• 대기
• /
• 제31권5호
• /
• pp.637-656
• /
• 2021

The United States has been known as the world's major producer of crops such as wheat, corn, and soybeans. Therefore, using meteorological long-term forecast data to project reliable crop yields in the United States is important for planning domestic food policies. The current study is part of an effort to improve the seasonal predictability of regional-scale precipitation across the United States for estimating crop production in the country. For the purpose, a dynamic downscaling method using Weather Research and Forecasting (WRF) model is utilized. The WRF simulation covers the crop-growing period (March to October) during 2000-2020. The initial and lateral boundary conditions of WRF are derived from the Pusan National University Coupled General Circulation Model (PNU CGCM), a participant model of Asia-Pacific Economic Cooperation Climate Center (APCC) Long-Term Multi-Model Ensemble Prediction System. For bias correction of downscaled daily precipitation, empirical quantile mapping (EQM) is applied. The downscaled data set without and with correction are called WRF_UC and WRF_C, respectively. In terms of mean precipitation, the EQM effectively reduces the wet biases over most of the United States and improves the spatial correlation coefficient with observation. The daily precipitation of WRF_C shows the better performance in terms of frequency and extreme precipitation intensity compared to WRF_UC. In addition, WRF_C shows a more reasonable performance in predicting drought frequency according to intensity than WRF_UC.

• 사물인터넷융복합논문지
• /
• 제9권6호
• /
• pp.111-117
• /
• 2023

시간-공간적 의존성을 모두 고려하는 방법으로 그래프 신경망과 순환 신경망을 함께 사용하는 연구가 많이 진행되고 있다. 특히 그래프 신경망은 새롭게 활발히 연구되고 있는 분야이다. 서울시 자전거 대여 서비스(일명 따릉이)는 서울시 곳곳에 대여소를 갖추고 있으며 각 대여소에서 대여 정보가 충실하게 기록되어 있는 시계열 자료이다. 각 대여소의 대여 정보는 시간에 따른 주기성을 보이는 시간적인 특성을 갖추고 있으며, 지역적인 특성도 대여 현황에 큰 영향을 미치리라고 생각된다. 지역적 상관관계는 그래프 신경망을 이용하여 잘 이해할 수 있다. 이 연구에서는 서울시 자전거 대여 서비스의 시계열 데이터를 그래프로 재구성하고 그래프 신경망과 순차 신경망을 결합한 대여 예측 모델을 개발하였다. 시간에 따른 주기성과 같은 시간 특성과 지역적인 특성 및 각 대여소의 중요도 정도를 고려하였다. 대여소의 중요도 정도는 대여량 예측에 중요한 인자로 사용됨을 확인하였다.

• 한국지반신소재학회논문집
• /
• 제22권1호
• /
• pp.67-74
• /
• 2023

경사면의 안정성을 모니터링 하기 위해 데이터 기반으로 사면의 붕괴를 예측, 경보를 하려는 연구가 증가하고 있다. 하지만 대부분의 논문에서는 데이터의 품질에 대해 간과하고 있다. 이는 오경보와 같은 문제를 발생시킬 수 있다. 이에 본 논문에서는 사면에서 수집된 데이터의 품질관리를 위한 규칙과 기계학습 모델로 구성된 2 단계의 접근 방안을 제안하였다. 규칙 기반은 높은 정확도와 직관적인 해석이 가능하다는 장점이 있으며 기계학습 모델은 명시적으로 표현할 수 없는 패턴을 도출할 수 있다는 장점이 있으며 2단계의 접근 방안은 이 두 장점을 모두 취할 수 있었다. 사례연구를 통해 두 방법을 단독으로 사용하였을 경우와 2단계의 접근 방안을 사용하였을 때의 성능을 비교하였고 2단계 접근 방안이 높은 성능을 보이는 것으로 판단되었다. 따라서 데이터의 품질관리를 위해 단독으로 두 방법을 사용하는 것보다 2단계 접근 방안 방법을 사용하는 것이 적절할것으로 판단된다.

• 환경영향평가
• /
• 제22권6호
• /
• pp.609-626
• /
• 2013

Air quality models have been widely used to study and simulate many air quality issues. In the simulation, it is important to raise the accuracy of meteorological predicted data because the results of air quality modeling is deeply connected with meteorological fields. Therefore in this study, we analyzed the effects of meteorological fields on the air quality simulation. This study was designed to evaluate MM5 predictions by using different initial condition data and different observations utilized in the data assimilation. Among meteorological scenarios according to these input data, the results of meteorological simulation using National Centers for Environmental Prediction (Final) Operational Global Analysis data were in closer agreement with the observations and resulted in better prediction on ozone concentration. And in Seoul, observations from Regional Meteorological Office for data assimilations of MM5 were suitable to predict ozone concentration. In other areas, data assimilation using both observations from Regional Meteorological Office and Automatical Weather System provided valid method to simulate the trends of meteorological fields and ozone concentrations. However, it is necessary to vertify the accuracy of AWS data in advance because slightly overestimated wind speed used in the data assimilation with AWS data could result in underestimation of high ozone concentrations.

• 한국대기환경학회지
• /
• 제24권1호
• /
• pp.1-15
• /
• 2008

Chemical Accident Response Information System (CARIS) which has been designed for the efficient emergency response of chemical accidents produces the real-time atmospheric fields through the Regional Atmospheric Modeling System, RAMS. The previous studies were emphasized that improving an initial input data had more effective results in developing prediction ability of atmospheric model. In a continuous effort to improve an initial input data, we replaced the land-use dataset using in the RAMS, which is a high resolution USGS digital data constructed in April, 1993, with the latest land-use data of the Korea Ministry of Environment over the South Korea and simulated atmospheric fields for developing a real-time prediction in dispersion of chemicals. The results showed that the new land-use data was written in a standard RAMS format and shown the modified surface characteristics and the landscape heterogeneity resulting from land-use change. In the results of sensitivity experiment we got the improved atmospheric fields and assured that it will give more reliable real-time atmospheric fields to all users of CARIS for the dispersion forecast in associated with hazardous chemical releases as well as general air pollutants.

• 한국농공학회논문집
• /
• 제66권1호
• /
• pp.1-13
• /
• 2024

This study assessed the efficacy of improving the accuracy of reservoir water level prediction models by employing automated machine learning models and efficient cross-validation methods for time-series data. Considering the inherent complexity and non-linearity of time-series data related to reservoir water levels, we proposed an optimized approach for model selection and training. The performance of twelve models was evaluated for the Obong Reservoir in Gangneung, Gangwon Province, using the TPOT (Tree-based Pipeline Optimization Tool) and four cross-validation methods, which led to the determination of the optimal pipeline model. The pipeline model consisting of Extra Tree, Stacking Ridge Regression, and Simple Ridge Regression showed outstanding predictive performance for both training and test data, with an R² (Coefficient of determination) and NSE (Nash-Sutcliffe Efficiency) exceeding 0.93. On the other hand, for predictions of water levels 12 hours later, the pipeline model selected through time-series split cross-validation accurately captured the change pattern of time-series water level data during the test period, with an NSE exceeding 0.99. The methodology proposed in this study is expected to greatly contribute to the efficient generation of reservoir water level predictions in regions with high rainfall variability.

• 대기
• /
• 제27권1호
• /
• pp.17-28
• /
• 2017

The sensitivity of the typhoon track and intensity simulation to physics schemes of the global model are examined for the typhoon Bolaven and Tembin cases by using the Global/Regional Integrated Model System-Global Model Program (GRIMs-GMP) with the physics package version 2.0 of the Korea Institute of Atmospheric Prediction Systems. Microphysics, Cloudiness, and Planetary boundary Layer (PBL) parameterizations are changed and the impact of each scheme change to typhoon simulation is compared with the control simulation and observation. It is found that change of microphysics scheme from WRF Single-Moment 5-class (WSM5) to 1-class (WSM1) affects to the typhoon simulation significantly, showing the intensified typhoon activity and increased precipitation amount, while the effect of the prognostic cloudiness and PBL enhanced mixing scheme is not noticeable. It appears that WSM1 simulates relatively unstable and drier atmospheric structure than WSM5, which is induced by the latent heat change and the associated radiative effect due to not considering ice cloud. And WSM1 results the enhanced typhoon intensity and heavy rainfall simulation. It suggests that the microphysics is important to improve the capability for typhoon simulation of a global model and to increase the predictability of medium range forecast.

• Nuclear Engineering and Technology
• /
• 제44권4호
• /
• pp.355-362
• /
• 2012

The aim of this study was to develop a bundle position-wise linear model (BPLM) to predict Pressure Tube (PT) diametral creep employing the previously measured PT diameters and operating conditions. There are twelve bundles in a fuel channel, and for each bundle a linear model was developed by using the dependent variables, such as the fast neutron fluences and the bundle coolant temperatures. The training data set was selected using the subtractive clustering method. The data of 39 channels that consist of 80 percent of a total of 49 measured channels from Units 2, 3, and 4 of the Wolsung nuclear plant in Korea were used to develop the BPLM. The data from the remaining 10 channels were used to test the developed BPLM. The BPLM was optimized by the maximum likelihood estimation method. The developed BPLM to predict PT diametral creep was verified using the operating data gathered from Units 2, 3, and 4. Two error components for the BPLM, which are the epistemic error and the aleatory error, were generated. The diametral creep prediction and two error components will be used for the generation of the regional overpower trip setpoint at the corresponding effective full power days. The root mean square (RMS) errors were also generated and compared to those from the current prediction method. The RMS errors were found to be less than the previous errors.

• 대기
• /
• 제22권4호
• /
• pp.455-464
• /
• 2012

This study investigates a 12 month-lead predictability of PNU Coupled General Circulation Model (CGCM) V1.1 hindcast, for which an oceanic data assimilated initialization is used to generate ocean initial condition. The CGCM, a participant model of APEC Climate Center (APCC) long-lead multi-model ensemble system, has been initialized at each and every month and performed 12-month-lead hindcast for each month during 1980 to 2011. The 12-month-lead hindcast consisted of 2-5 ensembles and this study verified the ensemble averaged hindcast. As for the sea-surface temperature concerns, it remained high level of confidence especially over the tropical Pacific and the mid-latitude central Pacific with slight declining of temporal correlation coefficients (TCC) as lead month increased. The CGCM revealed trustworthy ENSO prediction skills in most of hindcasts, in particular. For atmospheric variables, like air temperature, precipitation, and geopotential height at 500hPa, reliable prediction results have been shown during entire lead time in most of domain, particularly over the equatorial region. Though the TCCs of hindcasted precipitation are lower than other variables, a skillful precipitation forecasts is also shown over highly variable regions such as ITCZ. This study also revealed that there are seasonal and regional dependencies on predictability for each variable and lead.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제13권9호
• /
• pp.4665-4683
• /
• 2019

Previous methods build image annotation model by leveraging three basic dependencies: relations between image and label (image/label), between images (image/image) and between labels (label/label). Even though plenty of researches show that multiple dependencies can work jointly to improve annotation performance, different dependencies actually do not "work jointly" in their diagram, whose performance is largely depending on the result predicted by image/label section. To address this problem, we propose the adaptive attention annotation model (AAAM) to associate these dependencies with the prediction path, which is composed of a series of labels (tags) in the order they are detected. In particular, we optimize the prediction path by detecting the relevant labels from the easy-to-detect to the hard-to-detect, which are found using Binary Cross-Entropy (BCE) and Triplet Margin (TM) losses, respectively. Besides, in order to capture the inforamtion of each label, instead of explicitly extracting regional featutres, we propose the self-attention machanism to implicitly enhance the relevant region and restrain those irrelevant. To validate the effective of the model, we conduct experiments on three well-known public datasets, COCO 2014, IAPR TC-12 and NUSWIDE, and achieve better performance than the state-of-the-art methods.