• Korean Journal of Remote Sensing
• /
• v.25 no.2
• /
• pp.145-154
• /
• 2009

High spatial resolution satellite image classification has a limitation when only using the spectral information due to the complex spatial arrangement of features and spectral heterogeneity within each class. Therefore, the extraction of the spatial information is one of the most important steps in high resolution satellite image classification. This study proposes a new spatial feature extraction method, named SSI(Shape-Size Index). SSI uses a simple region-growing based image segmentation and allocates spatial property value in each segment. The extracted feature is integrated with spectral bands to improve overall classification accuracy. The classification is achieved by applying a SVM(Support Vector Machines) classifier. In order to evaluate the proposed feature extraction method, KOMPSAT-2 and QuickBird-2 data are used for experiments. It is demonstrated that proposed SSI algorithm leads to a notable increase in classification accuracy.

• Korean Journal of Remote Sensing
• /
• v.35 no.2
• /
• pp.299-316
• /
• 2019

The purpose of this study was to analyze landslide susceptibility in the Pyeongchang area using Weight of Evidence (WOE) and Evidential Belief Function (EBF) as probability models and Artificial Neural Networks (ANN) as a machine learning model in a geographic information system (GIS). This study examined the widespread shallow landslides triggered by heavy rainfall during Typhoon Ewiniar in 2006, which caused serious property damage and significant loss of life. For the landslide susceptibility mapping, 3,955 landslide occurrences were detected using aerial photographs, and environmental spatial data such as terrain, geology, soil, forest, and land use were collected and constructed in a spatial database. Seventeen factors that could affect landsliding were extracted from the spatial database. All landslides were randomly separated into two datasets, a training set (50%) and validation set (50%), to establish and validate the EBF, WOE, and ANN models. According to the validation results of the area under the curve (AUC) method, the accuracy was 74.73%, 75.03%, and 70.87% for WOE, EBF, and ANN, respectively. The EBF model had the highest accuracy. However, all models had predictive accuracy exceeding 70%, the level that is effective for landslide susceptibility mapping. These models can be applied to predict landslide susceptibility in an area where landslides have not occurred previously based on the relationships between landslide and environmental factors. This susceptibility map can help reduce landslide risk, provide guidance for policy and land use development, and save time and expense for landslide hazard prevention. In the future, more generalized models should be developed by applying landslide susceptibility mapping in various areas.

• Journal of the Korean earth science society
• /
• v.42 no.6
• /
• pp.623-631
• /
• 2021

The increased transport of marine hazardous and noxious substances (HNS) has resulted in frequent HNS spill accidents domestically and internationally. There are about 6,000 species of HNS internationally, and most of them have toxic properties. When an accidental HNS spill occurs, it can destroys the marine ecosystem and can damage life and property due to explosion and fire. Constructing a spectral library of HNS according to wavelength and developing a detection algorithm would help prepare for accidents. In this study, a ground HNS spill experiment was conducted in France. The toluene spectrum was determined through hyperspectral sensor measurements. HNS present in the hyperspectral images were detected by applying the spectral mixture algorithm. Preprocessing principal component analysis (PCA) removed noise and performed dimensional compression. The endmember spectra of toluene and seawater were extracted through the N-FINDR technique. By calculating the abundance fraction of toluene and seawater based on the spectrum, the detection accuracy of HNS in all pixels was presented as a probability. The probability was compared with radiance images at a wavelength of 418.15 nm to select abundance fractions with maximum detection accuracy. The accuracy exceeded 99% at a ratio of approximately 42%. Response to marine spills of HNS are presently impeded by the restricted access to the site because of high risk of exposure to toxic compounds. The present experimental and detection results could help estimate the area of contamination with HNS based on hyperspectral remote sensing.

• Korean Journal of Remote Sensing
• /
• v.38 no.6_1
• /
• pp.1207-1217
• /
• 2022

Vegetation indices using the reflectance of selected wavelength, associating with the monitoring purpose such as identifying the progress of crop growth, on the vegetation canopy surface is widely used in the digital agriculture technology. However, the surface reflectance anisotropy can distort the true value of vegetation index related to the condition of surface, even though the surface property be unchanged. That causes difficulty to observe accurately crop growth on the monitoring system. In this study, a simple type goniometer was designed to measure the reflectance from the anisotropic surface according to various zeniths and azimuths of sun and viewing sensor in the field. On the tarp like as Lambertian surface, the reflectance of Blue, Green, Red, Near-Infrared band was similar to the tarps' reflectance properties. However, the reflectance was slightly overestimated in the cloudy day. The relative difference values of vegetation indices on grass were overestimated for the forward viewing and underestimated for the backward viewing. In addition, enhanced vegetation index (EVI) showed less sensitive according to the positions of sun and sensor viewing. Field observation with a goniometer will be helpful to understand the anisotropy characteristics on the vegetation surface.

• Korean Journal of Remote Sensing
• /
• v.38 no.6_2
• /
• pp.1709-1722
• /
• 2022

The rise in temperature induced by global warming caused in El Nino and La Nina, and abnormally changed the temperature of seawater. Rainfall concentrates in some locations due to abnormal variations in seawater temperature, causing frequent abnormal floods. It is important to rapidly detect flooded regions to recover and prevent human and property damage caused by floods. This is possible with synthetic aperture radar. This study aims to generate a model that directly derives flood-damaged areas by using modified U-NET and TerraSAR-X images based on Multi Kernel to reduce the effect of speckle noise through various characteristic map extraction and using two images before and after flooding as input data. To that purpose, two synthetic aperture radar (SAR) images were preprocessed to generate the model's input data, which was then applied to the modified U-NET structure to train the flood detection deep learning model. Through this method, the flood area could be detected at a high level with an average F1 score value of 0.966. This result is expected to contribute to the rapid recovery of flood-stricken areas and the derivation of flood-prevention measures.

• Korean Journal of Remote Sensing
• /
• v.38 no.5_2
• /
• pp.695-706
• /
• 2022

Medium and high-resolution optical satellites have proven their effectiveness in detecting wildfire areas. However, smoke plumes generated by wildfire scatter visible light incidents on the surface, thereby interrupting accurate monitoring of the area where wildfire occurs. Therefore, a technology to extract smoke in advance is required. Deep learning technology is expected to improve the accuracy of smoke extraction, but the lack of training datasets limits the application. However, for clouds, which have a similar property of scattering visible light, a large amount of training datasets has been accumulated. The purpose of this study is to develop a smoke extraction technique using deep learning, and the limits due to the lack of datasets were overcome by using a cloud dataset on transfer learning. To check the effectiveness of transfer learning, a small-scale smoke extraction training set was made, and the smoke extraction performance was compared before and after applying transfer learning using a public cloud dataset. As a result, not only the performance in the visible light wavelength band was enhanced but also in the near infrared (NIR) and short-wave infrared (SWIR). Through the results of this study, it is expected that the lack of datasets, which is a critical limit for using deep learning on smoke extraction, can be solved, and therefore, through the advancement of smoke extraction technology, it will be possible to present an advantage in monitoring wildfires.

• Korean Journal of Remote Sensing
• /
• v.39 no.5_2
• /
• pp.785-798
• /
• 2023

Recently, forest fires have become frequent due to climate change, and the size of forest fires is also increasing. Forest fires in Korea continue to cause more than 100 ha of forest fire damage every year. It was found that 90% of the large-scale wildfires that occurred in Gangwon-do over the past five years were concentrated in the east coast area. The east coast area has a climate vulnerable to forest fires such as dry air and intermediate wind, and forest conditions of coniferous forests. In this regard, studies related to various forest fire analysis, such as predicting the risk of forest fires and calculating the risk of forest fires, are being promoted. There are many studies related to risk analysis for forest areas in consideration of weather and forest-related factors, but studies that have conducted risk analysis for forest-friendly areas are still insufficient. Management of forest adjacent areas is important for the protection of human life and property. Forest-adjacent houses and facilities are greatly threatened by forest fires. Therefore, in this study, a grid-based forest fire-related disaster risk map was created using factors affected by forest-neighboring areas using national branch numbers, and differences in risk ratings were compared for forest areas and areas adjacent to forests based on Gangneung forest fire cases.

• Korean Chemical Engineering Research
• /
• v.62 no.1
• /
• pp.13-18
• /
• 2024

To develop flexible electrode materials for wearable devices, we investigated the electrochemical characteristics of carbon fibers tow according to pretreatment. And an electrochemical non-enzymatic sensor was fabricated using glucose as a target. The carbon fibers tow was pretreated through desizing and activation processes, and activation was performed in two ways: chemical oxidation and electrochemical oxidation. Surface morphology of carbon fibers tow samples was observed by SEM and their electrochemical characteristics and sensing performance were investigated by cyclic voltammetry, electrochemical impedance spectroscopy and chronoamperometry. Carbon fibers tow samples showed improved electrochemical properties such as reduced R_et, ΔE_p, and increased I_p through pretreatment. And similar electrochemical properties were obtained with both activation methods. We selected electrochemically activated carbon fibers tow as the final electrode material for application of electrochemical sensor. The non-enzymatic glucose sensor based on this electrode has an enhanced sensitivity of 0.744 A/mM (in a linear range of 0.09899~3.75423 mM) and 0.330 mA/mM (3.75423~50 mM), respectively. Through this study, the possibility of using carbon fibers tow was confirmed as an electrode material. It is expected to be used as basic research for development of high-performance flexible electrode materials.

• Korean Chemical Engineering Research
• /
• v.62 no.3
• /
• pp.233-237
• /
• 2024

This study is about the fabrication of a flexible electrode based on PAN-based carbon fibers tow using organic/inorganic nanocomposite and its application of non-enzymatic sensor. The organic/inorganic nanocomposite was composed of the conductive polymer polyaniline (PANI) and the metal oxide CuO. And glucose was used as the target of the electrochemical sensor. Commercialized CFTs were pretreated through heat treatment for desizing and electrochemical oxidation for activation. This nanocomposite was sequentially synthesized on the pretreated CFT surface using electrochemical polymerization and electrochemical deposition. Finally, the CFT/PANI/CuO NPs electrode was obtained. The electrochemical properties and sensing performance of the CFT/PANI/CuO NPs electrode were analyzed using chronoamperometry (CA), cyclic voltammetry (CV), and electrochemical impedance spectroscopy (EIS). The sensitivity of the CFT/PANI/CuO NPs electrode was about 8.352 mA/mM (in a linear range of 0.445~6.674 mM) and 3.369 mA/mM (in a linear range of 6.674~50 mM), respectively. So, the CFT/PANI/CuO NPs electrode exhibited the enhanced sensing performances due to unique properties such as small peak potential separation, low electron transfer resistance, and large specific surface area.

• Journal of the Microelectronics and Packaging Society
• /
• v.22 no.2
• /
• pp.21-26
• /
• 2015

Mesoporous ceramic materials were applied in various fields such as adsorbent and gas sensor because of low thermal conductivity and high specific surface area properties. This structure could be divided into open-pore structure and closed-pore structure. Although closed-pore structure mesoporous ceramic materials have higher mechanical property than open-pore structure, it has a restriction on the application because the increase of specific surface area is limited. So, in this work, specific surface area of closed-pore structure $TiO_2$ was increased by anneal time. As increased annealing time, crystallization and grain growth of $TiO_2$ skeleton structured material in mesoporous structure induced a collapse and agglomeration of pores. Through this pore structural change, pore connectivity and specific surface area could be enhanced. After anneal for 24 hrs, porosity was decreased from 36.3% to 34.1%, but specific surface area was increased from $48m^2/g$ to $156m^2/g$. CO gas sensitivity was also increased by about 7.4 times due to an increase of specific surface area.