• 한국멀티미디어학회논문지
• /
• 제19권8호
• /
• pp.1530-1537
• /
• 2016

Recently, solar power generation shows the significant growth in the renewable energy field. Using the short-term prediction, it is possible to control the electric power demand and the power generation plan of the auxiliary device. However, a short-term prediction can be used when you know the weather forecast. If it is not possible to use the weather forecast information because of disconnection of network at the island and the mountains or for security reasons, the accuracy of prediction is not good. Therefore, in this paper, we proposed a system capable of short-term prediction of solar power generation amount by using only the weather information that has been collected by oneself. We used temperature, humidity and insolation as weather information. We have applied a moving average to each information because they had a characteristic of time series. It was composed of min, max and average of each information, differences of mutual information and gradient of it. An artificial neural network, SVM and RBF Network model was used for the prediction algorithm and they were combined by Ensemble method. The results of this suggest that using a moving average during pre-processing and ensemble prediction models will maximize prediction accuracy.

• International Journal of Advanced Culture Technology
• /
• 제6권4호
• /
• pp.190-194
• /
• 2018

The runway visual range is one of the important factors that decide the possibility of taking offs and landings of the airplane at local airports. The runway visual range is affected by weather conditions like fog, wind, etc. The pilots and aviation related workers check a local weather forecast such as runway visual range for safe flight. However there are several local airfields at which no other forecasting functions are provided due to realistic problems like the deterioration, breakdown, expensive purchasing cost of the measurement equipment. To this end, this study proposes a prediction model of runway visual range for a local airport by applying convolutional neural network that has been most commonly used for image/video recognition, image classification, natural language processing and so on to the prediction of runway visual range. For constituting the prediction model, we use the previous time series data of wind speed, humidity, temperature and runway visibility. This paper shows the usefulness of the proposed prediction model of runway visual range by comparing with the measured data.

• 대기
• /
• 제33권5호
• /
• pp.457-475
• /
• 2023

Accurately predicting localized heavy rainfall is challenging without high-resolution mesoscale cloud information in the numerical model's initial field, as precipitation intensity and amount vary significantly across regions. In the Korean Peninsula, the radar observation network covers the entire country, providing high-resolution data on hydrometeors which is suitable for data assimilation (DA). During the pre-processing stage, radar reflectivity is classified into hydrometeors (e.g., rain, snow, graupel) using the background temperature field. The mixing ratio of each hydrometeor is converted and inputted into a numerical model. Moreover, assimilating saturated water vapor mixing ratio and decomposing radar radial velocity into a three-dimensional wind vector improves the atmospheric dynamic field. This study presents radar DA experiments using a numerical prediction model to enhance the wind, water vapor, and hydrometeor mixing ratio information. The impact of radar DA on precipitation prediction is analyzed separately for each radar component. Assimilating radial velocity improves the dynamic field, while assimilating hydrometeor mixing ratio reduces the spin-up period in cloud microphysical processes, simulating initial precipitation growth. Assimilating water vapor mixing ratio further captures a moist atmospheric environment, maintaining continuous growth of hydrometeors, resulting in concentrated heavy rainfall. Overall, the radar DA experiment showed a 32.78% improvement in precipitation forecast accuracy compared to experiments without DA across four cases. Further research in related fields is necessary to improve predictions of mesoscale heavy rainfall in South Korea, mitigating its impact on human life and property.

• 한국지구과학회지
• /
• 제39권5호
• /
• pp.403-418
• /
• 2018

This study conducted synoptic and mesoscale analyses to understand the cause of Japan Tsukuba tornado development, which occurred at 0340 UTC 6 May 2012. Prior to the tornado occurrence, there was a circular jet stream over Japan, and the surface was moist due to overnight precipitation. The circular jet stream brought cold and dry air to the upper-level atmosphere which let strong solar radiation heat the ground with clearing of sky cover. A tornadic supercell developed in the area of potentially unstable atmosphere. Sounding data at Tateno showed a capping inversion at 900 hPa at 0000 UTC 6 May. Strong insolation in early morning hours and removal of the inversion instigated vigorous updraft with rotation due to vertical shear in the upper-level atmosphere. This caused multiple tornadoes to occur from 0220 to 0340 UTC 6 May 2012. When comparing Tateno's climatological temperature and dew-point temperature profile on the day of event, the mid-level atmosphere was moister than typical sounding in the region. This study showed that tornado development in Tsukuba was caused by a combination of (a) topography and potential vorticity anomaly, which increased vorticity over the Kanto Plain; (b) vertical shear, which produced horizontal vortex line; and c) thermal instability, which triggered supercell and tilted the vortex line in the vertical.

• 한국항행학회논문지
• /
• 제22권6호
• /
• pp.491-499
• /
• 2018

항공기 이착륙 유무의 중요한 지표 중 하나인 활주로 가시거리는 기온, 습도 등과 같은 기상 조건에 영향을 받는다. 비행장의 활주로 이용 시 도착시점에서의 활주로 가시거리를 예측하는 것은 항공기 이용의 효율성에서 중요하다. 본 연구에서는 활주로 가시거리를 예측하기 위해 기존에 제안된 심층 신경망을 활용한 활주로 가시거리 예측 모델의 고도화를 통해 1시간 이후의 국지 비행장의 활주로 가시거리를 예측하였다. 이를 위해 예측 모델의 고도화는 입력 값으로 기상 정보(기온, 습도, 풍속, 활주로 가시거리)에 대한 시간 간격 변화와 예측 값의 선형변환을 통해 진행하였다. 제안된 방법은 과거 기상 관측 값을 바탕으로 예측 모델의 학습을 생성해 1시간 이후의 활주로 가시거리에 대한 예측을 수행하였고, 1시간 이후의 측정된 활주로 가시거리와 비교를 통해 타당성을 확인했다. 제안된 예측 모델은 예보를 제공해주지 않는 지역의 소규모 비행장에서 참고할 수 있는 활주로 가시거리 생성에 활용 할 수 있을 것이다.

• 한국농림기상학회지
• /
• 제21권3호
• /
• pp.146-157
• /
• 2019

우리나라 농산촌 환경의 가장 큰 특징 중 하나는 지형이 복잡하여 좁은 지역 내에서도 기상/기후 분포변이가 크다는 점이다. 이를 효과적으로 모의하기 위하여 '소기후 모형'이 개발되었고 현재까지 지속적으로 개선 연구가 진행되고 있다. 소기후 모형은 우리나라 전역에 대해 농장필지 단위까지 공간적으로 정밀한 농업기상/기후 정보를 표현할 수 있는 모형으로 기후요소별로 독자적으로 개발되었다. 소기후모형을 이용하여 2000년대에는 국지규모의 현재평년 및 미래 시나리오 기반 기후정보를 산출하였다. 평년 전자기후도는 과거 30년 기간의 월별 최저기온, 최고기온, 강수량, 일사량을 30 m 격자해상도로 상세화 한 분포도이며, 이 전자기후도를 기반으로 미래 기후변화 시나리오를 고해상도로 상세화하여 제작하였다. 이 들 전자기후도는 농업분야 기후변화 영향평가에 다양한 형태로 재가공 되어 이용되었다. 2010년대에는 농장맞춤형 기상 실황 및 예보자료를 국지규모로 생성하고 있다. 소기후 모형은 지속적인 개선 과정을 통해 일별 관측기상자료를 기반으로 실황정보를 상세화하는 기술로 발전하고 있으며, 기상청 동네예보 및 중기예보를 30 m 격자해상도로 상세 모의하여 농업분야 종사자에게 예측 정보를 실시간 제공할 수 있는 '농업기상 재해 조기경보 서비스' 기반의 핵심기술로 인정 받고 있다. 현재 상세 기상 실황 및 예보정보로는 일 최저 및 최고기온과 강수량, 일사량, 일조시간 등이 산출되고 있으며, 과거-현재-미래의 농장규모 기상정보를 토대로 각종 농작물의 생육정보와 기상재해 예측정보를 생산하고 있다.

• 응용통계연구
• /
• 제25권6호
• /
• pp.977-985
• /
• 2012

Data quality and climate forecasting performance deteriorates because of long climate data contaminated by non-climatic factors such as the station relocation or new instrument replacement. For a trusted climate forecast, it is necessary to implement data quality control and test inhomogeneous data. Before the inhomogeneity test, a reference series was created by $d$ index to measure the temperature series relationship between the candidate and surrounding stations. In this study, a inhomogeneity test to each season and climatological station was performed on the daily mean temperatures, daily minimum temperatures and daily maximum temperatures. After comparing two inhomogeneity tests, the traditional and the adjusted SNHT method, we found the adjusted SNHT method was slightly superior to the traditional one.

• Communications for Statistical Applications and Methods
• /
• 제28권1호
• /
• pp.39-57
• /
• 2021

Time series prediction is an area of great interest to many people. Algorithms for time series prediction are widely used in many fields such as stock price, temperature, energy and weather forecast; in addtion, classical models as well as recurrent neural networks (RNNs) have been actively developed. After introducing the attention mechanism to neural network models, many new models with improved performance have been developed; in addition, models using attention twice have also recently been proposed, resulting in further performance improvements. In this paper, we consider time series prediction by introducing attention twice to an RNN model. The proposed model is a method that introduces H-attention and T-attention for output value and time step information to select useful information. We conduct experiments on stock price, temperature and energy data and confirm that the proposed model outperforms existing models.

• 대한안전경영과학회지
• /
• 제19권4호
• /
• pp.35-42
• /
• 2017

A number of plating companies have been exposed to the risk of fire due to unexpected temperature increasing of water or other reasons in a plating bath. Since the companies are not able to forecast the unexpected temperature increasing of plating bath and most of raw materials in the bath have low ignition temperature, it is easy to be exposed to the risk of fire. Thus, in previous study, we tried to monitor and notice the dangerous change of temperature of water immediately to prevent the risk of fire from plating process. However, unfortunately previous studies were not able to shut out the fundamental cause of fire since bath temperature sensor can detect air temperature when the level sensor was malfunctioned. In this paper we developed the Teflon heater which contains a built in temperature sensor and improved plating equipment system. Teflon heater is improved using Pt $100{\Omega}$ sensor which can detect until $600^{\circ}C$. When the bath temperature sensor detects over $60^{\circ}C$ or the Teflon heater sensor detects over $240^{\circ}C$ they temporarily shut down the heater to control temperature. Also relay completely shuts down main power when detects instant temperature is detected over 5% of $240^{\circ}C$ by the heater sensor to prevent teflon melting down and fire spreads. Developed plating equipment system can monitor a real time temperature in the teflon tube and bath water. Therefore we think the proposed plating equipment can eliminate the possibility of fire in plating processes fundamentally.

• 응용통계연구
• /
• 제32권2호
• /
• pp.319-330
• /
• 2019

과거의 전력소모량을 분석하여 미래의 전력소모량을 예측하는 것은 에너지 계획과 정책 결정에 있어 많은 이점을 가져다준다. 기계학습은 최근 전력소모량을 예측하는 분석 방법으로 많이 사용하고 있다. 그중 앙상블 학습은 모형의 과적합 현상을 방지하고 분산을 줄여 예측의 정확성을 높이는 방법으로 알려져 있다. 하지만 일별 데이터에 앙상블 학습을 적용했을 때 분석 방법의 특성으로 인해 피크를 잘 나타내지 못하고 중심값으로 예측하는 단점을 보였다. 본 연구에서는 앙상블 학습 전에 온도 변수와의 상관성을 고려하여 선형모형으로 적합함으로써 앙상블 학습의 단점을 보완한다. 그리고 9개의 모형을 비교한 결과 온도 변수를 선형모형으로 적합하고 랜덤포레스트를 사용한 모형이 결과가 가장 좋음을 보여준다.