TY - GEN
T1 - A radar-based method for detecting tsunami devastated areas using machine learning algorithm
AU - Gokon, Hideomi
AU - Post, Joachim
AU - Stein, Enrico
AU - Martinis, Sandro
AU - Twele, André
AU - Mück, Matthias
AU - Koshimura, Shunichi
PY - 2013/1/1
Y1 - 2013/1/1
N2 - After catastrophic earthquakes and subsequent tsunamis, relief activity and reconstruction activity might be delayed due to the breakdown of information network and interception of roads to the devastated zones. To rapidly estimate the impact of the tsunami, air- or spaceborne remote sensing technologies can be used. In particular, Synthetic Aperture Radar (SAR) which is available independent of atmospheric conditions is promising. In this study, a semi-automatic method using high-resolution multi-temporal SAR data (TerraSAR-X) is proposed to estimate building damage in tsunami devastated areas related to the 2011 Tohoku earthquake tsunami. To develop the method, machine learning, a research field of artificial intelligence, is applied. Finally, evaluation of the model is conducted through cross-validation. The best accuracy is obtained as 89.2 % and kappa statistic is calculated as 0.76 when a decision tree approach (C4.5) is applied.
AB - After catastrophic earthquakes and subsequent tsunamis, relief activity and reconstruction activity might be delayed due to the breakdown of information network and interception of roads to the devastated zones. To rapidly estimate the impact of the tsunami, air- or spaceborne remote sensing technologies can be used. In particular, Synthetic Aperture Radar (SAR) which is available independent of atmospheric conditions is promising. In this study, a semi-automatic method using high-resolution multi-temporal SAR data (TerraSAR-X) is proposed to estimate building damage in tsunami devastated areas related to the 2011 Tohoku earthquake tsunami. To develop the method, machine learning, a research field of artificial intelligence, is applied. Finally, evaluation of the model is conducted through cross-validation. The best accuracy is obtained as 89.2 % and kappa statistic is calculated as 0.76 when a decision tree approach (C4.5) is applied.
KW - Building damage
KW - Change detection
KW - Machine learning
KW - TerraSAR-X
KW - Tsunami
UR - http://www.scopus.com/inward/record.url?scp=84903454291&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84903454291&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:84903454291
SN - 9781629939100
T3 - 34th Asian Conference on Remote Sensing 2013, ACRS 2013
SP - 3535
EP - 3541
BT - 34th Asian Conference on Remote Sensing 2013, ACRS 2013
PB - Asian Association on Remote Sensing
T2 - 34th Asian Conference on Remote Sensing 2013, ACRS 2013
Y2 - 20 October 2013 through 24 October 2013
ER -