기상모델자료와 기계학습을 이용한 GK-2A/AMI Hourly AOD 산출물의 결측화소 복원

윤유정 ( Youjeong Youn ),강종구 ( Jonggu Kang ),김근아 ( Geunah Kim ),박강현 ( Ganghyun Park ),최소연 ( Soyeon Choi ) 대한원격탐사학회 2022 大韓遠隔探査學會誌 Vol.38 No.5

에어로솔(aerosol)은 대기 질을 악화시키는 등 인체 건강에 악영향을 끼치므로 에어로솔의 분포 및 특성에 대한 정량적인 관측이 필수적이다. 최근 전 지구 규모에서의 주기적이고 정량적인 정보 획득 수단으로 위성 관측 Aerosol Optical Depth (AOD) 영상이 다양한 연구에 활용되지만 광학센서 기반의 위성 AOD 영상은 구름 등의 조건을 가진 일부 지역에서 결측을 가진다. 이에 본 연구는 위성자료의 결측복원을 위하여 격자형 기상자료와 지리적 요소를 입력변수로 하여 Random Forest (RF) 기반 gap-filling 모델을 생성한 이후, gap-free GK-2A/AMI AOD hourly 영상을 산출하였다. 모델의 정확도는 -0.002의 Mean Bias Error (MBE), 0.145의 Root Mean Square Error (RMSE)로, 원자료의 목표 정확도보다 높으며 상관계수 0.714로 복원 대상이 대기변수인 점을 감안하면 상관계수 측면에서도 충분한 설명력을 갖춘 모델이다. 정지궤도 위성의 높은 시간 해상도는 일변화 관측에 적합하며 대기보정을 위한 입력, 지상 미세먼지 농도 추정, 소규모 화재 또는 오염원 분석 등 타 연구를 위한 자료 활용 측면에서 중요하다. Since aerosols adversely affect human health, such as deteriorating air quality, quantitative observation of the distribution and characteristics of aerosols is essential. Recently, satellite-based Aerosol Optical Depth (AOD) data is used in various studies as periodic and quantitative information acquisition means on the global scale, but optical sensor-based satellite AOD images are missing in some areas with cloud conditions. In this study, we produced gap-free GeoKompsat 2A (GK-2A) Advanced Meteorological Imager (AMI) AOD hourly images after generating a Random Forest based gap-filling model using grid meteorological and geographic elements as input variables. The accuracy of the model is Mean Bias Error (MBE) of -0.002 and Root Mean Square Error (RMSE) of 0.145, which is higher than the target accuracy of the original data and considering that the target object is an atmospheric variable with Correlation Coefficient (CC) of 0.714, it is a model with sufficient explanatory power. The high temporal resolution of geostationary satellites is suitable for diurnal variation observation and is an important model for other research such as input for atmospheric correction, estimation of ground PM, analysis of small fires or pollutants.

격자자료 결측복원을 위한 DCT-PLS 기법의 활용성 평가

윤유정 ( Youjeong Youn ),김서연 ( Seoyeon Kim ),정예민 ( Yemin Jeong ),조수빈 ( Subin Cho ),이양원 ( Yangwon Lee ) 대한원격탐사학회 2020 大韓遠隔探査學會誌 Vol.36 No.6

지구환경 변화를 파악하는 데 있어서는 장기 시계열의 격자자료가 필수적이며, 기후 재분석장과 위성 자료는 대기 및 지표면 변수에 대하여 전 지구 규모에서 주기적이고 정량적인 정보로 활용되고 있다. 본 연구에서는 위성자료의 결측 문제를 해결하기 위한 방안으로 DCT-PLS (penalized least square regression based on discrete cosine transform) 기반의 결측복원 기법을 서로 다른 특성을 가진 복수의 격자자료에 적용하고, 정량적인 검증을 통하여 그 활용성을 평가하였다. 원본 자료와의 객관적인 비교를 위하여 결측이 없는 LDAPS (Local Data Assimilation and Prediction System) 모델로부터 상대습도, 풍속 일자료를 추출하고, MODIS (Moderate Resolution Imaging Spectroradiometer)의 월간 합성 LST (land surface temperature), NDVI (normalized difference vegetation index) 영상을 사용하여, 임의로 생성된 결측 블록이 원본에 매우 가깝게 복원됨을 확인하였고, 4가지 변수 모두에서 상관계수 0.95 이상의 일치도를 나타내었다. DCT-PLS 기반 결측복원 기법은 별도의 보조자료를 필요로 하지 않고, 필요시 시간 및 공간 정보를 모두 활용할 수 있으며, 처리속도가 비교적 빠르기 때문에 현업시스템에 사용될 수 있을 것으로 사료된다. Long time-series gridded data is crucial for the analyses of Earth environmental changes. Climate reanalysis and satellite images are now used as global-scale periodical and quantitative information for the atmosphere and land surface. This paper examines the feasibility of DCT-PLS (penalized least square regression based on discrete cosine transform) for the spatial gap filling of gridded data through the experiments for multiple variables. Because gap-free data is required for an objective comparison of original with gap-filled data, we used LDAPS (Local Data Assimilation and Prediction System) daily data and MODIS (Moderate Resolution Imaging Spectroradiometer) monthly products. In the experiments for relative humidity, wind speed, LST (land surface temperature), and NDVI (normalized difference vegetation index), we made sure that randomly generated gaps were retrieved very similar to the original data. The correlation coefficients were over 0.95 for the four variables. Because the DCT-PLS method does not require ancillary data and can refer to both spatial and temporal information with a fast computation, it can be applied to operative systems for satellite data processing.

기온감률 보정과 최적크리깅을 이용한 산악기상관측망 기온자료의 우리나라 500미터 격자화

윤유정 ( Youjeong Youn ),김서연 ( Seoyeon Kim ),강종구 ( Jonggu Kang ),정예민 ( Yemin Jeong ),최소연 ( Soyeon Choi ),임윤교 ( Yungyo Im ),서영민 ( Youngmin Seo ),원명수 ( Myoungsoo Won ),천정화 ( Junghwa Chun ),김경민 ( Kyungmin K 대한원격탐사학회 2023 大韓遠隔探査學會誌 Vol.39 No.5

산악지역의 기상정보를 상세하고 적절히 제공하기 위해 산림청에서는 2012년부터 전국 주요 산악지역을 대상으로 산악기상관측망(Automatic Mountain Meteorology Observation Station, AMOS)을 구축하여, 2022년 현재 464개의 관측소가 운영되고 있다. 본 연구에서는 AMOS 지점 관측을 이용하여 우리나라 산림에 적합한 기온 격자자료를 산출하기 위해서, 기온감률 보정을 적용한 최적의 크리깅(kriging) 기법을 제안하고 그 가용성을 평가하였다. 우선 통계적 처리를 통해 AMOS 기온자료의 이상치를 제거하였고, 이 자료를 이용하여 경험 베리오그램(variogram)에 가장 근사하는 이론 베리오그램을 도출하여 최적화 크리깅을 수행하였다. 이 때 기온감률 보정(lapse rate correction)을 적용하여 산악지형의 고도 변이가 반영되는 500 m 해상도의 기온격자지도를 생성하였다. 공간적으로 치우치지 않은 검증샘플을 이용한 암맹평가를 통해 본 기법의 가용성을 평가한 결과, 0.899-0.953의 상관계수 및 0.933-1.230℃의 오차를 나타내 기온감률 보정을 적용하지 않은 정규크리깅에 비해 정확도가 다소 향상되었다. 또한 기온감률 크리깅은 우리나라 산림의 복잡지형을 잘 표현하여, 강원도 산간지역과 해안산림지역의 국지적인 변이 및 지리산·내장산과 그 주변 산림의 지형적 차이와 같은 미세한 지역특성을 살릴 수 있다는 것이 가장 큰 장점이라고 할 수 있다. To provide detailed and appropriate meteorological information in mountainous areas, the Korea Forest Service has established an Automatic Mountain Meteorology Observation Station (AMOS) network in major mountainous regions since 2012, and 464 stations are currently operated. In this study, we proposed an optimal kriging technique with lapse rate correction to produce gridded temperature data suitable for Korean forests using AMOS point observations. First, the outliers of the AMOS temperature data were removed through statistical processing. Then, an optimized theoretical variogram, which best approximates the empirical variogram, was derived to perform the optimal kriging with lapse rate correction. A 500-meter resolution Kriging map for temperature was created to reflect the elevation variations in Korean mountainous terrain. A blind evaluation of the method using a spatially unbiased validation sample showed a correlation coefficient of 0.899 to 0.953 and an error of 0.933 to 1.230℃, indicating a slight accuracy improvement compared to regular kriging without lapse rate correction. However, the critical advantage of the proposed method is that it can appropriately represent the complex terrain of Korean forests, such as local variations in mountainous areas and coastal forests in Gangwon province and topographical differences in Jirisan and Naejangsan and their surrounding forests.

산불위험지수 지역최적화를 통한 2022년 북한산불 사례분석

윤유정,김서연,최소연,박강현,강종구,김근아,권춘근,서경원,이양원,Youn, Youjeong,Kim, Seoyeon,Choi, Soyeon,Park, Ganghyun,Kang, Jonggu,Kim, Geunah,Kwon, Chunguen,Seo, Kyungwon,Lee, Yangwon 대한원격탐사학회 2022 大韓遠隔探査學會誌 Vol.38 No.6

Wildfires in North Korea can have a directly or indirectly affect South Korea if they go south to the Demilitarized Zone. Therefore, this study calculates the regional optimized Forest Fire Danger Index (FFDI) based on Local Data Assessment and Prediction System (LDAPS) weather data to obtain forest fire risk in North Korea, and applied it to the cases in Goseong-gun and Cheorwon-gun, North Korea in April 2022. As a result, the suitability was confirmed as the FFDI at the time of ignition corresponded to the risk class Extreme and Severe sections, respectively. In addition, a qualitative comparison of the risk map and the soil moisture map before and after the wildfire, the correlation was grasped. A new forest fire risk index that combines drought factors such as soil moisture, Standardized Precipitation Index (SPI), and Normalized Difference Water Index (NDWI) will be needed in the future.

YOLO를 이용한 SAR 영상의 선박 객체 탐지: 편파별 모델 구성과 정확도 특성 분석

임윤교,윤유정,강종구,김서연,정예민,최소연,서영민,이양원,Yungyo Im,Youjeong Youn,Jonggu Kang,Seoyeon Kim,Yemin Jeong,Soyeon Choi,Youngmin Seo,Yangwon Lee 대한원격탐사학회 2023 大韓遠隔探査學會誌 Vol.39 No.5

Ship detection at sea can be performed in various ways. In particular, satellites can provide wide-area surveillance, and Synthetic Aperture Radar (SAR) imagery can be utilized day and night and in all weather conditions. To propose an efficient ship detection method from SAR images, this study aimed to apply the You Only Look Once Version 5 (YOLOv5) model to Sentinel-1 images and to analyze the difference between individual vs. integrated models and the accuracy characteristics by polarization. YOLOv5s, which has fewer and lighter parameters, and YOLOv5x, which has more parameters but higher accuracy, were used for the performance tests (1) by dividing each polarization into HH, HV, VH, and VV, and (2) by using images from all polarizations. All four experiments showed very similar and high accuracy of 0.977 ≤ AP@0.5 ≤ 0.998. This result suggests that the polarization integration model using lightweight YOLO models can be the most effective in terms of real-time system deployment. 19,582 images were used in this experiment. However, if other SAR images,such as Capella and ICEYE, are included in addition to Sentinel-1 images, a more flexible and accurate model for ship detection can be built.

6SV2.1과 GK2A AOD를 이용한 기계학습 기반의 Sentinel-2 영상 대기보정

김서연,윤유정,강종구,정예민,최소연,임윤교,서영민,박찬원,이경도,나상일,안호용,류재현,이양원,Seoyeon Kim,Youjeong Youn,Jonggu Kang,Yemin Jeong,Soyeon Choi,Yungyo Im,Youngmin Seo,Chan-Won Park,Kyung-Do Lee,Sang-Il Na,Ho-Yong Ahn,Jae-Hyun Ryu 대한원격탐사학회 2023 大韓遠隔探査學會誌 Vol.39 No.5

In this letter, we simulated an atmospheric correction for Sentinel-2 images, of which spectral bands are similar to Compact Advanced Satellite 500-4 (CAS500-4). Using the second simulation of the satellite signal in the solar spectrum - vector (6SV)2.1 radiation transfer model and random forest (RF), a type of machine learning, we developed an RF-based atmospheric correction model to simulate 6SV2.1. As a result, the similarity between the reflectance calculated by 6SV2.1 and the reflectance predicted by the RF model was very high.

GK2A 일단위 NDVI의 과소추정 노이즈 실시간 보정

이수진,윤유정,손은하,김미자,이양원,Lee, Soo-Jin,Youn, Youjeong,Sohn, Eunha,Kim, Mija,Lee, Yangwon 대한원격탐사학회 2022 大韓遠隔探査學會誌 Vol.38 No.6

Normalized Difference Vegetation Index (NDVI) is utilized as an indicator to represent the vegetation condition on the land surface in various applications such as land cover, crop yield, agricultural drought, soil moisture, and forest disaster. However, satellite optical sensors for visible and infrared rays cannot see through the clouds, so the NDVI of the cloud pixel is not a valid value for the land surface. This study proposed a real-time correction of the underestimation noise for GEO-KOMPSAT-2A (GK2A) daily NDVI and made sure its feasibility through the quantitative comparisons with Moderate Resolution Imaging Spectroradiometer (MODIS) NDVI and the qualitative interpretation of time-series changes. The underestimation noise was effectively corrected by the procedures such as the time-series correction considering vegetation phenology, the outlier removal using long-term climatology, and the gap filling using rigorous statistical methods. The correlation with MODIS NDVI was higher, and the difference was lower, showing a 32.7% improvement compared to the original NDVI product. The proposed method has an extensibility for use in other satellite products with some modification.

MODIS와 ASOS 자료를 이용한 식물계절 모델링

김근아,윤유정,강종구,최소연,박강현,천정화,장근창,원명수,이양원,Kim, Geunah,Youn, Youjeong,Kang, Jonggu,Choi, Soyeon,Park, Ganghyun,Chun, Junghwa,Jang, Keunchang,Won, Myoungsoo,Lee, Yangwon 대한원격탐사학회 2022 大韓遠隔探査學會誌 Vol.38 No.5

최근 지구 온난화로 인한 기후 변화와 관련된 문제의 심각성이 커지고 있으며 평균 기온 또한 상승하고 있다. 이로 인해 온도에 민감한 다양한 생물과 생물이 살아가는 환경에 영향을 미치고 있으며, 생태계의 변화 역시 감지되고 있다. 계절은 그 지역에 사는 생물의 종류, 분포, 생육 특성 등에 영향을 미치는 중요한 요인의 하나이다. 기후 변화 영향 평가의 지표 중 가장 대중적이고 쉽게 인식될 수 있는 식물 계절 중 개화일과 단풍나무 절정일의 모델링을 수행하였다. 모델링에 사용된 식물의 종류에는 봄을 대표하는 식물로 볼 수 있는 개나리와 벚나무, 가을을 대표하는 식물로 볼 수 있는 단풍 나무와 은행 나무를 사용하였다. 모델링을 수행할 때 사용된 기상 자료로는 기상청의 Automated Surface Observing System (ASOS) 관측소를 통해서 관측된 기온, 강수, 일사 자료를 사용하였으며, 개나리, 벚나무의 개화일과 약 -0.2, 은행나무, 단풍나무의 단풍 절정일과 약 0.3 정도의 상관 계수를 가지는 Moderate Resolution Imaging Spectroradiometer (MODIS) 식생지수를 사용하여 모델링을 수행하였다. 사용된 모델로는 선형 모델인 다중 회귀 모형과, 비선형 모델인 Random Forest (RF)를 사용하여 모델을 수립하였다. 또한 각 모형으로 추정된 예측 값을 공간 내삽 기법을 이용하여 등치 선도로 2003~2020년의 식물 계절 변화 경향 성을 표현하였다. 향후에 높은 시공간 해상도를 가지는 식생지수를 사용한다면 더 높은 식물 계절 모델링의 정확도를 높일 수 있을 것으로 판단된다. Recently, the seriousness of climate change-related problems caused by global warming is growing, and the average temperature is also rising. As a result, it is affecting the environment in which various temperature-sensitive creatures and creatures live, and changes in the ecosystem are also being detected. Seasons are one of the important factors influencing the types, distribution, and growth characteristics of creatures living in the area. Among the most popular and easily recognized plant seasonal phenomena among the indicators of the climate change impact evaluation, the blooming day of flower and the peak day of autumn leaves were modeled. The types of plants used in the modeling were forsythia and cherry trees, which can be seen as representative plants of spring, and maple and ginkgo, which can be seen as representative plants of autumn. Weather data used to perform modeling were temperature, precipitation, and solar radiation observed through the ASOS Observatory of the Korea Meteorological Administration. As satellite data, MODIS NDVI was used for modeling, and it has a correlation coefficient of about -0.2 for the flowering date and 0.3 for the autumn leaves peak date. As the model used, the model was established using multiple regression models, which are linear models, and Random Forest, which are nonlinear models. In addition, the predicted values estimated by each model were expressed as isopleth maps using spatial interpolation techniques to express the trend of plant seasonal changes from 2003 to 2020. It is believed that using NDVI with high spatio-temporal resolution in the future will increase the accuracy of plant phenology modeling.

DeepLabV3+ 모델을 이용한 PlanetScope 영상의 해상 유출유 탐지

강종구,윤유정,김근아,박강현,최소연,양찬수,이종혁,이양원,Kang, Jonggu,Youn, Youjeong,Kim, Geunah,Park, Ganghyun,Choi, Soyeon,Yang, Chan-Su,Yi, Jonghyuk,Lee, Yangwon 대한원격탐사학회 2022 大韓遠隔探査學會誌 Vol.38 No.6

Since oil spills can be a significant threat to the marine ecosystem, it is necessary to obtain information on the current contamination status quickly to minimize the damage. Satellite-based detection of marine oil spills has the advantage of spatiotemporal coverage because it can monitor a wide area compared to aircraft. Due to the recent development of computer vision and deep learning, marine oil spill detection can also be facilitated by deep learning. Unlike the existing studies based on Synthetic Aperture Radar (SAR) images, we conducted a deep learning modeling using PlanetScope optical satellite images. The blind test of the DeepLabV3+ model for oil spill detection showed the performance statistics with an accuracy of 0.885, a precision of 0.888, a recall of 0.886, an F1-score of 0.883, and a Mean Intersection over Union (mIOU) of 0.793.

위성기반 산불피해지수를 이용한 북한지역 산불피해지 분석

김서연,윤유정,정예민,권춘근,서경원,이양원,Kim, Seoyeon,Youn, Youjeong,Jeong, Yemin,Kwon, Chunguen,Seo, Kyungwon,Lee, Yangwon 대한원격탐사학회 2022 大韓遠隔探査學會誌 Vol.38 No.6

Recent climate change can increase the frequency and damage of wildfires worldwide. It can also lead to the deterioration of the forest ecosystem and increase casualties and economic loss. Satellite-based indices for forest damage can facilitate an objective and rapid examination of burned areas and help analyze inaccessible places like North Korea. In this letter, we conducted a detection of burned areas in North Korea using the traditional Normalized Burn Ratio (NBR), the Normalized Difference Vegetation Index (NDVI) to represent vegetation vitality, and the Fire Burn Index (FBI) and Forest Withering Index (FWI) that were recently developed. Also, we suggested a strategy for the satellite-based detection of burned areas in the Korean Peninsula as a result of comparing the four indices. Future work requires the examination of small-size wildfires and the applicability of deep learning technologies.