• Korean Journal of Remote Sensing
• /
• v.35 no.5_2
• /
• pp.773-779
• /
• 2019

We developed the automatic ground deformation monitoring system using Sentinel-1 satellites which is operating by European Space Agency (ESA) for the Korea Peninsula's ground disaster monitoring. Ground deformation occurring over a long-term period are difficult to monitoring because it occurred in a wide area and required a large amount of satellite data for analysis. With the development of satellites, the methods to regularly observe large areas has been developed. These accumulated satellite data are used for time series ground displacement analysis. The National Disaster Management Research Institute (NDMI) established an automation system for all processes ranging from acquiring satellite observation data to analyzing ground displacement and expressing them. Based on the system developed in this research, ground displacement data on the Korean Peninsula can be updated periodically. In the future, more diverse ground displacement information could be provided if automated small regional analysis systems, multi-channel analysis method, and 3D analysis system techniques are developed with the existing system.

• Journal of Breast Cancer
• /
• v.21 no.4
• /
• pp.442-446
• /
• 2018

Purpose: The definition of nodal pathologic complete response (pCR) after a neoadjuvant chemotherapy (NAC) just included the evaluation of axillary lymph node (ALN) without internal mammary lymph node. This study aimed to evaluate the feasibility of internal mammary-sentinel lymph node biopsy (IM-SLNB) in patients with breast cancer who underwent NAC. Methods: From November 2011 to 2017, 179 patients with primary breast cancer who underwent operation after NAC were included in this study. All patients received radiotracer injection with modified injection technology. IM-SLNB would be performed on patients with internal mammary sentinel lymph node (IMSLN) visualization. Results: Among the 158 patients with cN+ disease, the rate of nodal pCR was 36.1% (57/158). Among the 179 patients, the visualization rate of IMSLN was 31.8% (57/179) and was 12.3% (7/57) and 87.7% (50/57) among those with $cN_0$ and cN+ disease, respectively. Furthermore, the detection rate of IMSLN was 31.3% (56/179). The success rate of IM-SLNB was 98.2% (56/57). The IMSLN metastasis rate was 7.1% (4/56), and all of them were accompanied by ALN metastasis. The number of positive ALNs in patients with IMSLN metastasis was 3, 6, 8, and 9. The pathology nodal stage had been changed from $pN_1/pN_2$ to $pN_{3b}$. The pathology stage had been changed from IIA/IIIA to IIIC. Conclusion: Patients with visualization of IMSLN should perform IM-SLNB after NAC, especially for patients with cN+ disease, in order to complete lymph nodal staging. IM-SLNB could further improve the definition of nodal pCR and guide the internal mammary node irradiation.

• Korean Journal of Remote Sensing
• /
• v.36 no.6_2
• /
• pp.1551-1565
• /
• 2020

On April 4, 2019, a forest fire started in Goseong County and lasted for three days, burning the neighboring areas of Sokcho. The strong winds moved the blaze from one region to another region and declared the worst wildfire in South Korea in years. More than 1,880 facilities, including 400 homes, were burnt down. The fire burned a total area of 529 hectares (1,307 acres), which involved 13,000 rescuers and 16,500 military troops to control the fire occurrence. Thousands of people were evacuated, and two people are dead. This study generated post-wildfire maps to provide necessary data for evacuation and mitigation planning to respond to this destructive wildfire, also prevent further damage and restore the area affected by the wildfire. This study used KOMPSAT-3A and Sentinel-2 imagery to map the post-wildfire condition. The SVM showed higher accuracy (overall accuracy 95.29%) compared with ANN (overall accuracy of 94.61%) for the KOMPSAT-3A. Moreover, for Sentinel-2, the SVM attained a higher accuracy (overall accuracy of 91.52%) than the ANN algorithm (overall accuracy 90.11%). In total, four post-wildfire burned area maps were generated; these results can be used to assess the area affected by the Sokcho wildfire and wildfire mitigation planning in the future.

• Korean Journal of Remote Sensing
• /
• v.38 no.5_1
• /
• pp.559-570
• /
• 2022

When a satellite image has low spatial resolution, it is difficult to detect small objects. In this research, we aim to check the effect of super resolution on object detection. Super resolution is a software method that increases the resolution of an image. Unpaired super resolution network is used to improve Sentinel-2's spatial resolution from 10 m to 3.2 m. Faster-RCNN, RetinaNet, FCOS, and S²ANet were used to detect vessels in the Sentinel-2 images. We experimented the change in vessel detection performance when super resolution is applied. As a result, the Average Precision (AP) improved by at least 12.3% and up to 33.3% in the ship detection models trained with the super-resolution image. False positive and false negative cases also decreased. This implies that super resolution can be an important pre-processing step in object detection, and it is expected to greatly contribute to improving the accuracy of other image-based deep learning technologies along with object detection.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2023.05a
• /
• pp.168-168
• /
• 2023

The frequent occurrence of cyanobacterial harmful algal blooms (CHABs) in inland waters under climate change seriously damages the ecosystem and human health and is becoming a big problem in South Korea. Satellite remote sensing is suggested for effective monitoring CHABs at a larger scale of water bodies since the traditional method based on sparse in-situ networks is limited in space. However, utilizing a standalone variable of satellite reflectances in common CHABs dual-models, which relies on both chlorophyll-a (Chl-a) and phycocyanin or cyanobacteria cells (Cyano-cell), is not fully beneficial because their seasonal variation is highly impacted by surrounding meteorological and bio-environmental factors. Along with the development of Artificial Intelligence (AI), monitoring CHABs from space with analyzing the effects of environmental factors is accessible. This study aimed to investigate the potential application of AI in the dual-model strategy (Chl-a and Cyano-cell are output parameters) for monitoring seasonal dynamics of CHABs from satellites over Korean inland waters. The Sentinel-3 satellite was selected in this study due to the variety of spectral bands and its unique band (620 nm), which is sensitive to cyanobacteria. Via the AI-based feature selection, we analyzed the relationships between two output parameters and major parameters (satellite water-leaving reflectances at different spectral bands), together with auxiliary (meteorological and bio-environmental) parameters, to select the most important ones. Several AI models were then employed for modelling Chl-a and Cyano-cell concentration from those selected important parameters. Performance evaluation of the AI models and their comparison to traditional semi-analytical models were conducted to demonstrate whether AI models (using water-leaving reflectances and environmental variables) outperform traditional models (using water-leaving reflectances only) and which AI models are superior for monitoring CHABs from Sentinel-3 satellite over a Korean inland water body.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2022.05a
• /
• pp.443-443
• /
• 2022

적설은 자주는 아니지만 가끔 비교적 넓은 범위에 피해를 발생시킨다. 적설에 의한 피해를 예방하기 위해서는 피해를 유발하는 적설심을 미리 파악해 둘 필요가 있다. 하지만 관측하고 있는 적설심은 특정 관측지점으로 한정되어 피해를 유발하는 한계적설심을 파악하는데 어려움이 있다. 이를 극복하기 위한 일반적인 방법은 관측지점의 적설을 보간하여 공간적으로 확대하는 것이다. 하지만 이것은 매우 적은 자료를 가지고 넓은 영역을 통계적으로 추정해야하는 한계로 인해 피해 유발 한계적설심의 구명에 더 혼란을 주기도 한다. 이를 보완하기 위해서는 넓은 영역을 관측하는 위성영상을 활용할 수 있으며, 그 중에서도 합성개구레이더(Synthetic Aperture Radar; SAR)를 이용한 InSAR(Interferometric Synthetic Aperture Radar) 기법은 이를 위해 적절한 방법일 수 있다. 영상의 간섭계는 두 개의 다른 시기에 측정된 합성개구레이더 영상의 위상차를 이용한 것으로 일반적으로 다른 조건들이 일치할 때 지형의 변화를 추적할 때 사용되곤 한다. 그런데 만약 두 시기 사이에 특별한 지형적인 변화를 일으키는 요인이 없고 단지 적설만이 존재한다면 두 영상의 위상차는 적설의 효과로 볼 수 있을 것이다. 적설이 전파의 전달경로를 다르게 만들어 위상차를 발생시키는 것으로 가정할 수 있다. 이때 발생하는 위상차는 적설심과 적설의 굴절률에 의해 다를 수 있다. 이에 본 연구에서는 적설 전후에 수집된 인공위성 합성개구레이더 자료의 위상차를 분석한 간섭영상을 이용해 적설심의 공간분포를 추정하여 비교해 보고자 한다. 이를 위해 적설에 대한 투과가 가능한 C밴드 레이더를 사용하는 Sentinel-1의 영상을 사용하였다. 적설심의 공간분포는 실제 피해발생지역의 적설심을 보다 정확하게 추정하는데 기여할 수 있으며, 이것은 실제 피해유발적설심을 파악하는데 도움이 될 것이다.

• Korean Journal of Remote Sensing
• /
• v.39 no.5_3
• /
• pp.891-907
• /
• 2023

Compact Advanced Satellite 500-4 (CAS500-4) is scheduled to be launched to collect high spatial resolution data focusing on vegetation applications. To achieve this goal, accurate surface reflectance retrieval through atmospheric correction is crucial. Therefore, a machine learning-based atmospheric correction algorithm was developed to simulate atmospheric correction from a radiative transfer model using Sentinel-2 data that have similarspectral characteristics as CAS500-4. The algorithm was then evaluated mainly for forest areas. Utilizing the atmospheric correction parameters extracted from Sentinel-2 and GEOKOMPSAT-2A (GK-2A), the atmospheric correction algorithm was developed based on Random Forest and Light Gradient Boosting Machine (LGBM). Between the two machine learning techniques, LGBM performed better when considering both accuracy and efficiency. Except for one station, the results had a correlation coefficient of more than 0.91 and well-reflected temporal variations of the Normalized Difference Vegetation Index (i.e., vegetation phenology). GK-2A provides Aerosol Optical Depth (AOD) and water vapor, which are essential parameters for atmospheric correction, but additional processing should be required in the future to mitigate the problem caused by their many missing values. This study provided the basis for the atmospheric correction of CAS500-4 by developing a machine learning-based atmospheric correction simulation algorithm.

• The Korean Journal of Nuclear Medicine Technology
• /
• v.14 no.2
• /
• pp.133-137
• /
• 2010

Purpose: Breast cancer is known to be more vulnerable to bone metastasis and lymph node metastasis than other types of cancer, and nuclear examinations whole body bone scan and lymphoscintigraphy are performed commonly before and after breast cancer operation. In case whole body bone scan is performed on the day before lymphoscintigraphy, the radiopharmaceutical taken into and remaining in the bones provides anatomical information for tracking and locating sentinel lymph nodes. Thus, this study purposed to examine how much bone density affects in locating sentinel lymph nodes. Materials and Methods: The subjects of this study were 22 patients (average age $52{\pm}7.2$) who had whole body bone scan and lymphoscintigraphy over two days in our hospital during the period from January to December, 2009. In the blind test, 22 patients (average age $57{\pm}6.5$) who had lymphoscintigraphy using $^{57}Co$ flood phantom were used as a control group. In quantitative analysis, the relative ratio of the background to sentinel lymph nodes was measured by drawing ROIs on sentinel lymph nodes and the background, and in gross examination, each of a nuclear physician and a radiological technologist with five years' or longer field experience examined images through blind test in a five-point scale. Results: In the results of quantitative analysis, the relative ratio of the background to sentinel lymph nodes was 14.2:1 maximum and 8.5:1 ($SD{\pm}3.48$) on the average on the front, and 14.7:1 maximum and 8.5:1 ($SD{\pm}3.42$) on the average on the side. In the results of gross examination, when $^{57}Co$ flood phantom images were compared with images containing bones, the score was relative high as 3.86 ($SD{\pm}0.35$) point for $^{57}Co$ flood phantom images and 4.09 ($SD{\pm}0.42$) for bone images. Conclusion: When whole body bone scan was performed on the day before lymphoscintigraphy, the ratio of the background to sentinel lymph nodes was over 10:1, so there was no problem in locating lymph nodes. In addition, we expect to reduce examination procedures and improve the quality of images by indicating the location of sentinel lymph nodes using bone images as body contour without the use of a source.

• Korean Journal of Remote Sensing
• /
• v.36 no.5_3
• /
• pp.1109-1123
• /
• 2020

In South Korea with forest as a major land cover class (over 60% of the country), many wildfires occur every year. Wildfires weaken the shear strength of the soil, forming a layer of soil that is vulnerable to landslides. It is important to identify the severity of a wildfire as well as the burned area to sustainably manage the forest. Although satellite remote sensing has been widely used to map wildfire severity, it is often difficult to determine the severity using only the temporal change of satellite-derived indices such as Normalized Difference Vegetation Index (NDVI) and Normalized Burn Ratio (NBR). In this study, we proposed an approach for determining wildfire severity based on machine learning through the synergistic use of Sentinel-1A Synthetic Aperture Radar-C data and Sentinel-2A Multi Spectral Instrument data. Three wildfire cases-Samcheok in May 2017, Gangreung·Donghae in April 2019, and Gosung·Sokcho in April 2019-were used for developing wildfire severity mapping models with three machine learning algorithms (i.e., Random Forest, Logistic Regression, and Support Vector Machine). The results showed that the random forest model yielded the best performance, resulting in an overall accuracy of 82.3%. The cross-site validation to examine the spatiotemporal transferability of the machine learning models showed that the models were highly sensitive to temporal differences between the training and validation sites, especially in the early growing season. This implies that a more robust model with high spatiotemporal transferability can be developed when more wildfire cases with different seasons and areas are added in the future.

• Nuclear Medicine and Molecular Imaging
• /
• v.41 no.6
• /
• pp.546-552
• /
• 2007

Purpose: In the breast cancer patient, lymphatic mapping and sentinel lymph node biopsy are the most important procedure for axillary lymph node staging. We aimed to compare the three radiocolloids [$^{99m}Tc$-antimony trisulfide colloid (ASC), $^{99m}Tc$-tin colloid (TC), and $^{99m}Tc$-human serum albumin (HSA)] for sentinel lymph node mapping. Subjects and Methods: Totally, 397 patients with clinically N0 stage were enrolled. $^{99m}Tc$-ASC was injected in 202 out of 397 patients, $^{99m}Tc$-TC was injected in 120 patients, and $^{99m}Tc$-HSA was injected in the remaining 75 patients. The sentinel lymph nodes were localized by lymphoscintigraphy and selected using intraoperative gamma probe. All sentinel lymph nodes were investigated by intraoperative pathologic consultation. The axillary lymph nodes which were harvested by the lymph node dissection were also investigated. Results: The patients of each group showed similar clinical characteristics. There were no significant differences (p>0.05) in the identification rate of sentinel lymph nodes (IR), false negative rate (FNR), and negative predictive value (NPV). The axillary lymphadenectomy revealed axillary lymph node metastases in those three groups (ASC-33.2%, TC-31.7%, HSA-22.7%). The IR, FNR, and NPV were not significantly different among those groups. Conclusion: Those three $^{99m}Tc$-labeled radiocolloids showed equivalent results in sentinel lymph node mapping of breast cancer.