024-04-24T19:55:19Z |
| publishDate | 2024-03-01 |
| publisher | SpringerOpen |
| record_format | Article |
| series | Geoscience Letters |
| spelling | doaj.art-c73bf949b847499b8f036fdf74b5cecc2024-03-24T12:22:43ZengSpringerOpenGeoscience Letters2196-40922024-03-0111111210.1186/s40562-024-00323-zEvaluation of residential building damage for the July 2021 flood in Westport, New ZealandRyan Paulik0Alec Wild1Conrad Zorn2Liam Wotherspoon3Shaun Williams4Department of Civil and Environmental Engineering, Faculty of Engineering, University of AucklandAonDepartment of Civil and Environmental Engineering, Faculty of Engineering, University of AucklandDepartment of Civil and Environmental Engineering, Faculty of Engineering, University of AucklandNational Institute of Water and Atmospheric ResearchAbstract Reliable flood damage models are informed by detailed damage assessments. Damage models are critical in flood risk assessments, representing an elements vulnerability to damage. This study evaluated residential building damage for the July 2021 flood in Westport, New Zealand. We report on flood hazard, exposure and damage features observed for 247 residential buildings. Damage samples were applied to evaluate univariable and multivariable model performance using different variable sample sizes and regression-based supervised learning algorithms. Feature analysis for damage prediction showed high importance of water depth variables and low importance for commonly observed building variables such as structural frame and storeys. Overfitting occurred for most models evaluated when more than 150 samples were used. This resulted from limited damage heterogeneity observed, and variables of low importance affecting model learning. The Random Forest algorithm, which considered multiple important variables (water depth above floor level, area and floor height) improved predictive precision by 17% relative to other models when over 150 damage samples were considered. Our findings suggest the evaluated model performance could be improved by incorporating heterogeneous damage samples from similar flood contexts, in turn increasing capacity for reliable spatial transfer.https://doi.org/10.1186/s40562-024-00323-zFloodDamageResidential buildingUnivariable modelMultivariable model |
| spellingShingle | Ryan Paulik Alec Wild Conrad Zorn Liam Wotherspoon Shaun Williams Evaluation of residential building damage for the July 2021 flood in Westport, New Zealand Geoscience Letters Flood Damage Residential building Univariable model Multivariable model |
| title | Evaluation of residential building damage for the July 2021 flood in Westport, New Zealand |
| title_full | Evaluation of residential building damage for the July 2021 flood in Westport, New Zealand |
| title_fullStr | Evaluation of residential building damage for the July 2021 flood in Westport, New Zealand |
| title_full_unstemmed | Evaluation of residential building damage for the July 2021 flood in Westport, New Zealand |
| title_short | Evaluation of residential building damage for the July 2021 flood in Westport, New Zealand |
| title_sort | evaluation of residential building damage for the july 2021 flood in westport new zealand |
| topic | Flood Damage Residential building Univariable model Multivariable model |
| url | https://doi.org/10.1186/s40562-024-00323-z |
| work_keys_str_mv | AT ryanpaulik evaluationofresidentialbuildingdamageforthejuly2021floodinwestportnewzealand AT alecwild evaluationofresidentialbuildingdamageforthejuly2021floodinwestportnewzealand AT conradzorn evaluationofresidentialbuildingdamageforthejuly2021floodinwestportnewzealand AT liamwotherspoon evaluationofresidentialbuildingdamageforthejuly2021floodinwestportnewzealand AT shaunwilliams evaluationofresidentialbuildingdamageforthejuly2021floodinwestportnewzealand |