KLAPS 재분석 자료를 이용한 진화최적화 RBFNNs 기반 호우특보 판별 모델 설계

김현명(Hyun-Myung Kim),오성권(Sung-Kwun Oh),이용희(Yong-Hee Lee) 한국지능시스템학회 2013 한국지능시스템학회논문지 Vol.23 No.5

본 논문에서는 KLAPS(Korea Local Analysis and Prediction System)의 재분석 자료를 이용하여 지능형 뉴로-퍼지 알고리즘 RBFNNs(Polynomial-based Radial Basis Function Neural Networks) 기반 호우특보 판별 모델을 개발한다. 기존의 호우예측 시스템들의 예측능력은 일반적으로 기상데이터의 가공 기법의 영향을 받는다. 본 연구에서는 이를 보완하기 위하여 기상데이터의 전처리를 통한 호우예측 방법을 소개한다. 기상 데이터 전처리 기법은 KLAPS 데이터를 기반으로 지점별 변환, 누적강수량 생성, 시계열 데이터 가공, 호우특보 추출 방식에 의하여 설계된다. 최종적으로, 향후 t(t=1,2,3) 시간 후 6시간 동안 누적강수량에 대해 예측하고 호우특보를 결정하기 위한 정보를 제공한다. 또한 다항식의 형태, 규칙의 개수, 퍼지화 계수와 같은 제안된 모델의 중요 파라미터는 최적화 기법인 차분 진화(Differential Evolution; DE)를 이용하여 최적화한다. In this paper, we develop the Heavy Rain Advisory Decision Model based on intelligent neuro-fuzzy algorithm RBFNNs by using KLAPS(Korea Local Analysis and Prediction System) Reanalysis data. the prediction ability of existing heavy rainfall forecasting systems is usually affected by the processing techniques of meteorological data. In this study, we introduce the heavy rain forecast method using the pre-processing techniques of meteorological data are in order to improve these drawbacks of conventional system. The pre-processing techniques of meteorological data are designed by using point conversion, cumulative precipitation generation, time series data processing and heavy rain warning extraction methods based on KLAPS data. Finally, the proposed system forecasts cumulative rainfall for six hours after future t(t=1,2,3) hours and offers information to determine heavy rain advisory. The essential parameters of the proposed model such as polynomial order, the number of rules, and fuzzification coefficient are optimized by means of Differential Evolution.

LAPS와 관측자료를 이용한 고해상도 경기도 농업기상정보 분석시스템

천지민 ( Ji Min Chun ),김규랑 ( Kyu Rang Kim ),이선용 ( Seon Yong Lee ),강위수 ( Wee Soo Kang ),박종선 ( Jong Sun Park ),이채연 ( Chae Yon Yi ),최영진 ( Young Jean Choi ),박은우 ( Eun Woo Park ),홍순성 ( Sun Sung Hong ) 한국농림기상학회 2012 한국농림기상학회지 Vol.14 No.2

Demand for high resolution weather data grows in the agriculture and forestry fields. Local Analysis and Prediction System (LAPS) can be used to analyze the local weather at high spatial and temporal resolution, utilizing the data from various sources including numerical weather prediction models, wind or temperature profilers, Automated Weather Station (AWS) networks, radars, and satellites. LAPS has been set to analyze weather elements such as air temperature, relative humidity, wind speed, and wind direction every hour at the spatial resolution of 100 m × 100 m for Gyeonggi-do on near real-time basis. The AWS data were revised by adding the agricultural field AWS data (33 stations) in addition to the KMA data. The analysis periods were from 1 to 31 August 2009 and from 15 to 21 February 2010. The comparison of the LAPS output showed the smaller errors when using the agricultural AWS observation data together with the KMA data as its input data than using only either the agricultural or KMA AWS data. The accuracy of the current system needs improvement by further optimization of analyzing options of the system. However, the system is highly applicable to various fields in agriculture and forestry because it can provide site specific data with reasonable time intervals.

초단기 파랑예측시스템 구축 및 예측성능 검증

노민,라나리,오상명,강기룡,장필훈 한국해안,해양공학회 2020 한국해안해양공학회 논문집 Vol.32 No.5

한반도 대기모델의 해상풍을 입력자료로 사용하는 초단기 파랑예측시스템을 구축하고, 예측성능을 결정하는 중요한 요소인 입력바람장-파랑 상호작용을 고려하여, 수치모의실험을 수행하였다. 예측성능을 검증하기 위해 비태풍시기와 태풍시기에 대한 파랑모델의 예측결과를 기상청 계류부이 관측자료와 비교하였다. 비태풍시기에는 전반적으로 모델의 과소모의 경향이 나타났으며, 입력바람장과 파랑의 상호작용 물리계수를 증가시키면 과소모의하는 예측경향과 평균제곱근오차(RMSE)는 감소하는 것을 확인할 수 있었다. RMSE가 최소가 되는 실험조건을 적용하여태풍시기를 분석한 결과, 비태풍시기와 비교하여 예측오차가 증가하였다. 이는 파랑모델이 상대적으로 약한 비태풍시기의 바람장 영향을 고려했기 때문으로 보이며, 강한 바람장 형성으로 인한 파랑의 비선형효과와 파랑에너지 소산효과가 충분히 반영되지 않았던 것으로 판단된다. A rapid refresh wave forecasting system has been developed using the sea wind on the Korea Local Analysis and Prediction System. We carried out a numerical experiment for wind-wave interaction as an important parameter in determining the forecasting performance. The simulation results based on the seasons of with typhoon and without typhoon has been compared with the observation of the ocean data buoy to verify the forecasting performance. In case of without typhoon, there was an underestimate of overall forecasting tendency, and it confirmed that an increase in the wind-wave interaction parameter leads to a decrease in the underestimate tendency and root mean square error (RMSE). As a result of typhoon season by applying the experiment condition with minimum RMSE on without typhoon, the forecasting error has increased in comparison with the result without typhoon season. It means that the wave model has considered the influence of the wind forcing on a relatively weak period on without typhoon, therefore, it might be that the wave model has not sufficiently reflected the nonlinear effect and the wave energy dissipation due to the strong wind forcing.

Post Flight Analysis Using Numerical Weather Prediction Data, KLAPS

정석영,이재은,김민규,박성현 한국항공우주학회 2022 International Journal of Aeronautical and Space Sc Vol.23 No.2

Numerical weather prediction data, in this study, were proposed to replace the meteorological measurement data acquired by widely used radiosonde, for the purpose of constructing atmospheric environment model applying to post flight analysis, especially evaluating aerodynamic performance in flight. KLAPS (Korea Local Analysis and Prediction System), the numerical weather model used in this study, is provided by the Korea Meteorological Administration every hour through the Internet and contains the meteorological information for a local region around the Korean peninsula, which is expected to give some advantage in the acquisition of regional and temporal variation of atmosphere state over the radiosonde measurement which has some drawbacks of acquiring data on only one point at one height while drifting via wind and taking some hours to climb up to 30 km high. The accuracy of KLAPS was verified by regenerating vertical distributions of atmospheric properties at the same locations and times as radiosonde measured and comparing them. Post flight analysis was carried out with an atmosphere environment model based on KLAPS and proved that the numerical weather model can provide an accurate atmospheric environment model enough to substitute the radiosonde measurement data.

SVR을 사용한 데이터 학습 기반의 풍속 예측 모델 생성

서기성 한국지능시스템학회 2017 한국지능시스템학회논문지 Vol.27 No.6

Developing numerical models for weather prediction is a very difficult and expensive task. The approach to compensate numerical prediction models is mainly occupied, and the generation of daa tbased prediction models has hardly been tried. We have attemtepd to generate a data based prediction model of wind speed using SVR technique for long term data. Using the UM and KLAPS data from 2007 to 2013 year for Seoul, Busan, and Jeju Island, the prediction model was generated and the performance was evaluated. As a result, the results approximated to the compenation method were obtained. On the other hand, fundamental errors are included by using the generated values of the numerical prediction model instead of actual measurement data for predictor variables constituting the model. In order to solve this problem, we constructed a model using data with errors less than a certain level, which resulted in improved outcomess 기상 예측에 대한 수치 예보 모델을 개발하는 것은 매우 어렵고 비용이 많이 드는 작업이므로, 통계적 데이터 기반의 모델생성이 대안이 될 수 있다. 그러나 지금까지는 주로 수치 예보 모델을 보정하는 접근법이 주를 차지하고 있고, 데이터 기반의예보 모델 생성은 거의 시도되지 않고 있다. 본 논문에서는 장기간의 데이터에 대해서 SVR 기법을 사용하여 풍속에 대한데이터 기반 예보 모델을 생성한다. 서울, 부산, 제주도 지역에 대해서 2007~2013년도의 UM과 KLAPS 데이터를 사용하여모델을 생성하고 보정방식과 성능을 비교하여 근접한 성능 결과를 얻었다. 한편 모델을 구성하는 기본 인자들의 데이터가실측치가 아닌 수치예보모델에 의한 생성값을 사용함으로써 원천적인 오차를 포함하고 있다. 이 문제를 해결하기 위해서오차가 일정 수준 이하의 수치예보모델 데이터를 사용하여 모델을 구성하고 이를 통해 향상된 결과를 얻었다

풍력기상자원지도 산출방법에 따른 풍력자원 비교

서범근,김연희,김지희,김백조 한국신·재생에너지학회 2017 신재생에너지 Vol.13 No.4

Two types of wind resource maps for Korea were developed. The first wind resource map was a TMY (TypicalMeteorological Year) wind resource map based on the WRF (Weather Research and Forecasting) model using the NCEP FNL for theTMY period from 1998 to 2009. The second wind resource map was a KLAPS (Korea Local Analysis and Prediction System) windresource map based on the WRF model using the high resolution KLAPS reanalysis data of a continuous period from 2010 to 2013. Acomparative verification was carried out using the observation data of the ASOS sites. The KLAPS wind resource map was improvedby 17.9% (0.24 m s-1, mean bias) and 10.6% (0.24 m s-1, mean RMSE) compared to the TMY wind resource map. The wind speedverification at an 80 m height of the KLAPS wind resource map was conducted for the Gochang site (onshore) and HeMOSU-1 site(offshore). As a result, the bias was 0.5 m s-1and -0.2 m s-1, and the RMSE was 2.1 m s-1and 2.0 m s-1, respectively. The wind speed ofthe KLAPS wind resource map was strong in winter (onshore) and spring (offshore), and weak in summer. Moreover the wind speedduring the daytime was stronger than that at night. The wind resource map depicted the average wind speed, maximum wind speed,prevailing wind direction, frequency of 3 ~ 25 m s-1wind speed, and Weibull distribution in major wind farms for the development ofwind energy.

KLAPS 재분석 자료를 이용한 진화최적화 RBFNN 기반 호우특보 판별 모델 설계

김현명(Hyun-Myung Kim),오성권(Sung-Kwun Oh),이용희(Yong-Hee Lee) 한국지능시스템학회 2013 한국지능시스템학회 학술발표 논문집 Vol.23 No.1

연구논문 : 객관분석기법에 의한 바람장 모의의 초기입력장 변화 효과 분석

김유근 ( Yoo Keun Kim ),정주희 ( Ju Hee Jeong ),배주현 ( Joo Hyun Bae ),권지혜 ( Ji Hye Kwun ),서장원 ( Jang Won Seo ) 한국환경과학회 2006 한국환경과학회지 Vol.15 No.8

UM LDAPS를 활용한 풍력자원지도 고도화

이영미(Youngmi Lee),박정근(Jeongkeun Park),배주현(Joohyun Bae),김진영(Jin-Young Kim),김현구(Hyun-Goo Kim) 한국신재생에너지학회 2016 한국신재생에너지학회 학술대회논문집 Vol.2016 No.5

Comparison of Wind Resource Characteristics in Korea According to Different Mapping Method

Yeon-Hee Kim(김연희),Jinah Yun(윤진아),Beom-Keun Seo(서범근),Baek-Jo Kim(김백조) 한국신재생에너지학회 2018 한국신재생에너지학회 학술대회논문집 Vol.2018 No.4