• 한국농림기상학회지
• /
• 제4권1호
• /
• pp.23-28
• /
• 2002

CART(Classification and Regression Tree) 모형을 이용해서 결로시간 예측에 필요한 기상변수들을 평가하였다. 입력 기상 변수들은 0.3m와 1.5m에서 측정된 기온, 상대습도, 풍속의 시간별 측정값으로서 이 관측 값들은 1997년부터 1999년 5월에서 9월 사이에 미국의 Iowa, Illinois 및 Nebraska주에 위치한 15개 자동 기상 관측소에서 관측된 것이다. 0.3 m에서 측정된 기온, 상대습도, 그리고 풍속을 이용해서 얻어진 모형이 가장 높은 결로시간의 예측 적중율(85.5%)을 보였으며, 이 모형은 Gleason 등(1994)의 CART/SLD 모형의 적중률(84.7%) 보다 다소 높았다. 그러나 새로운 변수를 추가한 경우에 정확도의 향상이 다소 있었으나 CART/SLD 모형을 대체할 정도는 아니었다. 따라서, 기온, 상대습도, 풍속들의 종관 기상관측값들을 입력변수로 사용하는 CART/SLD 모형이 종관 기상관측 자료 이외의 추가적인 자료를 필요로 하는 모형으로 결로시간을 예측하는 것보다 합리적일 것으로 보인다.

• 수산해양기술연구
• /
• 제47권1호
• /
• pp.46-58
• /
• 2011

A steady-state analysis and a simple dynamic model as simplified methods are developed, and results of energy consumption loads are compared with results obtained using computer to evaluate the analytical solution. Before obtaining simplified model a mathematical model is formulated for the effect of wall mass on the thermal performance of four different houses having various wall construction. This analytical study was motivated by the experimental work of Burch et al. An analytical solution of one-dimensional, linear, partial differential equation for wall temperature profiles and room air temperatures is obtained using the Laplace transform method. Typical Meteorological Year data are processed to yield hourly average monthly values. This study is conducted using weather data from four different locations in the United States: Albuquerque, New mexico; Miami, Florida; Santa Maria, California; and Washington D.C. for both winter and summer conditions. The steady state analysis that does not include the effect of thermal mass can provide an accurate estimate of energy consumption in most cases except for houses #2 and #4 in mild weather areas. This result shows that there is an effect of mass on the thermal performance of heavily constructed house in mild weather conditions. The simple dynamic model is applicable for high cycling rates and accurate values of inside wall temperature and ambient air temperature.

• Water Engineering Research
• /
• 제3권2호
• /
• pp.113-122
• /
• 2002

Accurate quantitative forecasting of rainfall for basins with a short response time is essential to predict flash floods. In this study, a Quantitative Flood Forecasting (QFF) model was developed by incorporating the evolving structure and frequency of intense weather systems and by using neural network approach. Besides using radiosonde and rainfall data, the model also used the satellite-derived characteristics of storm systems such as tropical cyclones, mesoscale convective complex systems and convective cloud clusters as input. The convective classification and tracking system (CCATS) was used to identify and quantify storm properties such as lifetime, area, eccentricity, and track. As in standard expert prediction systems, the fundamental structure of the neural network model was learned from the hydroclimatology of the relationships between weather system, rainfall production and streamflow response in the study area. All these processes stretched leadtime up to 18 hours. The QFF model will be applied to the mid-Atlantic region of United States in a forthcoming paper.

• 한국IT서비스학회지
• /
• 제18권1호
• /
• pp.173-186
• /
• 2019

Recently, as the amount of fine dust has risen rapidly, our interest is increasing day by day. It is virtually impossible to remove fine dust. However, it is best to predict the concentration of fine dust and minimize exposure to it. In this study, we developed a mathematical model that can predict the concentration of fine dust using various information related to the weather and air quality, which is provided in real time in 'Air Korea (http://www.airkorea.or.kr/)' and 'Weather Data Open Portal (https://data.kma.go.kr/).' In the mathematical model, various domestic seasonal variables and atmospheric state variables are extracted by multiple regression analysis. The parameters that have significant influence on the fine dust concentration are extracted, and using ANN (Artificial Neural Network) and SVM (Support Vector Machine), which are machine learning techniques, we proposed a prediction model. The proposed model can verify its effectiveness by using past dust and weather big data.

• 한국수자원학회:학술대회논문집
• /
• 한국수자원학회 2009년도 학술발표회 초록집
• /
• pp.540-544
• /
• 2009

Hydrologic pattern under climate change has been paid attention to as one of the most important issues in hydrologic science group. Rainfall and runoff is a key element in the Earth's hydrological cycle, and associated with many different aspects such as water supply, flood prevention and river restoration. In this regard, a main objective of this study is to evaluate design flood using simulation techniques which can consider a full spectrum of uncertainty. Here we utilize a weather state based stochastic multivariate model as conditional probability model for simulating the rainfall field. A major premise of this study is that large scale climatic patterns are a major driver of such persistent year to year changes in rainfall probabilities. Uncertainty analysis in estimating design flood is inevitably needed to examine reliability for the estimated results. With regard to this point, this study applies a Bayesian Markov Chain Monte Carlo scheme to the NWS-PC rainfall-runoff model that has been widely used, and a case study is performed in Soyang Dam watershed in Korea. A comprehensive discussion on design flood under climate change is provided.

• Water Engineering Research
• /
• 제3권2호
• /
• pp.123-134
• /
• 2002

A developed Quantitative Flood Forecasting (QFF) model was applied to the mid-Atlantic region of the United States. The model incorporated the evolving structure and frequency of intense weather systems of the study area for improved flood forecasting. Besides using radiosonde and rainfall data, the model also used the satellite-derived characteristics of storm systems such as tropical cyclones, mesoscale convective complex systems and convective cloud clusters associated with synoptic atmospheric conditions as Input. Here, we present results from the application of the Quantitative Flood Forecasting (QFF) model in 2 small watersheds along the leeward side of the Appalachian Mountains in the mid-Atlantic region. Threat scores consistently above 0.6 and close to 0.8 ∼ 0.9 were obtained fur 18 hour lead-time forecasts, and skill scores of at least 40% and up to 55 % were obtained.

• The Plant Pathology Journal
• /
• 제21권2호
• /
• pp.111-118
• /
• 2005

Weather data for disease forecasts are usually derived from automated weather stations (AWS) that may be dispersed across a region in an irregular pattern. We have developed an alternative method to simulate local scale, high-resolution weather and plant disease in a grid pattern. The system incorporates a simplified mesoscale boundary layer model, LAWSS, for estimating local conditions such as air temperature and relative humidity. It also integrates special models for estimating of surface wetness duration and disease forecasts, such as the grapevine downy mildew forecast model, DMCast. The system can recreate weather forecasts utilizing the NCEP/NCAR reanalysis database, which contains over 57 years of archived and corrected global upper air conditions. The highest horizontal resolution of 0.150 km was achieved by running 5-step nested child grids inside coarse mother grids. Over the Finger Lakes and Chautauqua Lake regions of New York State, the system simulated three growing seasons for estimating the risk of grape downy mildew with 1 km resolution. Outputs were represented as regional maps or as site-specific graphs. The highest resolutions were achieved over North America, but the system is functional for any global location. The system is expected to be a powerful tool for site selection and reanalysis of historical plant disease epidemics.

• 한국국방경영분석학회지
• /
• 제25권1호
• /
• pp.169-177
• /
• 1999

There is some limitations for ship to gather weather and sea state information. To make up for this weakness, land organizations can gather the wider variety of information, evaluate the navigational safety on a ship, and supply this information to the ship. In this study, the involuntary speed loss are calculated using the real-time information on weather and considering the increase of resistance induced by wave, and the navigational safety in a seaway is evaluated. The used model for computer simulation is Lpp 93m frigate class ship. The feasibility study is made of using simulation results in actual operation.

• 한국수자원학회:학술대회논문집
• /
• 한국수자원학회 2009년도 학술발표회 초록집
• /
• pp.1142-1146
• /
• 2009

A rainfall simulation and forecasting technique that can generate daily rainfall sequences conditional on multi-model ensemble GCMs is developed and applied to data in Korea for the major rainy season. The GCM forecasts are provided by APEC climate center. A Weather State Based Downscaling Model (WSDM) is used to map teleconnections from ocean-atmosphere data or key state variables from numerical integrations of Ocean-Atmosphere General Circulation Models to simulate daily sequences at multiple rain gauges. The method presented is general and is applied to the wet season which is JJA(June-July-August) data in Korea. The sequences of weather states identified by the EM algorithm are shown to correspond to dominant synoptic-scale features of rainfall generating mechanisms. Application of the methodology to seasonal rainfall forecasts using empirical teleconnections and GCM derived climate forecast are discussed.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제14권8호
• /
• pp.3567-3582
• /
• 2020

Human activities are often affected by weather conditions. Automatic weather recognition is meaningful to traffic alerting, driving assistance, and intelligent traffic. With the boost of deep learning and AI, deep convolutional neural networks (CNN) are utilized to identify weather situations. In this paper, a three-channel convolutional neural network (3C-CNN) model is proposed on the basis of ResNet50.The model extracts global weather features from the whole image through the ResNet50 branch, and extracts the sky and ground features from the top and bottom regions by two CNN5 branches. Then the global features and the local features are merged by the Concat function. Finally, the weather image is classified by Softmax classifier and the identification result is output. In addition, a medium-scale dataset containing 6,185 outdoor weather images named WeatherDataset-6 is established. 3C-CNN is used to train and test both on the Two-class Weather Images and WeatherDataset-6. The experimental results show that 3C-CNN achieves best on both datasets, with the average recognition accuracy up to 94.35% and 95.81% respectively, which is superior to other classic convolutional neural networks such as AlexNet, VGG16, and ResNet50. It is prospected that our method can also work well for images taken at night with further improvement.