• Journal of Korea Spatial Information System Society
• /
• v.11 no.4
• /
• pp.33-38
• /
• 2009

Since the beginning of 2000, the ubiquitous technology rapidly has been at center of public concerns, and application of the ubiquitous technology is expanding in Korea with U-City as the center. U-City is currently planned and built by local governments, but the applicable range of the ubiquitous technology should be expanded in the future to build U-Territory and U-Land projects. As a part of this, U-forest should also be implemented, and that now is the time to gain support in policy and systematic initiative. Therefore, this study defines U-Forest concept to implement valuable national resources, healthy land environment, and pleasant green space by using ubiquitous technology as an effective way to produce, manage, use, and distribute the forest. In order to establish strategy for U-Forest, it has considered basic forest plan, k-Forest, and FGIS projects, and has drawn a service model pertaining to them. Also, it has proposed the need to establish the basic plan for U-Forest, and suggested details to include in the plan.

• 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.