TY - JOUR
T1 - Towards operational satellite-based damage-mapping using U-net convolutional network
T2 - A case study of 2011 Tohoku Earthquake-Tsunami
AU - Bai, Yanbing
AU - Mas, Erick
AU - Koshimura, Shunichi
N1 - Funding Information:
Funding: This research was funded by JST (Japan Science and Technology Agency) CREST (grant number JP-MJCR1411), JSPS Grants-in-Aid for Scientific Research (grant number 17H06108), Microsoft AI for Earth grant and China Scholarship Council (CSC).
Funding Information:
Acknowledgments: We would like to thank Microsoft for providing the Azure service through AI for Earth grant and ESRI for providing the ArcGIS package to guarantee the fulfillment of this work. We would also like to show our great gratitude to Yanzhang from RIKEN, Xing Liu and Luis Moya from Tohoku University for providing good suggestions to this work.
PY - 2018/10/1
Y1 - 2018/10/1
N2 - The satellite remote-sensing-based damage-mapping technique has played an indispensable role in rapid disaster response practice, whereas the current disaster response practice remains subject to the low damage assessment accuracy and lag in timeliness, which dramatically reduces the significance and feasibility of extending the present method to practical operational applications. Therefore, a highly efficient and intelligent remote-sensing image-processing framework is urgently required to mitigate these challenges. In this article, a deep learning algorithm for the semantic segmentation of high-resolution remote-sensing images using the U-net convolutional network was proposed to map the damage rapidly. The algorithm was implemented within a Microsoft Cognitive Toolkit framework in the GeoAI platform provided by Microsoft. The study takes the 2011 Tohoku Earthquake-Tsunami as a case study, for which the pre- and post-disaster high-resolution WorldView-2 image is used. The performance of the proposed U-net model is compared with that of deep residual U-net. The comparison highlights the superiority U-net for tsunami damage mapping in this work. Our proposed method achieves the overall accuracy of 70.9% in classifying the damage into "washed away," "collapsed," and "survived" at the pixel level. In future disaster scenarios, our proposed model can generate the damage map in approximately 2-15 min when the preprocessed remote-sensing datasets are available. Our proposed damage-mapping framework has significantly improved the application value in operational disaster response practice by substantially reducing the manual operation steps required in the actual disaster response. Besides, the proposed framework is highly flexible to extend to other scenarios and various disaster types, which can accelerate operational disaster response practice.
AB - The satellite remote-sensing-based damage-mapping technique has played an indispensable role in rapid disaster response practice, whereas the current disaster response practice remains subject to the low damage assessment accuracy and lag in timeliness, which dramatically reduces the significance and feasibility of extending the present method to practical operational applications. Therefore, a highly efficient and intelligent remote-sensing image-processing framework is urgently required to mitigate these challenges. In this article, a deep learning algorithm for the semantic segmentation of high-resolution remote-sensing images using the U-net convolutional network was proposed to map the damage rapidly. The algorithm was implemented within a Microsoft Cognitive Toolkit framework in the GeoAI platform provided by Microsoft. The study takes the 2011 Tohoku Earthquake-Tsunami as a case study, for which the pre- and post-disaster high-resolution WorldView-2 image is used. The performance of the proposed U-net model is compared with that of deep residual U-net. The comparison highlights the superiority U-net for tsunami damage mapping in this work. Our proposed method achieves the overall accuracy of 70.9% in classifying the damage into "washed away," "collapsed," and "survived" at the pixel level. In future disaster scenarios, our proposed model can generate the damage map in approximately 2-15 min when the preprocessed remote-sensing datasets are available. Our proposed damage-mapping framework has significantly improved the application value in operational disaster response practice by substantially reducing the manual operation steps required in the actual disaster response. Besides, the proposed framework is highly flexible to extend to other scenarios and various disaster types, which can accelerate operational disaster response practice.
KW - 2011 Tohoku earthquake and tsunami
KW - Microsoft Cognitive Toolkit
KW - Operational damage-mapping
KW - Semantic segmentation
KW - U-net convolutional neural network
UR - http://www.scopus.com/inward/record.url?scp=85055410848&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85055410848&partnerID=8YFLogxK
U2 - 10.3390/rs10101626
DO - 10.3390/rs10101626
M3 - Article
AN - SCOPUS:85055410848
VL - 10
JO - Remote Sensing
JF - Remote Sensing
SN - 2072-4292
IS - 10
M1 - 1626
ER -