• Korean Journal of Remote Sensing
• /
• v.39 no.2
• /
• pp.207-221
• /
• 2023

This study suggests deep neural network models for estimating air temperature with Level 1B (L1B) datasets of GEO-KOMPSAT-2A (GK-2A). The temperature at 1.5 m above the ground impact not only daily life but also weather warnings such as cold and heat waves. There are many studies to assume the air temperature from the land surface temperature (LST) retrieved from satellites because the air temperature has a strong relationship with the LST. However, an algorithm of the LST, Level 2 output of GK-2A, works only clear sky pixels. To overcome the cloud effects, we apply a deep neural network (DNN) model to assume the air temperature with L1B calibrated for radiometric and geometrics from raw satellite data and compare the model with a linear regression model between LST and air temperature. The root mean square errors (RMSE) of the air temperature for model outputs are used to evaluate the model. The number of 95 in-situ air temperature data was 2,496,634 and the ratio of datasets paired with LST and L1B show 42.1% and 98.4%. The training years are 2020 and 2021 and 2022 is used to validate. The DNN model is designed with an input layer taking 16 channels and four hidden fully connected layers to assume an air temperature. As a result of the model using 16 bands of L1B, the DNN with RMSE 2.22℃ showed great performance than the baseline model with RMSE 3.55℃ on clear sky conditions and the total RMSE including overcast samples was 3.33℃. It is suggested that the DNN is able to overcome cloud effects. However, it showed different characteristics in seasonal and hourly analysis and needed to append solar information as inputs to make a general DNN model because the summer and winter seasons showed a low coefficient of determinations with high standard deviations.

• Journal of Korea Multimedia Society
• /
• v.13 no.12
• /
• pp.1760-1766
• /
• 2010

The linearized suffix tree (LST) is an array data structure supporting traversals on suffix trees. We apply this LST to two dimensional (2D) suffix trees and obtain a space-efficient substitution of 2D suffix trees. Given an $n{\times}n$ text matrix and an $m{\times}m$ pattern matrix over an alphabet ${\Sigma}$, our 2D-LST provides pattern matching in $O(m^2log{\mid}{\Sigma}{\mid})$ time and $O(n^2)$ space.

• Tribology and Lubricants
• /
• v.26 no.1
• /
• pp.1-6
• /
• 2010

In the last decade, laser surface texturing (LST) has emerged as a viable option of surface engineering. Many problems related with mechanical components such as thrust bearings, mechanical face seals and piston rings, etc, LST result in significant improvement in load capacity, wear resistance and reduction in friction force. It is mainly experimentally reported the micro-dimpled bearing surfaces can reduce friction force, however, precise theoretical results are not presented until now. In this paper, a commercial computational fluid dynamics(CFD) code, FLUENT is used to investigate the lubrication characteristics of a parallel thrust bearing having 3-dimensional micro-dimple. The results show that the pressure, velocity and density distributions are highly affected by the location and number of dimple. The numerical method and results can be use in design of optimum dimple characteristics, and further researches are required.

• Journal of Environmental Impact Assessment
• /
• v.12 no.4
• /
• pp.303-313
• /
• 2003

This study was carried out to survey the high ozone episode of summertime in Busan. The selected day was July 18, 1999 and August 24, 2001 which recorded exceed to 12ppb/hr at 3 station in Busan simultaneously. In case July 18, 1999, thick cloud and variable wind made weak ozone concentration during morning hour. And increase of ozone concentration by revolution of mixed layer for morning hour did not occur in this case study day. Photochemical reaction by strong radiation after 1100LST made sharp increase rate of ozone concentration(50ppb/hr). In case August 24, 2001, the meteorological condition of this day was not general wind with gradient force, very clear day with less cloud amount, high insolation and sunshine. Dongsamdong, Beomcheondong, Daeyeondong, and Sinpyeongdong had double peak which twice maximum concentration in the early afternoon and late afternoon. Ozone concentration of this day was in inverse proportion to Nitrogen oxide strongly. Ozone concentration exceed to 60ppb/hr occurred at 1400LST, continued to 2300LST.

• ETRI Journal
• /
• v.31 no.4
• /
• pp.454-456
• /
• 2009

The maximum likelihood linear spectral transformation (ML-LST) using a numerical iteration method has been previously proposed for robust speech recognition. The numerical iteration method is not appropriate for real-time applications due to its computational complexity. In order to reduce the computational cost, the objective function of the ML-LST is approximated and a closed-form solution is proposed in this paper. It is shown experimentally that the proposed closed-form solution for the ML-LST can provide rapid speaker and environment adaptation for robust speech recognition.

• Proceedings of the KSPS conference
• /
• 2005.04a
• /
• pp.53-56
• /
• 2005

In this paper, we propose a transformation based robust adaptation technique that uses the maximum mutual information(MMI) estimation for the objective function and the linear spectral transformation(LST) for adaptation. LST is an adaptation method that deals with environmental noises in the linear spectral domain, so that a small number of parameters can be used for fast adaptation. The proposed technique is called MMI-LST, and evaluated on TIMIT and FFMTIMIT corpora to show that it is advantageous when only a small amount of adaptation speech is used.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2010.05a
• /
• pp.1016-1020
• /
• 2010

본 연구는 충북 청주시에 위치한 무심천 주변을 대상으로 하천이 도시 주변 열 환경에 미치는 영향에 대해 원격탐사(Remote Sensing; RS)기법을 이용하여 분석하였다. 열 환경 특성 분석 순서는 먼저 Landsat 5 TM 위성영상의 열적외 밴드를 이용하여 대상지역의 표면 온도(Land Surface Temperature; LST)를 추출하였다. 다음으로 추출된 LST를 이용하여 무심천을 중심으로 주변의 공업단지와 주거지, 산림 지역의 지표면 온도 분포를 비교 분석하여 하천이 주변의 열 환경에 미치는 영향을 정량화하였다. 또한 공간적 특성 분석을 위해 등온선을 작성하여 하천 주변 열 환경을 파악하였다. 그 결과 온도분포에 따른 열 이동의 크기와 방향을 확인할 수 있었고 열 분포의 공간분포는 공업지>주거지>하천>산림 순으로 나타나 토지이용특성에 따른 열 분포의 경향을 파악할 수 있었다.

• Journal of Environmental Science International
• /
• v.2 no.2
• /
• pp.103-113
• /
• 1993

The land and sea breeze over the Pusan coastal area is studied by three dimensional mesoscale numerical model. According to the results of the simulation experiments, both Pusan areas and Kimhae areas, the sea breeze began at 0800LST and the strongest at 1500LST and then at 1800LST. After midnight, the sea breeze changed about the land breeze and become weaker than that of the sea breeze in the daytime. Comparisons between calculations and observations showed that the characteristics of diurnal variation and v-component of the wind velocity relatively is similar to the Pusan areas. On the Kimhae areas, however, observations showed time lag which compared to the results of simulation experiments in the velocity of sea breeze and diurnal variation. From the above results, comparisons between calculations and observations is much more similar to the coastal areas than on the inland area.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2019.05a
• /
• pp.140-140
• /
• 2019

본 연구에서는 Terra MODIS 위성자료와 Tensorflow를 활용해 1 km 공간 해상도의 토양수분을 산정하는 알고리즘을 개발하고, 국내 관측 자료를 활용해 검증하고자 한다. 토양수분 모의를 위한 입력 자료는 Terra MODIS NDVI(Normalized Difference Vegetation Index)와 LST(Land Surface Temperature), GPM(Global Precipitation Measurement) 강우 자료를 구축하고, 농촌진흥청에서 제공하는 1:25,000 정밀토양도를 기반으로 모의하였다. 여기서, LST와 GPM의 자료는 기상청의 종관기상관측지점의 LST, 강우 자료와 조건부합성(Conditional Merging, CM) 기법을 적용해 결측치를 보간하였고, 모든 위성 자료의 공간해상도를 1 km로 resampling하여 활용하였다. 토양수분 산정 기술은 인공 신경망(Artificial Neural Network) 모형의 딥 러닝(Deep Learning)을 적용, 기계 학습기반의 패턴학습을 사용하였다. 패턴학습에는 Python 라이브러리인 TensorFlow를 사용하였고 학습 자료로는 농촌진흥청 농업기상정보서비스에서 101개 지점의 토양수분 자료(2014 ~ 2016년)를 활용하고, 모의 결과는 2017 ~ 2018년까지의 자료로 검증하고자 한다.

• Spatial Information Research
• /
• v.22 no.1
• /
• pp.55-63
• /
• 2014

Near surface air temperature data which are one of the essential factors in hydrology, meteorology and climatology, have drawn a substantial amount of attention from various academic domains and societies. Meteorological observations, however, have high spatio-temporal constraints with the limits in the number and distribution over the earth surface. To overcome such limits, many studies have sought to estimate the near surface air temperature from satellite image data at a regional or continental scale with simple regression methods. Alternatively, we applied various Kriging methods such as ordinary Kriging, universal Kriging, Cokriging, Regression Kriging in search of an optimal estimation method based on near surface air temperature data observed from automatic weather stations (AWS) in South Korea throughout 2010 (365 days) and MODIS land surface temperature (LST) data (MOD11A1, 365 images). Due to high spatial heterogeneity, auxiliary data have been also analyzed such as land cover, DEM (digital elevation model) to consider factors that can affect near surface air temperature. Prior to the main estimation, we calculated root mean square error (RMSE) of temperature differences from the 365-days LST and AWS data by season and landcover. The results show that the coefficient of variation (CV) of RMSE by season is 0.86, but the equivalent value of CV by landcover is 0.00746. Seasonal differences between LST and AWS data were greater than that those by landcover. Seasonal RMSE was the lowest in winter (3.72). The results from a linear regression analysis for examining the relationship among AWS, LST, and auxiliary data show that the coefficient of determination was the highest in winter (0.818) but the lowest in summer (0.078), thereby indicating a significant level of seasonal variation. Based on these results, we utilized a variety of Kriging techniques to estimate the surface temperature. The results of cross-validation in each Kriging model show that the measure of model accuracy was 1.71, 1.71, 1.848, and 1.630 for universal Kriging, ordinary Kriging, cokriging, and regression Kriging, respectively. The estimates from regression Kriging thus proved to be the most accurate among the Kriging methods compared.