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...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-10-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/12/19/10077 |
| _version_ | 1797480458160701440 |
|---|---|
| author | Changhui Lee Seonyoung Park Taeheon Kim Sicong Liu Mohd Nadzri Md Reba Jaehong Oh Youkyung Han |
| author_facet | Changhui Lee Seonyoung Park Taeheon Kim Sicong Liu Mohd Nadzri Md Reba Jaehong Oh Youkyung Han |
| author_sort | Changhui Lee |
| collection | DOAJ |
| 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. |
| first_indexed | 2024-03-09T22:00:20Z |
| format | Article |
| id | doaj.art-2909b1aa1a1148e694fb3cc0642d59da |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-09T22:00:20Z |
| publishDate | 2022-10-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-2909b1aa1a1148e694fb3cc0642d59da2023-11-23T19:50:39ZengMDPI AGApplied Sciences2076-34172022-10-0112191007710.3390/app121910077Machine Learning-Based Forest Burned Area Detection with Various Input Variables: A Case Study of South KoreaChanghui Lee0Seonyoung Park1Taeheon Kim2Sicong Liu3Mohd Nadzri Md Reba4Jaehong Oh5Youkyung Han6Department of Civil Engineering, Seoul National University of Science and Technology, 232, Gongneung-ro, Nowon-gu, Seoul 01811, KoreaDepartment of Applied Artificial Intelligence, Seoul National University of Science and Technology, 232, Gongneung-ro, Nowon-gu, Seoul 01811, KoreaDepartment of Civil Engineering, Seoul National University of Science and Technology, 232, Gongneung-ro, Nowon-gu, Seoul 01811, KoreaCollege of Surveying and Geoinformatics, Tongji University, Shanghai 200092, ChinaGeoscience and Digital Earth Center (INSTeG), Research Institute for Sustainable and Environment (RISE), Universiti Teknologi Malaysia (UTM), Johor Bahru 81310, MalaysiaDepartment of Civil Engineering, Korea Maritime and Ocean University, Busan 49112, KoreaDepartment of Civil Engineering, Seoul National University of Science and Technology, 232, Gongneung-ro, Nowon-gu, Seoul 01811, KoreaRecently, 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.https://www.mdpi.com/2076-3417/12/19/10077forest fire burned area detectionSentinel-2Random ForestLightGBMU-Netinput variables analysis |
| spellingShingle | Changhui Lee Seonyoung Park Taeheon Kim Sicong Liu Mohd Nadzri Md Reba Jaehong Oh Youkyung Han Machine Learning-Based Forest Burned Area Detection with Various Input Variables: A Case Study of South Korea Applied Sciences forest fire burned area detection Sentinel-2 Random Forest LightGBM U-Net input variables analysis |
| title | 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_short | 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 |
| topic | forest fire burned area detection Sentinel-2 Random Forest LightGBM U-Net input variables analysis |
| url | https://www.mdpi.com/2076-3417/12/19/10077 |
| work_keys_str_mv | AT changhuilee machinelearningbasedforestburnedareadetectionwithvariousinputvariablesacasestudyofsouthkorea AT seonyoungpark machinelearningbasedforestburnedareadetectionwithvariousinputvariablesacasestudyofsouthkorea AT taeheonkim machinelearningbasedforestburnedareadetectionwithvariousinputvariablesacasestudyofsouthkorea AT sicongliu machinelearningbasedforestburnedareadetectionwithvariousinputvariablesacasestudyofsouthkorea AT mohdnadzrimdreba machinelearningbasedforestburnedareadetectionwithvariousinputvariablesacasestudyofsouthkorea AT jaehongoh machinelearningbasedforestburnedareadetectionwithvariousinputvariablesacasestudyofsouthkorea AT youkyunghan machinelearningbasedforestburnedareadetectionwithvariousinputvariablesacasestudyofsouthkorea |