Next Article in Journal
Retrieving Photometric Properties and Soil Moisture Content of Tidal Flats Using Bidirectional Spectral Reflectance
Next Article in Special Issue
Applications of Satellite Radar Imagery for Hazard Monitoring: Insights from Australia
Previous Article in Journal
Satellite-Based Observations Reveal the Altitude-Dependent Patterns of SIFyield and Its Sensitivity to Ambient Temperature in Tibetan Meadows
Previous Article in Special Issue
Earthquake Damage Region Detection by Multitemporal Coherence Map Analysis of Radar and Multispectral Imagery
Article

The Potential Role of News Media to Construct a Machine Learning Based Damage Mapping Framework

1
Graduate School of Engineering, Tohoku University, Aoba 468-1, Aramaki, Aoba-ku, Sendai 980-8572, Japan
2
International Research Institute of Disaster Science, Tohoku University, Aoba 468-1, Aramaki, Aoba-ku, Sendai 980-8572, Japan
3
Japan-Peru Center for Earthquake Engineering Research and Disaster Mitigation, National University of Engineering, Tupac Amaru Avenue 1150, Lima 25, Peru
*
Author to whom correspondence should be addressed.
Academic Editor: Jungho Im
Remote Sens. 2021, 13(7), 1401; https://doi.org/10.3390/rs13071401
Received: 1 February 2021 / Revised: 20 March 2021 / Accepted: 30 March 2021 / Published: 5 April 2021
When flooding occurs, Synthetic Aperture Radar (SAR) imagery is often used to identify flood extent and the affected buildings for two reasons: (i) for early disaster response, such as rescue operations, and (ii) for flood risk analysis. Furthermore, the application of machine learning has been valuable for the identification of damaged buildings. However, the performance of machine learning depends on the number and quality of training data, which is scarce in the aftermath of a large scale disaster. To address this issue, we propose the use of fragmentary but reliable news media photographs at the time of a disaster and use them to detect the whole extent of the flooded buildings. As an experimental test, the flood occurred in the town of Mabi, Japan, in 2018 is used. Five hand-engineered features were extracted from SAR images acquired before and after the disaster. The training data were collected based on news photos. The date release of the photographs were considered to assess the potential role of news information as a source of training data. Then, a discriminant function was calibrated using the training data and the support vector machine method. We found that news information taken within 24 h of a disaster can classify flooded and nonflooded buildings with about 80% accuracy. The results were also compared with a standard unsupervised learning method and confirmed that training data generated from news media photographs improves the accuracy obtained from unsupervised classification methods. We also provide a discussion on the potential role of news media as a source of reliable information to be used as training data and other activities associated to early disaster response. View Full-Text
Keywords: disaster; flood; machine learning; training data collection; remote sensing disaster; flood; machine learning; training data collection; remote sensing
Show Figures

Figure 1

MDPI and ACS Style

Okada, G.; Moya, L.; Mas, E.; Koshimura, S. The Potential Role of News Media to Construct a Machine Learning Based Damage Mapping Framework. Remote Sens. 2021, 13, 1401. https://doi.org/10.3390/rs13071401

AMA Style

Okada G, Moya L, Mas E, Koshimura S. The Potential Role of News Media to Construct a Machine Learning Based Damage Mapping Framework. Remote Sensing. 2021; 13(7):1401. https://doi.org/10.3390/rs13071401

Chicago/Turabian Style

Okada, Genki, Luis Moya, Erick Mas, and Shunichi Koshimura. 2021. "The Potential Role of News Media to Construct a Machine Learning Based Damage Mapping Framework" Remote Sensing 13, no. 7: 1401. https://doi.org/10.3390/rs13071401

Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Back to TopTop