• 한국수자원학회:학술대회논문집
• /
• 한국수자원학회 2002년도 학술발표회 논문집(I)
• /
• pp.43-50
• /
• 2002

Accurate quantitative forecasting of rainfall for basins with a short response time is essential to predict streamflow and flash floods. Previously, neural networks were used to develop a Quantitative Precipitation Forecasting (QPF) model that highly improved forecasting skill at specific locations in Pennsylvania, using both Numerical Weather Prediction (NWP) output and rainfall and radiosonde data. The objective of this study was to improve an existing artificial neural network model and incorporate the evolving structure and frequency of intense weather systems in the mid-Atlantic region of the United States 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 as input. The convective classification and tracking system (CCATS) was used to identify and quantify storm properties such as life time, 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. The new Quantitative Flood Forecasting (QFF) model was applied to predict streamflow peaks with lead-times of 18 and 24 hours over a five year period in 4 watersheds on the leeward side of the Appalachian mountains in the mid-Atlantic region. Threat scores consistently above .6 and close to 0.8 ∼ 0.9 were obtained fur 18 hour lead-time forecasts, and skill scores of at least 4％ and up to 6％ were attained for the 24 hour lead-time forecasts. This work demonstrates that multisensor data cast into an expert information system such as neural networks, if built upon scientific understanding of regional hydrometeorology, can lead to significant gains in the forecast skill of extreme rainfall and associated floods. In particular, this study validates our hypothesis that accurate and extended flood forecast lead-times can be attained by taking into consideration the synoptic evolution of atmospheric conditions extracted from the analysis of large-area remotely sensed imagery While physically-based numerical weather prediction and river routing models cannot accurately depict complex natural non-linear processes, and thus have difficulty in simulating extreme events such as heavy rainfall and floods, data-driven approaches should be viewed as a strong alternative in operational hydrology. This is especially more pertinent at a time when the diversity of sensors in satellites and ground-based operational weather monitoring systems provide large volumes of data on a real-time basis.

• 대기
• /
• 제25권4호
• /
• pp.611-622
• /
• 2015

Heavy rainfall ($>30mm\;hr^{-1}$) over the Korean Peninsula is examined in order to understand thermo-dynamic characteristics of the atmosphere, using radiosonde observational data from seven upper-air observation stations during the last 17 years (1997~2013). A total of 82 heavy rainfall cases during the summer season (June-August) were selected for this study. The average values of thermo-dynamic indices of heavy rainfall events are Total Precipitable Water (TPW) = 60 mm, Convective Available Potential Energy (CAPE) = $850J\;kg^{-1}$, Convective Inhibition (CIN) = $15J\;kg^{-1}$, Storm Relative Helicity (SRH) = $160m^2s^{-2}$, and 0~3 km bulk wind shear = $5s^{-1}$. About 34% of the cases were associated with a Changma front; this pattern is more significant than other synoptic pressure patterns such as troughs (22%), migratory cyclones (15%), edges of high-pressure (12%), typhoons (11%), and low-pressure originating from Changma fronts (6%). The spatial distribution of thermo-dynamic conditions (CAPE and SRH) is similar to the range of thunderstorms over the United States, but extreme conditions (supercell thunderstorms and tornadoes) did not appear in the Korean Peninsula. Synoptic conditions, vertical buoyancy (CAPE, CIN), and wind parameters (SRH, shear) are shown to discriminate among the environments of the three types. The first type occurred with high CAPE and low wind shear by the edge of the high pressure pattern, but Second type is related to Changma front and typhoon, exhibiting low CAPE and high wind shear. The last type exhibited characteristics intermediate between the first and second types, such as moderate CAPE and wind shear near the migratory cyclone and trough.

• 한국ITS학회 논문지
• /
• 제17권6호
• /
• pp.121-132
• /
• 2018

기상은 교통흐름, 운전자의 주행패턴, 교통사고 등 여러 방면에서 도로교통에 영향을 미치는 중요한 요인이다. 본 연구는 기상상황과 노면상태 사이의 관계에 초점을 맞추어 기계학습을 통해 도로의 노면상태를 추정하는 모델을 개발하였다. 노면 상태의 수집을 위해 실험 차량에 노면센서를 부착하여 '건조', '습윤', '젖음', 3가지 범주로 구분된 노면상태 정보를 수집하였고, 이를 추정하기 위한 변수로 도로의 기하구조 정보(곡률, 구배), 교통정보(교통량), 기상정보(강우량, 습도, 온도, 풍속)를 활용하였다. 노면 상태를 예측하기 위한 알고리즘으로는 다양한 기계학습 알고리즘이 검토되었으며, 그 중 가장 높은 정확도를 보인 'Random forest'를 기반으로 한 2단계 분류모형을 구축하였다. 총 16일의 실측 데이터 중 14일의 데이터를 모델을 학습하는 데 활용하였고, 2일의 데이터를 모형의 정확도를 검증하기 위해 사용하였다. 그 결과 81.74%의 검증 정확도를 가지는 노면상태 예측 모델을 구축하였다. 본 연구의 결과는 기상청에서 관측하는 기상정보로 도로의 노면상태를 추정할 수 있다는 가능성을 보여주며, 새로운 장비나 센서를 설치하지 않고도 기존의 기상 관측 정보와 교통정보 등을 활용하여 노면의 상태를 추정할 수 있음을 시사한다.

• 한국농림기상학회지
• /
• 제17권2호
• /
• pp.102-107
• /
• 2015

본 연구에서는 중국의 동북지역 기후자료를 수집하여 DB를 구축하고, 이들 기후자료를 활용하여 농업기후지대를 구분함으로써 대상지역의 농업기상특성 분석의 기초정보를 확보하고자 하였으며, 국외의 주요 곡물 수출국의 기상관측정보를 수집, 분석, 제공할 수 있는 체계를 구축하고자 하였다. 중국 동북지역 농업기후지대를 구분하기 위하여 미국 항공우주국의 전 지구 모델링 및 동화 센터의 1979-2010년까지 32년 동안의 월별 기온 및 강수량 자료와 Weather Research and Forecasting(WRF) 모형의 동아시아 영역의 해발고도와 식물비 자료를 활용하였다. 중국 동북지역은 해발고도는 200m 이하, 200-800m, 800m 이상, 식물비 60%, 연평균 기온은 $0^{\circ}C$, 최난월 기온은 $22^{\circ}C$, 연평균 강수량 700mm를 기준으로 22개 농업기후지대로 구분되었다. 22개 농업기후지대는 연평균기온은 $3.4^{\circ}C$, 강수량 613.2mm, 일사량 $4,414.2MJ/m^2$의 기후특성을 보였다.

• 한국환경농학회지
• /
• 제38권1호
• /
• pp.34-37
• /
• 2019

BACKGROUND: A region can be divided into agroclimatic zones based on homogeneity in weather variables that have greatest influence on crop growth and yield. The agro-climatic zone has been used to identify yield variability and limiting factors for crop growth. This study was conducted to classify agro-climatic zones in the state of Mato Grosso in Brazil for predicting crop productivity and assessing crop suitability etc. METHODS AND RESULTS: For agro-climatic zonation, monthly mean temperature, precipitation, and solar radiation data from Global Modeling and Assimilation Office (GMAO) of National Aeronautics and Space Administration (NASA, USA) between 1980 and 2010 were collected. Altitude and vegetation fraction of Brazil from Weather Research and Forecasting (WRF) were also used to classify them. The criteria of agro-climatic classification were temperature in the hottest month ($30^{\circ}C$), annual precipitation (600 mm and 1000 mm), and altitude (200 m and 500 m). The state of Mato Gross in Brazil was divided into 9 agro-climatic zones according to these criteria by using matrix classification method. CONCLUSION: The results could be useful as information for estimating agro-meteorological characteristics and predicting crop development and crop yield in the state of Mato Grosso in Brazil.

• 천문학회보
• /
• 제40권1호
• /
• pp.64.3-64.3
• /
• 2015

We have developed a set of daily solar flare peak flux forecast models for strong flares using multiple linear regression and artificial neural network methods. We consider input parameters as solar activity data from January 1996 to December 2013 such as sunspot area, X-ray flare peak flux and weighted total flux of previous day, and mean flare rates of McIntosh sunspot group (Zpc) and Mount Wilson magnetic classification. For a training data set, we use the same number of 61 events for each C-, M-, and X-class from Jan. 1996 to Dec. 2004, while other previous models use all flares. For a testing data set, we use all flares from Jan. 2005 to Nov. 2013. The best three parameters related to the observed flare peak flux are weighted total flare flux of previous day (r = 0.51), X-ray flare peak flux (r = 0.48), and Mount Wilson magnetic classification (r = 0.47). A comparison between our neural network models and the previous models based on Heidke Skill Score (HSS) shows that our model for X-class flare is much better than the models and that for M-class flares is similar to them. Since all input parameters for our models are easily available, the models can be operated steadily and automatically in near-real time for space weather service.

• 한국멀티미디어학회논문지
• /
• 제23권8호
• /
• pp.1006-1018
• /
• 2020

Dataset is getting more import to develop a learning based algorithm. Quality of the algorithm definitely depends on dataset. So we introduce new dataset over 200 thousands images which are fully labeled multi modal sensor data. Proposed dataset was designed and constructed for researchers who want to develop detection, tracking, and action classification in outdoor environment for surveillance scenarios. The dataset includes various images and multi modal sensor data under different weather and lighting condition. Therefor, we hope it will be very helpful to develop more robust algorithm for systems equipped with difference kinds of sensors in outdoor application. Case studies with the proposed dataset are also discussed in this paper.

• 한국정보과학회논문지:소프트웨어및응용
• /
• 제31권11호
• /
• pp.1534-1542
• /
• 2004

본 논문에서는 교통 영상에서 실시간 교통 정보를 산출하는 새로운 기법을 소개한다. 각 차선의 검지 영역은 통계적 특징과 형상적 특징을 이용하여 도로, 차량, 그리고 그림자 영역으로 분류한다. 한 프레임에서의 오류는 연속된 프레임에서의 차량 영역의 상관적 특징을 이용하여 시공간 영상에서 교정된다. 국부 검지 영역만을 처리하므로 전용의 병렬 처리기 없이도 초당 30 프레임 이상의 실시간 처리가 가능하며 기상조건, 그림자, 교통량의 변화에도 강건한 성능을 보장할 수 있다.

• 환경영향평가
• /
• 제16권1호
• /
• pp.89-98
• /
• 2007

In order to conduct the environmental assessment of long range transboundary air pollutants over East Asia, the moving pathways of air pollutants are of great importance, which are depending upon the meteorological weather patterns. Therefore regional scale modeling study requires the identified geopotential height distribution patterns to deal with behaviors of long range transport air pollutants for the effective long term atmospheric environmental assessment. In this study the synoptic meteorological classification using cluster analysis technique over Northeast Asia, and its previous applications of the regional scale air pollutant modeling studies were reviewed and summarized in detail. Other synoptic meteorological characteristics over Korean peninsula are also discussed.

• 한국대기환경학회지
• /
• 제34권5호
• /
• pp.735-747
• /
• 2018

Rainfall depth is an important meteorological information. Generally, high spatial resolution rainfall data such as road-level rainfall data are more beneficial. However, it is expensive to set up sufficient Automatic Weather Systems to get the road-level rainfall data. In this paper, we propose to use deep learning to recognize rainfall depth from road surveillance videos. To achieve this goal, we collect a new video dataset and propose a procedure to calculate refined rainfall depth from the original meteorological data. We also propose to utilize the differential frame as well as the optical flow image for better recognition of rainfall depth. Under the Temporal Segment Networks framework, the experimental results show that the combination of the video frame and the differential frame is a superior solution for the rainfall depth recognition. The final model is able to achieve high performance in the single-location low sensitivity classification task and reasonable accuracy in the higher sensitivity classification task for both the single-location and the multi-location case.