A transferable remote sensing approach to classify building structural types for seismic risk analyses: the case of Val d'Agri area (Italy).
Saved in:
| Title: | A transferable remote sensing approach to classify building structural types for seismic risk analyses: the case of Val d'Agri area (Italy). |
|---|---|
| Authors: | Liuzzi, Mariangela1 (AUTHOR) mariangelaliuzzi88@gmail.com, Aravena Pelizari, Patrick2 (AUTHOR), Geiß, Christian2 (AUTHOR), Masi, Angelo1 (AUTHOR), Tramutoli, Valerio1 (AUTHOR), Taubenböck, Hannes2 (AUTHOR) |
| Source: | Bulletin of Earthquake Engineering. Sep2019, Vol. 17 Issue 9, p4825-4853. 29p. |
| Subject Terms: | *Earthquake resistant design, *Remote sensing, *Risk assessment, *Case studies, *Feature selection, *Urban morphology |
| Geographic Terms: | Italy |
| Abstract: | This study proposes a methodology based on machine learning (ML) algorithms for rapid and robust classification of building structural types (STs) in multispectral remote sensing imagery aiming to assess buildings' seismic vulnerability. The seismic behavior of buildings is strongly affected by the ST, including material, age, height, and other main structural features. Previous works deployed in situ data integrated with remote sensing information to statistically infer STs through supervised ML methods. We propose a transferable methodology with specific focus on situations with imbalanced in situ data (i.e., the number of available labeled samples for model learning differs largely between different STs). We learn a transferable model by selecting features from an exhaustive set. The transferability relies on deploying geometric features characterizing individual buildings; thus, the model is less sensitive to domain adaption problems frequently induced by e.g., changes in acquisition parameters of remotely sensed imagery. Thereby, we show that few geometry features enable generalization capabilities similar to models learned with a large number of features describing spectral, geometrical or contextual building properties. We rely on an extensive geodatabase containing almost 18,000 building footprints. We follow a Random Forest (RF)-based feature selection strategy to objectively identify most valuable features for prediction. Furthermore, the problem of unbalanced classes is addressed by adopting two approaches: downsampling the majority class and modifying the classifier internally (weighted RF). The implemented model is transferred on the challenging urban morphology of the Val d'Agri area (Italy). Results confirm the statistical robustness of the model and the importance of the geometry features, allowing for reliable identification of STs. [ABSTRACT FROM AUTHOR] |
| Database: | Energy & Power Source |
|
Full text is not displayed to guests.
Login for full access.
|
|
| FullText | Links: – Type: pdflink Text: Availability: 1 |
|---|---|
| Header | DbId: enr DbLabel: Energy & Power Source An: 138029345 AccessLevel: 6 PubType: Academic Journal PubTypeId: academicJournal PreciseRelevancyScore: 0 |
| IllustrationInfo | |
| Items | – Name: Title Label: Title Group: Ti Data: A transferable remote sensing approach to classify building structural types for seismic risk analyses: the case of Val d'Agri area (Italy). – Name: Author Label: Authors Group: Au Data: <searchLink fieldCode="AR" term="%22Liuzzi%2C+Mariangela%22">Liuzzi, Mariangela</searchLink><relatesTo>1</relatesTo> (AUTHOR)<i> mariangelaliuzzi88@gmail.com</i><br /><searchLink fieldCode="AR" term="%22Aravena+Pelizari%2C+Patrick%22">Aravena Pelizari, Patrick</searchLink><relatesTo>2</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Geiß%2C+Christian%22">Geiß, Christian</searchLink><relatesTo>2</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Masi%2C+Angelo%22">Masi, Angelo</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Tramutoli%2C+Valerio%22">Tramutoli, Valerio</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Taubenböck%2C+Hannes%22">Taubenböck, Hannes</searchLink><relatesTo>2</relatesTo> (AUTHOR) – Name: TitleSource Label: Source Group: Src Data: <searchLink fieldCode="JN" term="%22Bulletin+of+Earthquake+Engineering%22">Bulletin of Earthquake Engineering</searchLink>. Sep2019, Vol. 17 Issue 9, p4825-4853. 29p. – Name: Subject Label: Subject Terms Group: Su Data: *<searchLink fieldCode="DE" term="%22Earthquake+resistant+design%22">Earthquake resistant design</searchLink><br />*<searchLink fieldCode="DE" term="%22Remote+sensing%22">Remote sensing</searchLink><br />*<searchLink fieldCode="DE" term="%22Risk+assessment%22">Risk assessment</searchLink><br />*<searchLink fieldCode="DE" term="%22Case+studies%22">Case studies</searchLink><br />*<searchLink fieldCode="DE" term="%22Feature+selection%22">Feature selection</searchLink><br />*<searchLink fieldCode="DE" term="%22Urban+morphology%22">Urban morphology</searchLink> – Name: SubjectGeographic Label: Geographic Terms Group: Su Data: <searchLink fieldCode="DE" term="%22Italy%22">Italy</searchLink> – Name: Abstract Label: Abstract Group: Ab Data: This study proposes a methodology based on machine learning (ML) algorithms for rapid and robust classification of building structural types (STs) in multispectral remote sensing imagery aiming to assess buildings' seismic vulnerability. The seismic behavior of buildings is strongly affected by the ST, including material, age, height, and other main structural features. Previous works deployed in situ data integrated with remote sensing information to statistically infer STs through supervised ML methods. We propose a transferable methodology with specific focus on situations with imbalanced in situ data (i.e., the number of available labeled samples for model learning differs largely between different STs). We learn a transferable model by selecting features from an exhaustive set. The transferability relies on deploying geometric features characterizing individual buildings; thus, the model is less sensitive to domain adaption problems frequently induced by e.g., changes in acquisition parameters of remotely sensed imagery. Thereby, we show that few geometry features enable generalization capabilities similar to models learned with a large number of features describing spectral, geometrical or contextual building properties. We rely on an extensive geodatabase containing almost 18,000 building footprints. We follow a Random Forest (RF)-based feature selection strategy to objectively identify most valuable features for prediction. Furthermore, the problem of unbalanced classes is addressed by adopting two approaches: downsampling the majority class and modifying the classifier internally (weighted RF). The implemented model is transferred on the challenging urban morphology of the Val d'Agri area (Italy). Results confirm the statistical robustness of the model and the importance of the geometry features, allowing for reliable identification of STs. [ABSTRACT FROM AUTHOR] |
| PLink | https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=enr&AN=138029345 |
| RecordInfo | BibRecord: BibEntity: Identifiers: – Type: doi Value: 10.1007/s10518-019-00648-7 Languages: – Code: eng Text: English PhysicalDescription: Pagination: PageCount: 29 StartPage: 4825 Subjects: – SubjectFull: Earthquake resistant design Type: general – SubjectFull: Remote sensing Type: general – SubjectFull: Risk assessment Type: general – SubjectFull: Case studies Type: general – SubjectFull: Feature selection Type: general – SubjectFull: Urban morphology Type: general – SubjectFull: Italy Type: general Titles: – TitleFull: A transferable remote sensing approach to classify building structural types for seismic risk analyses: the case of Val d'Agri area (Italy). Type: main BibRelationships: HasContributorRelationships: – PersonEntity: Name: NameFull: Liuzzi, Mariangela – PersonEntity: Name: NameFull: Aravena Pelizari, Patrick – PersonEntity: Name: NameFull: Geiß, Christian – PersonEntity: Name: NameFull: Masi, Angelo – PersonEntity: Name: NameFull: Tramutoli, Valerio – PersonEntity: Name: NameFull: Taubenböck, Hannes IsPartOfRelationships: – BibEntity: Dates: – D: 01 M: 09 Text: Sep2019 Type: published Y: 2019 Identifiers: – Type: issn-print Value: 1570761X Numbering: – Type: volume Value: 17 – Type: issue Value: 9 Titles: – TitleFull: Bulletin of Earthquake Engineering Type: main |
| ResultId | 1 |
