Cover Image

Machine learning-based forest burned area detection with various input variables: A case study of South Korea

Recently, an increase in wildfire incidents has caused significant damage from economical, humanitarian, and environmental perspectives. Wildfires have increased in severity, frequency, and duration because of climate change and rising global temperatures, resulting in the release of massive volumes...

Full description

Saved in:
Bibliographic Details
Main Authors: Lee, Changhui, Park, Seonyoung, Kim, Taeheon, Liu, Sicong, Md. Reba, Mohd. Nadzri, Oh, Jaehong, Han, Youkyung
Format: Article
Language:English
Published: MDPI 2022
Subjects:
GE Environmental Sciences
Online Access:http://eprints.utm.my/id/eprint/100985/1/MohdNadzri2022_MachineLearningBasedForestBurnedArea.pdf
http://eprints.utm.my/id/eprint/100985/
http://dx.doi.org/10.3390/app121910077
Tags: Add Tag
No Tags, Be the first to tag this record!
id my.utm.100985
record_format eprints
spelling my.utm.1009852023-05-23T10:23:44Z http://eprints.utm.my/id/eprint/100985/ Machine learning-based forest burned area detection with various input variables: A case study of South Korea Lee, Changhui Park, Seonyoung Kim, Taeheon Liu, Sicong Md. Reba, Mohd. Nadzri Oh, Jaehong Han, Youkyung GE Environmental Sciences Recently, an increase in wildfire incidents has caused significant damage from economical, humanitarian, and environmental perspectives. Wildfires have increased in severity, frequency, and duration because of climate change and rising global temperatures, resulting in the release of massive volumes of greenhouse gases, the destruction of forests and associated habitats, and the damage to infrastructures. Therefore, identifying burned areas is crucial for monitoring wildfire damage. In this study, we aim at detecting forest burned areas occurring in South Korea using optical satellite images. To exploit the advantage of applying machine learning, the present study employs representative three machine learning methods, Light Gradient Boosting Machine (LightGBM), Random Forest (RF), and U-Net, to detect forest burned areas with a combination of input variables, namely Surface Reflectance (SR), Normalized Difference Vegetation Index (NDVI), and Normalized Burn Ratio (NBR). Two study sites of recently occurred forest fire events in South Korea were selected, and Sentinel-2 satellite images were used by considering a small scale of the forest fires. The quantitative and qualitative evaluations according to the machine learning methods and input variables were carried out. In terms of the comparison focusing on machine learning models, the U-Net showed the highest accuracy in both sites amongst the designed variants. The pre and post fire images by SR, NDVI, NBR, and difference of indices as the main inputs showed the best result. We also demonstrated that diverse landcovers may result in a poor burned area detection performance by comparing the results of the two sites. MDPI 2022 Article PeerReviewed application/pdf en http://eprints.utm.my/id/eprint/100985/1/MohdNadzri2022_MachineLearningBasedForestBurnedArea.pdf Lee, Changhui and Park, Seonyoung and Kim, Taeheon and Liu, Sicong and Md. Reba, Mohd. Nadzri and Oh, Jaehong and Han, Youkyung (2022) Machine learning-based forest burned area detection with various input variables: A case study of South Korea. Applied Sciences (Switzerland), 12 (19). pp. 1-20. ISSN 2076-3417 http://dx.doi.org/10.3390/app121910077 DOI : 10.3390/app121910077
institution Universiti Teknologi Malaysia
building UTM Library
collection Institutional Repository
continent Asia
country Malaysia
content_provider Universiti Teknologi Malaysia
content_source UTM Institutional Repository
url_provider http://eprints.utm.my/
language English
topic GE Environmental Sciences
spellingShingle GE Environmental Sciences
Lee, Changhui
Park, Seonyoung
Kim, Taeheon
Liu, Sicong
Md. Reba, Mohd. Nadzri
Oh, Jaehong
Han, Youkyung
Machine learning-based forest burned area detection with various input variables: A case study of South Korea
description Recently, an increase in wildfire incidents has caused significant damage from economical, humanitarian, and environmental perspectives. Wildfires have increased in severity, frequency, and duration because of climate change and rising global temperatures, resulting in the release of massive volumes of greenhouse gases, the destruction of forests and associated habitats, and the damage to infrastructures. Therefore, identifying burned areas is crucial for monitoring wildfire damage. In this study, we aim at detecting forest burned areas occurring in South Korea using optical satellite images. To exploit the advantage of applying machine learning, the present study employs representative three machine learning methods, Light Gradient Boosting Machine (LightGBM), Random Forest (RF), and U-Net, to detect forest burned areas with a combination of input variables, namely Surface Reflectance (SR), Normalized Difference Vegetation Index (NDVI), and Normalized Burn Ratio (NBR). Two study sites of recently occurred forest fire events in South Korea were selected, and Sentinel-2 satellite images were used by considering a small scale of the forest fires. The quantitative and qualitative evaluations according to the machine learning methods and input variables were carried out. In terms of the comparison focusing on machine learning models, the U-Net showed the highest accuracy in both sites amongst the designed variants. The pre and post fire images by SR, NDVI, NBR, and difference of indices as the main inputs showed the best result. We also demonstrated that diverse landcovers may result in a poor burned area detection performance by comparing the results of the two sites.
format Article
author Lee, Changhui
Park, Seonyoung
Kim, Taeheon
Liu, Sicong
Md. Reba, Mohd. Nadzri
Oh, Jaehong
Han, Youkyung
author_facet Lee, Changhui
Park, Seonyoung
Kim, Taeheon
Liu, Sicong
Md. Reba, Mohd. Nadzri
Oh, Jaehong
Han, Youkyung
author_sort Lee, Changhui
title Machine learning-based forest burned area detection with various input variables: A case study of South Korea
title_short Machine learning-based forest burned area detection with various input variables: A case study of South Korea
title_full Machine learning-based forest burned area detection with various input variables: A case study of South Korea
title_fullStr Machine learning-based forest burned area detection with various input variables: A case study of South Korea
title_full_unstemmed Machine learning-based forest burned area detection with various input variables: A case study of South Korea
title_sort machine learning-based forest burned area detection with various input variables: a case study of south korea
publisher MDPI
publishDate 2022
url http://eprints.utm.my/id/eprint/100985/1/MohdNadzri2022_MachineLearningBasedForestBurnedArea.pdf
http://eprints.utm.my/id/eprint/100985/
http://dx.doi.org/10.3390/app121910077
_version_ 1768006593217036288
score 13.211869

Similar Items