• Korean Journal of Remote Sensing
• /
• v.39 no.6_1
• /
• pp.1413-1425
• /
• 2023

The increasing frequency of wildfires due to climate change is causing extreme loss of life and property. They cause loss of vegetation and affect ecosystem changes depending on their intensity and occurrence. Ecosystem changes, in turn, affect wildfire occurrence, causing secondary damage. Thus, accurate estimation of the areas affected by wildfires is fundamental. Satellite remote sensing is used for forest fire detection because it can rapidly acquire topographic and meteorological information about the affected area after forest fires. In addition, deep learning algorithms such as convolutional neural networks (CNN) and transformer models show high performance for more accurate monitoring of fire-burnt regions. To date, the application of deep learning models has been limited, and there is a scarcity of reports providing quantitative performance evaluations for practical field utilization. Hence, this study emphasizes a comparative analysis, exploring performance enhancements achieved through both model selection and data design. This study examined deep learning models for detecting wildfire-damaged areas using Landsat 8 satellite images in California. Also, we conducted a comprehensive comparison and analysis of the detection performance of multiple models, such as U-Net and High-Resolution Network-Object Contextual Representation (HRNet-OCR). Wildfire-related spectral indices such as normalized difference vegetation index (NDVI) and normalized burn ratio (NBR) were used as input channels for the deep learning models to reflect the degree of vegetation cover and surface moisture content. As a result, the mean intersection over union (mIoU) was 0.831 for U-Net and 0.848 for HRNet-OCR, showing high segmentation performance. The inclusion of spectral indices alongside the base wavelength bands resulted in increased metric values for all combinations, affirming that the augmentation of input data with spectral indices contributes to the refinement of pixels. This study can be applied to other satellite images to build a recovery strategy for fire-burnt areas.

• Journal of Korean Society of Forest Science
• /
• v.10 no.1
• /
• pp.29-39
• /
• 1970

Forest fires often destory forests that have taken years to grow in a few minutes. Forest fire therefore, is an important problem in forest management and have caused heavy losses to the nations economy. In order to resolve this problem many investigations have been made in many countries. However, ecological studies on the forest after accidental fire have not yet been made in Korea. In order to conduct such a study, a burned area on Mt. Samak which is located at Dukduwon-ri, Seo-myon, Chunsung-gun, Kangwon-do, was chosen as experimental plot in 1967. The remaining seeds were collected from the burned area, and investigations on their germination rate and their productivity were made comparing to those of the seeds of undemaged area, and following results were obtained. 1. The number of seed collected from the control plots were 740 while it was 537 from the test plots (Table 3, 4). It was considered that this difference between burned and unburned area was mainly due to the fact that some of the seeds had been burnt by the fire, and the unfavorable environmental conditions in the burned area was also considered to be a reason. In the germination rate in the control plots showed 28.1% while it was 3.2% in the test plots. This difference was considered to be due to complete loss of viability of the seed by burning and high heat. 2. In the test plots, sixteen seeds of the Alnus japonica were collected and six of these seeds germinated (index number 100) which was the highest germination rate among the species of collected seeds. From these results, it was considered that a high temperature (above $150^{\circ}C$) caused reduction of the germination rate (Quadrat. 1.2). Seeds of Carex lanceolata var. Nana, were appeared much more in the higher plots than in the lower plots and it seemed to be due to the fact that the forest floor plants were much more abundant in the lower plots than in the higher plots which is covered with shrubbery. And some small seeds midght be able to avoid the effect of fire being burried in the soil or under the gravel. 3. With Pinus densiflora, 43 seeds were collected, and 11 of these germinated in the control plots. However in the test plots, 11 seeds were collected and no seed germinated. This shows that the Pinus densiflora was the weakest in resisting to heat among the observed species in this study. 4. Without exception the germination rate showed a higher index in the herbs than in the woody plants and it is believed that the herbs produced more seed than the wood plants because of the abundance of herbs colony.