Classification of Forest Fire Damage Grade Using Machine Learning and Sentinel-2

Youn Hyoungjin; Jeong, Jong Chul

doi:10.15793/kspr.2020.106..006

This study applies machine learning techniques to forest fire damage area. The study area was Sokcho, Gangwon-do, which occurred forest fire damage on April 4, 2019. We used Sentinel-2 images for detecting forest fire area. We adjusted four cases for train model based on the dNBR severity level classes. We used 4 SVM kernels, because the accuracy may vary depending on the structure of the data to learning. The training results showed that in all four cases, the SVM RBF model showed the highest accuracy. The SVM RBF model with the highest training accuracy was used in the test area classification process. During the verification process, we created 300 GTP using KOMPSAT-3 for verification. Verification results show that the test results using the SVM RBF model classified (82.67%) was more affected than dNBR classification result (80.67%). The results of the study suggested a direction to incorporate mechanical learning in the analysis process for detecting and classifying forest fire damage areas.

Citation status

KCI Citation Counts (2)
열림/닫힘 버튼
REFERENCES (15)
열림/닫힘 버튼
* 2021년 이후 발행 논문의 참고문헌은 현재 구축 중입니다.

[journal] 강남이 / 2013 / A Comparative Study on Suitable SVM Kernel Function of Land Cover Classification Using KOMPSAT-2 Imagery / 대한공간정보학회지 / 대한공간정보학회 21(2) : 17~23 / http://dx.doi.org/10.7319/kogsis.2013.21.2.017

[journal] 이수진 / 2017 / Development of FBI(Fire Burn Index) for Sentinel-2 images and an experiment for detection of burned areas in Korea / 한국사진지리학회지 / 한국사진지리학회 27(4) : 187~202 / 10.35149/jakpg.2017.27.4.012

[report] 임륭혁 / 2020 / 재난지역 피해규모 산정을 위한 위성영상과 국토지표 활용방안 / 국토연구원

[journal] 원명수 / 2014 / Analysis of Burn Severity in Large-fire Area Using SPOT5 Images and Field Survey Data / 한국농림기상학회지 / 한국농림기상학회 16(2) : 114~124 / 10.5532/KJAFM.2014.16.2.114

[journal] 채경재 / 2018 / Development of a Gangwon Province Forest Fire Prediction Model using Machine Learning and Sampling / 한국빅데이터학회 학회지 / 사)한국빅데이터학회 3(2) : 71~78 / 10.36498/kbigdt.2018.3.2.71

[journal] 최재완 / 2006 / Support Vector Machine Classification of Hyperspectral Image using Spectral Similarity Kernel / 대한공간정보학회지 / 대한공간정보학회 14(4) : 71~77

[journal] Bui, D. T. / 2018 / GIS-based spatial prediction of tropical forest fire danger using a new hybrid machine learning method / Ecological Informatics 48 : 104~116 / https://doi.org/10.1016/j.ecoinf.2018.08.008

[journal] Federico Filipponi / 2019 / Exploitation of Sentinel-2 Time Series to Map Burned Areas at the National Level: A Case Study on the 2017 Italy Wildfires / Remote Sensing / MDPI AG 11(6) : 622~ / 10.3390/rs11060622

[journal] Shannon Franks / 2017 / Monitoring forest regrowth following large scale fire using satellite data-A case study of Yellowstone National Park, USA- / European Journal of Remote Sensing / Informa UK Limited 46(1) : 551~569 / 10.5721/EuJRS20134632

[book] Key, C. H. / 2005 / FIREMON: Fire Effects Monitoring and Inventory System / USDA Forest Service, Rocky Mountains Research Station

[journal] Adrijana car / 2018 / Automated Delineation Of Wildfire Areas Using Sentinel-2 Satellite Imagery / GI_Forum / Osterreichische Akademie der Wissenschaften 1 : 251~262 / 10.1553/giscience2018_01_s251

[journal] E. Roteta / 2019 / Development of a Sentinel-2 burned area algorithm: Generation of a small fire database for sub-Saharan Africa / Remote Sensing of Environment / Elsevier BV 222 : 1~17 / 10.1016/j.rse.2018.12.011

[journal] Jae-Hyun Ryu / 2018 / Satellite-Based Evaluation of the Post-Fire Recovery Process from the Worst Forest Fire Case in South Korea / Remote Sensing / MDPI AG 10(6) : 918~ / 10.3390/rs10060918

[book] Vapnik, V. N. / 1995 / The Nature of Statistical Learning Theory / Springer-Verlag

[journal] Zhao, J. / 2011 / SVM based forest fire detection using static and dynamic features / Computer Science and Information Systems 8(3) : 821~841

KJC Korea
Journal Central

Statistics

Tools

Sharing

Issue List

Citation status