Browse > Article
http://dx.doi.org/10.7780/kjrs.2020.36.5.3.9

Wildfire Severity Mapping Using Sentinel Satellite Data Based on Machine Learning Approaches  

Sim, Seongmun (Department of Urban and Environmental Engineering, Ulsan National Institute of Science and Technology)
Kim, Woohyeok (Department of Urban and Environmental Engineering, Ulsan National Institute of Science and Technology)
Lee, Jaese (Department of Urban and Environmental Engineering, Ulsan National Institute of Science and Technology)
Kang, Yoojin (Department of Urban and Environmental Engineering, Ulsan National Institute of Science and Technology)
Im, Jungho (Department of Urban and Environmental Engineering, Ulsan National Institute of Science and Technology)
Kwon, Chunguen (Division of Forest Disaster Management, National Institute of Forest Science)
Kim, Sungyong (Division of Forest Disaster Management, National Institute of Forest Science)
Publication Information
Korean Journal of Remote Sensing / v.36, no.5_3, 2020 , pp. 1109-1123 More about this Journal
Abstract
In South Korea with forest as a major land cover class (over 60% of the country), many wildfires occur every year. Wildfires weaken the shear strength of the soil, forming a layer of soil that is vulnerable to landslides. It is important to identify the severity of a wildfire as well as the burned area to sustainably manage the forest. Although satellite remote sensing has been widely used to map wildfire severity, it is often difficult to determine the severity using only the temporal change of satellite-derived indices such as Normalized Difference Vegetation Index (NDVI) and Normalized Burn Ratio (NBR). In this study, we proposed an approach for determining wildfire severity based on machine learning through the synergistic use of Sentinel-1A Synthetic Aperture Radar-C data and Sentinel-2A Multi Spectral Instrument data. Three wildfire cases-Samcheok in May 2017, Gangreung·Donghae in April 2019, and Gosung·Sokcho in April 2019-were used for developing wildfire severity mapping models with three machine learning algorithms (i.e., Random Forest, Logistic Regression, and Support Vector Machine). The results showed that the random forest model yielded the best performance, resulting in an overall accuracy of 82.3%. The cross-site validation to examine the spatiotemporal transferability of the machine learning models showed that the models were highly sensitive to temporal differences between the training and validation sites, especially in the early growing season. This implies that a more robust model with high spatiotemporal transferability can be developed when more wildfire cases with different seasons and areas are added in the future.
Keywords
machine learning; wildfire; Wildfire-damaged area; Sentinel-1; Sentinel-2;
Citations & Related Records
Times Cited By KSCI : 9  (Citation Analysis)
연도 인용수 순위
1 Addison, P., and T. Oommen, 2018. Utilizing satellite radar remote sensing for burn severity estimation, International Journal of Applied Earth Observation and Feoinformation, 73: 292-299.   DOI
2 Bak, S. H., H. M. Kim, B. K. Kim, D. H. Hwang, E. Unuzaya, and H. J. Yoon, 2018. Study on Detection Technique for Cochlodinium polykrikoides Red tide using Logistic Regression Model and Decision Tree Model, The Journal of the Korea Institute of Electronic Communication Sciences, 13(4): 777-786 (in Korean with English abstract).   DOI
3 Ban, Y., P. Zhang, A. Nascetti, A. R. Bevington, and M. A. Wulder, 2020. Near Real-Time Wildfire Progression Monitoring with Sentinel-1 SAR Time Series and Deep Learning, Scientific Reports, 10(1): 1-15.   DOI
4 Breiman, L., 2001. Random forests, Machine Learning, 45(1): 5-32.   DOI
5 Brown, A. R., G. P. Petropoulos, and K. P. Ferentinos, 2018. Appraisal of the Sentinel-1 & 2 use in a large-scale wildfire assessment: A case study from Portugal's fires of 2017, Applied Geography, 100: 78-89.   DOI
6 Cieslak, D. A., and N. V. Chawla, 2008. Learning decision trees for unbalanced data, In Joint European Conference on Machine Learning and Knowledge Discovery in Databases, Springer, Berlin, Heidelberg, pp. 241-256.
7 Collins, L., P. Griffioen, G. Newell, and A. Mellor, 2018. The utility of Random Forests for wildfire severity mapping, Remote Sensing of Environment, 216: 374-384.   DOI
8 Escuin, S., R. Navarro, and P. Fernandez, 2008. Fire severity assessment by using NBR (Normalized Burn Ratio) and NDVI (Normalized Difference Vegetation Index) derived from LANDSAT TM/ETM images, International Journal of Remote Sensing, 29(4): 1053-1073.   DOI
9 Hall, R. J., J. T. Freeburn, W. J. De Groot, J. M. Pritchard, T. J. Lynham, and R. Landry, 2008. Remote sensing of burn severity: experience from western Canada boreal fires, International Journal of Wildland Fire, 17(4): 476-489.   DOI
10 Han, D., Y. J. Kim, J. Im, S. Lee, Y. Lee, and H. C. Kim, 2018. The estimation of arctic air temperature in summer based on machine learning approaches using IABP buoy and AMSR2 satellite data, Korean Journal of Remote Sensing, 34(6-2): 1261-1272 (in Korean with English abstract).   DOI
11 Hosmer Jr, D. W., S. Lemeshow, and R. X. Sturdivant, 2013. Applied logistic regression (Vol. 398). John Wiley & Sons.
12 Mountrakis, G., J. Im, and C. Ogole, 2011. Support vector machines in remote sensing: A review, ISPRS Journal of Photogrammetry and Remote Sensing, 66(3): 247-259.   DOI
13 Korea Forest Service, 2016. Forest basic statistics 2016, Korea Forest Service, 189, Cheongsas-ro, Seogu, Daejeon. (in Korean).
14 Korea Forest Service, 2020. Forestfire statistical yearbook 2019, Korea Forest Service, 189, Cheongsas-ro, Seo-gu, Daejeon (in Korean).
15 Lasaponara, R., and B. Tucci, 2019. Identification of burned areas and severity using SAR Sentinel-1, IEEE Geoscience and Remote Sensing Letters, 16(6): 917-921.   DOI
16 Lentile, L. B., Z. A. Holden, A. M. Smith, M. J. Falkowski, A. T. Hudak, P. Morgan, and N. C. Benson, 2006. Remote sensing techniques to assess active fire characteristics and post-fire effects, International Journal of Wildland Fire, 15(3): 319-345.   DOI
17 Liu, T., A. Abd-Elrahman, J. Morton, and V. L. Wilhelm, 2018. Comparing fully convolutional networks, random forest, support vector machine, and patch-based deep convolutional neural networks for object-based wetland mapping using images from small unmanned aircraft system, GIScience & Remote Sensing, 55(2): 243-264.   DOI
18 National Institute of Forest Science, 2013. A study on damage characteristics and development of burn severity evaluation methods, National Institute of Forest Science Research report, Seoul, Korea, pp. 13-37 (in Korean).
19 Park, S., M. Shin, J. Im, C. K. Song, M. Choi, J. Kim, and S. K. Kim, 2019. Estimation of groundlevel particulate matter concentrations through the synergistic use of satellite observations and process-based models over South Korea, Atmospheric Chemistry and Physics, 19(2): 1097-1097.   DOI
20 Roteta, E., A. Bastarrika, M. Padilla, T. Storm, and E. Chuvieco, 2019. Development of a Sentinel-2 burned area algorithm: Generation of a small fire database for sub-Saharan Africa, Remote Sensing of Environment, 222: 1-17.   DOI
21 Roy, D. P., L. Boschetti, and S. N. Trigg, 2006. Remote sensing of fire severity: assessing the performance of the normalized burn ratio, IEEE Geoscience and Remote Sensing Letters, 3(1): 112-116.   DOI
22 Won, M., K. Kim, and S. Lee, 2014. Analysis of Burn Severity in Large-fire Area Using SPOT5 Imagesand Field Survey Data, Korean Journal of Agricultural and Forest Meteorology, 16(2): 114-124 (in Korean with English abstract).   DOI
23 Roy, D. P., H. Huang, L. Boschetti, L. Giglio, L. Yan, H.H. Zhang, and Z. Li, 2019. Landsat-8 and Sentinel-2 burned area mapping-A combined sensor multi-temporal change detection approach, Remote Sensing of Environment, 231: 111254.   DOI
24 Stankova, N., and R. Nedkov, 2015. Monitoring forest regrowth with different burn severity using aerial and Landsat data, In 2015 IEEE International Geoscience and Remote Sensing Symposium (IGARSS), Milan, IT, Jul. 26-31, pp. 2166-2169.
25 Wilson, K. B., and D. D. Baldocchi, 2000. Seasonal and interannual variability of energy fluxes over a broadleaved temperate deciduous forest in North America, Agricultural and Forest Meteorology, 100(1): 1-18.   DOI
26 Won, M., K. Jang, S. Yoon, and H.T. Lee, 2019. Change Detection of Damaged Area and Burn Severity due to Heat Damage from Gangwon Large Fire Area in 2019, Korean Journal of Remote Sensing, 35(6): 1083-1093 (in Korean with English abstract).   DOI
27 Yoo, C., D. Han, J. Im, and B. Bechtel, 2019. Comparison between convolutional neural networks and random forest for local climate zone classification in mega urban areas using Landsat images, ISPRS Journal of Photogrammetry and Remote Sensing, 157: 155-170.   DOI
28 Youn, H., J. Jeong, 2019. Detection of Forest Fire and NBR Mis-classified Pixel Using Multi-temporal Sentinel-2A Images, Korean Journal of Remote Sensing, 35(6-2): 1107-1115 (in Korean with English abstract).   DOI