Estimation of pixel-level seismic vulnerability of the building environment based on mid-resolution optical remote sensing images
Building damage after seismic disasters is one of the most vital factors threatening people's lives. The seismic vulnerability of buildings over large scales at the regional or country level is a key parameter for the mitigation of seismic disaster risk and rapid assessment of casualties after...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2021-09-01
|
| Series: | International Journal of Applied Earth Observations and Geoinformation |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S0303243421000465 |
| _version_ | 1818549870263271424 |
|---|---|
| author | Xiwei Fan Gaozhong Nie Chaoxu Xia Junxue Zhou |
| author_facet | Xiwei Fan Gaozhong Nie Chaoxu Xia Junxue Zhou |
| author_sort | Xiwei Fan |
| collection | DOAJ |
| description | Building damage after seismic disasters is one of the most vital factors threatening people's lives. The seismic vulnerability of buildings over large scales at the regional or country level is a key parameter for the mitigation of seismic disaster risk and rapid assessment of casualties after seismic events. To acquire the seismic vulnerability of buildings over large areas, a machine learning method based on mid-resolution satellite optical images is proposed. Taking field-investigated building vulnerability at the satellite pixel scale as a reference, the 15 most correlated features are calculated based on VIIRS nighttime light, MODIS vegetation index and surface reflectance, and texture data from Landsat-8 OLI surface reflectance products. Taking Yancheng, Jiangsu Province, China, as the study area, where 401 pixel-level seismic vulnerabilities (PLSVs) of the building environment are acquired based on field investigations, support vector regression (SVR) and random forest (RF) models are proposed using the 15 features calculated from satellite optical images. The results show that the proposed method can be used to estimate the PLSV with a root mean square error of approximately 0.1, with the PLSV normalized between 0 and 1. The machine learning model proposed in this study has a better accuracy for PLSV estimation than spatial interpolation. |
| first_indexed | 2024-12-12T08:38:54Z |
| format | Article |
| id | doaj.art-a3c23d59ba6a4e198b2c0b85c9d4b134 |
| institution | Directory Open Access Journal |
| issn | 1569-8432 |
| language | English |
| last_indexed | 2024-12-12T08:38:54Z |
| publishDate | 2021-09-01 |
| publisher | Elsevier |
| record_format | Article |
| series | International Journal of Applied Earth Observations and Geoinformation |
| spelling | doaj.art-a3c23d59ba6a4e198b2c0b85c9d4b1342022-12-22T00:30:50ZengElsevierInternational Journal of Applied Earth Observations and Geoinformation1569-84322021-09-01101102339Estimation of pixel-level seismic vulnerability of the building environment based on mid-resolution optical remote sensing imagesXiwei Fan0Gaozhong Nie1Chaoxu Xia2Junxue Zhou3Key Laboratory of Seismic and Volcanic Hazards, China Earthquake Administration, Beijing 100029, China; Institute of Geology, China Earthquake Administration, Beijing 100029, ChinaKey Laboratory of Seismic and Volcanic Hazards, China Earthquake Administration, Beijing 100029, China; Institute of Geology, China Earthquake Administration, Beijing 100029, China; Corresponding author.Key Laboratory of Seismic and Volcanic Hazards, China Earthquake Administration, Beijing 100029, China; Institute of Geology, China Earthquake Administration, Beijing 100029, ChinaEarthquake Administration of Guangxi Zhuang Autonomous Region, Nanning 530022, ChinaBuilding damage after seismic disasters is one of the most vital factors threatening people's lives. The seismic vulnerability of buildings over large scales at the regional or country level is a key parameter for the mitigation of seismic disaster risk and rapid assessment of casualties after seismic events. To acquire the seismic vulnerability of buildings over large areas, a machine learning method based on mid-resolution satellite optical images is proposed. Taking field-investigated building vulnerability at the satellite pixel scale as a reference, the 15 most correlated features are calculated based on VIIRS nighttime light, MODIS vegetation index and surface reflectance, and texture data from Landsat-8 OLI surface reflectance products. Taking Yancheng, Jiangsu Province, China, as the study area, where 401 pixel-level seismic vulnerabilities (PLSVs) of the building environment are acquired based on field investigations, support vector regression (SVR) and random forest (RF) models are proposed using the 15 features calculated from satellite optical images. The results show that the proposed method can be used to estimate the PLSV with a root mean square error of approximately 0.1, with the PLSV normalized between 0 and 1. The machine learning model proposed in this study has a better accuracy for PLSV estimation than spatial interpolation.http://www.sciencedirect.com/science/article/pii/S0303243421000465EarthquakeBuilding seismic vulnerabilityMODISNighttime lightLandsat-8 |
| spellingShingle | Xiwei Fan Gaozhong Nie Chaoxu Xia Junxue Zhou Estimation of pixel-level seismic vulnerability of the building environment based on mid-resolution optical remote sensing images International Journal of Applied Earth Observations and Geoinformation Earthquake Building seismic vulnerability MODIS Nighttime light Landsat-8 |
| title | Estimation of pixel-level seismic vulnerability of the building environment based on mid-resolution optical remote sensing images |
| title_full | Estimation of pixel-level seismic vulnerability of the building environment based on mid-resolution optical remote sensing images |
| title_fullStr | Estimation of pixel-level seismic vulnerability of the building environment based on mid-resolution optical remote sensing images |
| title_full_unstemmed | Estimation of pixel-level seismic vulnerability of the building environment based on mid-resolution optical remote sensing images |
| title_short | Estimation of pixel-level seismic vulnerability of the building environment based on mid-resolution optical remote sensing images |
| title_sort | estimation of pixel level seismic vulnerability of the building environment based on mid resolution optical remote sensing images |
| topic | Earthquake Building seismic vulnerability MODIS Nighttime light Landsat-8 |
| url | http://www.sciencedirect.com/science/article/pii/S0303243421000465 |
| work_keys_str_mv | AT xiweifan estimationofpixellevelseismicvulnerabilityofthebuildingenvironmentbasedonmidresolutionopticalremotesensingimages AT gaozhongnie estimationofpixellevelseismicvulnerabilityofthebuildingenvironmentbasedonmidresolutionopticalremotesensingimages AT chaoxuxia estimationofpixellevelseismicvulnerabilityofthebuildingenvironmentbasedonmidresolutionopticalremotesensingimages AT junxuezhou estimationofpixellevelseismicvulnerabilityofthebuildingenvironmentbasedonmidresolutionopticalremotesensingimages |