AUTOMATIC COLLECTION OF TRAINING SAMPLES FOR FLOODED AREAS

Luis Moya; Masakazu Hashimoto; Erick Mas; Shunichi Koshimura

doi:10.1109/IGARSS47720.2021.9554446

AUTOMATIC COLLECTION OF TRAINING SAMPLES FOR FLOODED AREAS

Luis Moya, Masakazu Hashimoto, Erick Mas, Shunichi Koshimura

Risk Evaluation and Disaster Mitigation Research Division

Research output: Contribution to conference › Paper › peer-review

Abstract

We show the application of an automatic collection of training samples for the identification of flooded buildings. The method is based on a near real time estimation of the flooded area using in-place sensors and a numerical simulation. Then, microwave remote sensing images are used to improve the accuracy of the extent of the flooded area. The floods produced during the 2018 heavy rainfalls in the town of Mabi is reported as case study. The results are consistent with the flood map provided by a third party.

Original language	English
Pages	8305-8308
Number of pages	4
DOIs	https://doi.org/10.1109/IGARSS47720.2021.9554446
Publication status	Published - 2021
Event	2021 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2021 - Brussels, Belgium Duration: 2021 Jul 12 → 2021 Jul 16

Conference

Conference	2021 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2021
Country/Territory	Belgium
City	Brussels
Period	21/7/12 → 21/7/16

Keywords

Floods
Machine learning
SAR
Training samples

ASJC Scopus subject areas

Computer Science Applications
Earth and Planetary Sciences(all)

Access to Document

10.1109/IGARSS47720.2021.9554446

Cite this

@conference{88628f964a2f4037bb17b2fcc6885fd4,

title = "AUTOMATIC COLLECTION OF TRAINING SAMPLES FOR FLOODED AREAS",

abstract = "We show the application of an automatic collection of training samples for the identification of flooded buildings. The method is based on a near real time estimation of the flooded area using in-place sensors and a numerical simulation. Then, microwave remote sensing images are used to improve the accuracy of the extent of the flooded area. The floods produced during the 2018 heavy rainfalls in the town of Mabi is reported as case study. The results are consistent with the flood map provided by a third party.",

keywords = "Floods, Machine learning, SAR, Training samples",

author = "Luis Moya and Masakazu Hashimoto and Erick Mas and Shunichi Koshimura",

note = "Funding Information: Thanks to the Concytec-World Bank project ”Improvement and Extension of the services of the National System of Science, Technology and Technological Innovation” 8682-PE through its executing unit Fondecyt [contract 038-2019], to the Japan Society for the Promotion of Science (JSPS) Kak-enhi (17H06108), to the Core Research Cluster of Disaster Science at To-hoku University (a Designated National university), and to the JSPS Kakenhi (20K15000). Publisher Copyright: {\textcopyright} 2021 IEEE; 2021 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2021 ; Conference date: 12-07-2021 Through 16-07-2021",

year = "2021",

doi = "10.1109/IGARSS47720.2021.9554446",

language = "English",

pages = "8305--8308",

}

TY - CONF

T1 - AUTOMATIC COLLECTION OF TRAINING SAMPLES FOR FLOODED AREAS

AU - Moya, Luis

AU - Hashimoto, Masakazu

AU - Mas, Erick

AU - Koshimura, Shunichi

N1 - Funding Information: Thanks to the Concytec-World Bank project ”Improvement and Extension of the services of the National System of Science, Technology and Technological Innovation” 8682-PE through its executing unit Fondecyt [contract 038-2019], to the Japan Society for the Promotion of Science (JSPS) Kak-enhi (17H06108), to the Core Research Cluster of Disaster Science at To-hoku University (a Designated National university), and to the JSPS Kakenhi (20K15000). Publisher Copyright: © 2021 IEEE

PY - 2021

Y1 - 2021

N2 - We show the application of an automatic collection of training samples for the identification of flooded buildings. The method is based on a near real time estimation of the flooded area using in-place sensors and a numerical simulation. Then, microwave remote sensing images are used to improve the accuracy of the extent of the flooded area. The floods produced during the 2018 heavy rainfalls in the town of Mabi is reported as case study. The results are consistent with the flood map provided by a third party.

AB - We show the application of an automatic collection of training samples for the identification of flooded buildings. The method is based on a near real time estimation of the flooded area using in-place sensors and a numerical simulation. Then, microwave remote sensing images are used to improve the accuracy of the extent of the flooded area. The floods produced during the 2018 heavy rainfalls in the town of Mabi is reported as case study. The results are consistent with the flood map provided by a third party.

KW - Floods

KW - Machine learning

KW - SAR

KW - Training samples

UR - http://www.scopus.com/inward/record.url?scp=85130035326&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85130035326&partnerID=8YFLogxK

U2 - 10.1109/IGARSS47720.2021.9554446

DO - 10.1109/IGARSS47720.2021.9554446

M3 - Paper

AN - SCOPUS:85130035326

SP - 8305

EP - 8308

T2 - 2021 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2021

Y2 - 12 July 2021 through 16 July 2021

ER -

AUTOMATIC COLLECTION OF TRAINING SAMPLES FOR FLOODED AREAS

Abstract

Conference

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this