Learning from the 2018 Western Japan Heavy Rains to Detect Floods during the 2019 Hagibis Typhoon
Applications of machine learning on remote sensing data appear to be endless. Its use in damage identification for early response in the aftermath of a large-scale disaster has a specific issue. The collection of training data right after a disaster is costly, time-consuming, and many times impossib...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-07-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/12/14/2244 |
| _version_ | 1827604934385729536 |
|---|---|
| author | Luis Moya Erick Mas Shunichi Koshimura |
| author_facet | Luis Moya Erick Mas Shunichi Koshimura |
| author_sort | Luis Moya |
| collection | DOAJ |
| description | Applications of machine learning on remote sensing data appear to be endless. Its use in damage identification for early response in the aftermath of a large-scale disaster has a specific issue. The collection of training data right after a disaster is costly, time-consuming, and many times impossible. This study analyzes a possible solution to the referred issue: the collection of training data from past disaster events to calibrate a discriminant function. Then the identification of affected areas in a current disaster can be performed in near real-time. The performance of a supervised machine learning classifier to learn from training data collected from the 2018 heavy rainfall at Okayama Prefecture, Japan, and to identify floods due to the typhoon Hagibis on 12 October 2019 at eastern Japan is reported in this paper. The results show a moderate agreement with flood maps provided by local governments and public institutions, and support the assumption that previous disaster information can be used to identify a current disaster in near-real time. |
| first_indexed | 2024-03-09T06:11:29Z |
| format | Article |
| id | doaj.art-503f05298530480ea55589c9b135d866 |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-09T06:11:29Z |
| publishDate | 2020-07-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-503f05298530480ea55589c9b135d8662023-12-03T11:58:25ZengMDPI AGRemote Sensing2072-42922020-07-011214224410.3390/rs12142244Learning from the 2018 Western Japan Heavy Rains to Detect Floods during the 2019 Hagibis TyphoonLuis Moya0Erick Mas1Shunichi Koshimura2International Research Institute of Disaster Science, Tohoku University, Aoba 468-1-E301, Aramaki, Aoba-ku, Sendai 980-8572, JapanInternational Research Institute of Disaster Science, Tohoku University, Aoba 468-1-E301, Aramaki, Aoba-ku, Sendai 980-8572, JapanInternational Research Institute of Disaster Science, Tohoku University, Aoba 468-1-E301, Aramaki, Aoba-ku, Sendai 980-8572, JapanApplications of machine learning on remote sensing data appear to be endless. Its use in damage identification for early response in the aftermath of a large-scale disaster has a specific issue. The collection of training data right after a disaster is costly, time-consuming, and many times impossible. This study analyzes a possible solution to the referred issue: the collection of training data from past disaster events to calibrate a discriminant function. Then the identification of affected areas in a current disaster can be performed in near real-time. The performance of a supervised machine learning classifier to learn from training data collected from the 2018 heavy rainfall at Okayama Prefecture, Japan, and to identify floods due to the typhoon Hagibis on 12 October 2019 at eastern Japan is reported in this paper. The results show a moderate agreement with flood maps provided by local governments and public institutions, and support the assumption that previous disaster information can be used to identify a current disaster in near-real time.https://www.mdpi.com/2072-4292/12/14/2244Sentinel-1 SAR dataflood mappingtraining datamachine learning |
| spellingShingle | Luis Moya Erick Mas Shunichi Koshimura Learning from the 2018 Western Japan Heavy Rains to Detect Floods during the 2019 Hagibis Typhoon Remote Sensing Sentinel-1 SAR data flood mapping training data machine learning |
| title | Learning from the 2018 Western Japan Heavy Rains to Detect Floods during the 2019 Hagibis Typhoon |
| title_full | Learning from the 2018 Western Japan Heavy Rains to Detect Floods during the 2019 Hagibis Typhoon |
| title_fullStr | Learning from the 2018 Western Japan Heavy Rains to Detect Floods during the 2019 Hagibis Typhoon |
| title_full_unstemmed | Learning from the 2018 Western Japan Heavy Rains to Detect Floods during the 2019 Hagibis Typhoon |
| title_short | Learning from the 2018 Western Japan Heavy Rains to Detect Floods during the 2019 Hagibis Typhoon |
| title_sort | learning from the 2018 western japan heavy rains to detect floods during the 2019 hagibis typhoon |
| topic | Sentinel-1 SAR data flood mapping training data machine learning |
| url | https://www.mdpi.com/2072-4292/12/14/2244 |
| work_keys_str_mv | AT luismoya learningfromthe2018westernjapanheavyrainstodetectfloodsduringthe2019hagibistyphoon AT erickmas learningfromthe2018westernjapanheavyrainstodetectfloodsduringthe2019hagibistyphoon AT shunichikoshimura learningfromthe2018westernjapanheavyrainstodetectfloodsduringthe2019hagibistyphoon |