기계학습을 활용한 기상예측자료 기반 태양광 발전량 예측 향상기법

정진화(Jin-Hwa Jeong),채영태(Young-Tae Chae) 한국생활환경학회 2018 한국생활환경학회지 Vol.25 No.1

This study investigated a selection of machine learning model to forecast electric power output from photovoltaic arrays based on forecasted weather data and historic solar radiation data. It tested two approaches to improve forecasting accuracy of power output with three typical machine learning algorithms such as Random Forest(RF), Artificial Neural Network(ANN), and Support Vector Machine(SVM). A forecasting power output was conducted with conventional weather forecasting data from national weather service which does not include solar radiation. The other approach has two steps, forecasting solar radiation with weather forecasting data and historic solar radiation data then it forecasts the electric power output of photovoltaic arrays. It has been studied the importance variables incorporated with the power output forecasting. The results show that the forecasting accuracy of the power output improves by using forecasted solar radiation data and Random Forest outperforms on this power output forecasting problem among other machine learning algorithms.

한국어 학습자를 위한 일기예보 말뭉치 구축 및 어휘 분석

김미영 배재대학교 주시경교양교육연구소 2020 대학교양교육연구 Vol.5 No.2

It is seasonal and weather-related information that appears in Korean language education. It is essential to know the season and the weather to lead daily life in Korea, where there are four distinct seasons. Also, the seasons and weather affect Korean culture such as traditional houses and food, so we need to know the weather and season of Korea to understand Korean culture properly. Although vocabulary about seasons and weather appears in Korean textbooks, Korean learners find it difficult to understand weather forecasts because they do not know the vocabulary they do not know or the meaning of response descriptions that appear with them. In response, this paper established a weather forecast corpus of the Korea Meteorological Administration (KMA) to analyze the vocabulary frequency by item, the preceding of the predicate, the trailing co-occurrence relationship, the seasonal vocabulary frequency, and the monthly vocabulary frequency to secure educational materials on what season and weather vocabulary should be taught to help learners understand. In this paper, we confirmed that nouns are the most frequently presented in weather forecasts and the types of nouns vary. In the high frequency vocabulary of nouns, difficult words were evenly distributed from easy vocabulary. It was suggested that time nouns, place nouns, and general nouns should be presented together as well as vocabulary representing the seasons. In the case of verbs, adjectives, and adverbs, the high frequency vocabulary is not difficult and there are frequently used leading and trailing element patterns, so presenting them together will help learners understand. According to an analysis of verbs and nouns frequently used on a monthly basis, there was a month in which words representing conflicting weather appeared simultaneously. And it seems necessary to revise the syntactic classification that categorizes May and September as spring and autumn.

건강예보 서비스 제공에 대한 지불의사금액 추정

오진아 ( Jin A Oh ),박종길 ( Jong Kil Park ),오민경 ( Min Kyung Oh ) 한국환경과학회 2011 한국환경과학회지 Vol.20 No.3

Weather forecasting is one of the key elements to improve health through the prevention and mitigation of health problems. Health forecasting is a potential resource creating enormous added value as it is effectively used for people. The purpose of this study is to estimate ``Willingness to Pay`` for health forecasting. This survey was carried out to derive willingness to pay from 400 people who lived in Busan and Kyungnam Province and over 30 years of age during the period of July 1-31, 2009. The results showed that a 47.50% of people had intention to willingness to pay for health forecasting, and the pay was 7,184.21 won per year. Willing to pay goes higher depending on ``tax burden as to benefit of weather forecasting``, ``importance of the weather forecasting in the aspect of health``, ``satisfaction to the weather forecasting``, and ``frequency of health weather index check``. This study followed the suggestion of the Korea Meteorological Administration generally and the values derived through surveys could be reliable. It can be concluded that a number of citizens who are willing to pay for health forecasting are high enough to meet the costs needed to provide health forecasting.

신뢰성 해석기법을 이용한 배추 가격폭등 예측 모형의 개발

서교,이정재,김태곤 한국농공학회 2008 한국농공학회논문집 Vol.50 No.3

Generally the price of agricultural products has much different characteristics from that of manufacturing products. If products have the limitation of long-term storage and the short period of cultivation, the price of products can be more unstable. Moreover, the price forecasting is very difficult because it doesn't follow any cycle or trend. However price can be regarded as risk instead of uncertainty if we can calculate the probability of price. Reliability analysis techniques are used for forecasting the price change of chinese cabbage. This study aims to show the usability of reliability analysis for price forecasting. A price-forecasting model was developed based on weather data of 10 days before 70 days and the average price and standard deviation of wholesale market prices from 1996 to 2001 and applied to forecast the boom price of upland Chinese cabbage in 2002 and 2003. Applied results showed the possibility of boom price forecasting using reliability analysis techniques. Generally the price of agricultural products has much different characteristics from that of manufacturing products. If products have the limitation of long-term storage and the short period of cultivation, the price of products can be more unstable. Moreover, the price forecasting is very difficult because it doesn't follow any cycle or trend. However price can be regarded as risk instead of uncertainty if we can calculate the probability of price. Reliability analysis techniques are used for forecasting the price change of chinese cabbage. This study aims to show the usability of reliability analysis for price forecasting. A price-forecasting model was developed based on weather data of 10 days before 70 days and the average price and standard deviation of wholesale market prices from 1996 to 2001 and applied to forecast the boom price of upland Chinese cabbage in 2002 and 2003. Applied results showed the possibility of boom price forecasting using reliability analysis techniques.

Application of Numerical Weather Prediction Data to Estimate Infection Risk of Bacterial Grain Rot of Rice in Korea

Hyo-suk Kim,Ki Seok Do,Joo Hyeon Park,Wee Soo Kang,Yong Hwan Lee,Eun Woo Park 한국식물병리학회 2020 Plant Pathology Journal Vol.36 No.1

This study was conducted to evaluate usefulness of numerical weather prediction data generated by the Unified Model (UM) for plant disease forecast. Using the UM06- and UM18-predicted weather data, which were released at 0600 and 1800 Universal Time Coordinated (UTC), respectively, by the Korea Meteorological Administration (KMA), disease forecast on bacterial grain rot (BGR) of rice was examined as compared with the model output based on the automated weather stations (AWS)-observed weather data. We analyzed performance of BGRcast based on the UM-predicted and the AWS-observed daily minimum temperature and average relative humidity in 2014 and 2015 from 29 locations representing major rice growing areas in Korea using regression analysis and two-way contingency table analysis. Temporal changes in weather conduciveness at two locations in 2014 were also analyzed with regard to daily weather conduciveness (Ci) and the 20-day and 7-day moving averages of Ci for the inoculum build-up phase (Cinc) prior to the panicle emergence of rice plants and the infection phase (Cinf) during the heading stage of rice plants, respectively. Based on Cinc and Cinf , we were able to obtain the same disease warnings at all locations regardless of the sources of weather data. In conclusion, the numerical weather prediction data from KMA could be reliable to apply as input data for plant disease forecast models. Weather prediction data would facilitate applications of weather-driven disease models for better disease management. Crop growers would have better options for disease control including both protective and curative measures when weather prediction data are used for disease warning.

장기예보 서비스의 현황 분석 및 활용 방안 연구 : 에너지 산업을 중심으로

신정엽,이건학,최영은,정준석,김현경 한국지도학회 2011 한국지도학회지 Vol.11 No.3

현대 사회에서 기상청의 날씨 정보는 점점 중요해지고 있으며, 최근에 장기예보에 대한 관심이 증대되고 있다. 장기예보는 국가 차원에서 기온, 강수량을 중심으로 하여 서비스되고 있으며, 이러한 공공성 정보를 토대로 민간 부문에서도 다양한 장기예보 서비스를 제공 중이다. 이러한 장기예보 서비스는 산업 부문의 효율성 제고에도 유용한데, 이러한 측면에서 본 연구는 에너지 산업에 필요한 장기예보 활용 방안을 수립하고자 하였다. 에너지 산업에 맞는 효율적인 장기예보 활용 방안은 실제적인 수요 조사를 바탕으로 유용성, 활용성, 사용자 편의성, 업무 효율성을 토대로 수립되었으며, 단계별 활용 전략이 수립되었다. 즉 1단계에서는 장기예보 서비스의 홍보와 인지도 향상, 2단계에서는 장기예보 서비스 강화를 위한 정비, 3단계에서는 맞춤형 장기예보 서비스 개발 및 연구 수행, 4단계에서는 서비스 정보 고효율화 및 활용 극대화를 목표로 활용방안이 수립되었다. 이러한 활용 방안은 에너지 산업의 장기예보 활용을 보다 활성화시킬 수 있을 뿐 아니라, 다른 산업 부문의 활용성을 확대시키는데 유용한 프레임 워크를 제공할 수 있으리라 기대된다. In the modern societies, the weather information of the weather services is becoming considered as important, and in recent years, more attention was paid to the long-term weather forecasts. The long-term weather forecasts is being serviced with the temperatures, precipitation in the perspective of nation, and based on the public information, the private sector is providing various kinds of long-term forecasts. This long-term forecasts is useful for the enhancement of the efficiency in the industry sector, and with this regard, the research is to establish the utilization plan of the long-term forecasts for the energy industry. The efficient utilization plan of the long-term forecasts for the energy industry was established based on actual demand research with the consideration of the utility, the applicability, the degree of the user-friendly, mission efficiency, and the phased utilization strategy was established. The purpose of the first phase is the public relations and enhancement of the awareness of the long-term forecast service, and that of the second phase is the organization for the service reinforcement of the long-term forecast service. The purpose of the third phase is the development and research of the tailored service of the long-term forecast, and that of the fourth is the high efficiency and utility maximization of the service. It is expected that this service utilization plan will revitalize the service of the long-term forecast in the energy industry and provide a useful framework for expanding the utility in other industry sectors.

A stochastic flood analysis using weather forecasts and a simple catchment dynamics

Kim, Daeha,Jang, Sangmin 한국수자원학회 2017 한국수자원학회논문집 Vol.50 No.11

기후변화에 대한 우려와 함께 증가하고 있는 극한호우의 피해를 줄이기 위해서는 호우사상 발생 이전에 홍수위험을 미리 파악하여 피해를 대비 할 시간을 늘리는 것이 중요하다. 본 연구에서는 기상청 동네예보를 기반으로 하는 간단한 확률적 홍수위험 산정방법을 제시하였다. 예보강수를 조건부로 하는 6시간 강수량의 확률밀도함수를 이용해 다수의 임의 강수량을 생성한 후 추계학적 모형으로 1시간 단위로 분해하여 간단한 강우-유 출모형에 입력하는 방법을 사용하였다. 보청천 유역의 2017년 주요 강우사상에 제안된 방법을 적용한 결과, 7월 4일 최대홍수량이 나타났던 사상에 대해서는 예보강수를 이용한 모의는 홍수위험을 과소평가하였음을 확인하였고 반면 8월 15일 사상에 대한 동네예보는 강수량을 다소 과대추 정하였지만 홍수위험을 충분히 알릴 수 있는 정보로 평가되었다. 본 연구는 확정론적 모형과 확률론적 강수량을 결합하여 기상예보의 불확실성을 고려한 자료기반 홍수위험도 산정방법을 제시한다. With growing concerns about ever-increasing anthropogenic greenhouse gas emissions, it is crucial to enhance preparedness for unprecedented extreme weathers that can bring catastrophic consequences. In this study, we proposed a stochastic framework that considers uncertainty in weather forecasts for flood analyses. First, we calibrated a simple rainfall-runoff model against observed hourly hydrographs. Then, using probability density functions of rainfall depths conditioned by 6-hourly weather forecasts, we generated many stochastic rainfall depths for upcoming 48 hours. We disaggregated the stochastic 6-hour rainfalls into an hourly scale, and input them into the runoff model to quantify a probabilistic range of runoff during upcoming 48 hours. Under this framework, we assessed two rainfall events occurred in Bocheong River Basin, South Korea in 2017. It is indicated actual flood events could be greater than expectations from weather forecasts in some cases; however, the probabilistic runoff range could be intuitive information for managing flood risks before events. This study suggests combining deterministic and stochastic methods for forecast-based flood analyses to consider uncertainty in weather forecasts.

Public Satisfaction Analysis of Weather Forecast Service by Using Twitter

Ki-Kwang Lee(이기광) 한국산업경영시스템학회 2018 한국산업경영시스템학회지 Vol.41 No.2

This study is intended to investigate that it is possible to analyze the public awareness and satisfaction of the weather forecast service provided by the Korea Meteorological Administration (KMA) through social media data as a way to overcome limitations of the questionnaire-based survey in the previous research. Sentiment analysis and association rule mining were used for Twitter data containing opinions about the weather forecast service. As a result of sentiment analysis, the frequency of negative opinions was very high, about 75%, relative to positive opinions because of the nature of public services. The detailed analysis shows that a large portion of users are dissatisfied with precipitation forecast and that it is needed to analyze the two kinds of error types of the precipitation forecast, namely, ‘False alarm’ and ‘Miss’ in more detail. Therefore, association rule mining was performed on negative tweets for each of these error types. As a result, it was found that a considerable number of complaints occurred when preventive actions were useless because the forecast predicting rain had a ‘False alarm’ error. In addition, this study found that people’s dissatisfaction increased when they experienced inconveniences due to either unpredictable high winds and heavy rains in summer or severe cold in winter, which were missed by weather forecast. This study suggests that the analysis of social media data can provide detailed information about forecast users’ opinion in almost real time, which is impossible through survey or interview.

Twitter를 활용한 기상예보서비스에 대한 사용자들의 만족도 분석

이기광 한국산업경영시스템학회 2018 한국산업경영시스템학회지 Vol.41 No.2

This study is intended to investigate that it is possible to analyze the public awareness and satisfaction of the weather forecast service provided by the Korea Meteorological Administration (KMA) through social media data as a way to overcome limitations of the questionnaire-based survey in the previous research. Sentiment analysis and association rule mining were used for Twitter data containing opinions about the weather forecast service. As a result of sentiment analysis, the frequency of negative opinions was very high, about 75%, relative to positive opinions because of the nature of public services. The detailed analysis shows that a large portion of users are dissatisfied with precipitation forecast and that it is needed to analyze the two kinds of error types of the precipitation forecast, namely, ‘False alarm’ and ‘Miss’ in more detail. Therefore, association rule mining was performed on negative tweets for each of these error types. As a result, it was found that a considerable number of complaints occurred when preventive actions were useless because the forecast predicting rain had a ‘False alarm’ error. In addition, this study found that people’s dissatisfaction increased when they experienced inconveniences due to either unpredictable high winds and heavy rains in summer or severe cold in winter, which were missed by weather forecast. This study suggests that the analysis of social media data can provide detailed information about forecast users’ opinion in almost real time, which is impossible through survey or interview.

기상정보를 활용한 의류제품 판매예측 시스템 연구: S/S 시즌 제품을 중심으로

오재호 ( Jai Ho Oh ),오희선 ( Hee Sun Oh ),최경민 ( Kyung Min Choi ) 한국의류산업학회 2017 한국의류산업학회지 Vol.19 No.3

This study aims to develop clothing sales forecast system using weather information. As the annual temperature variation affects changes in daily sales of seasonal clothes, sales period can be predicted growth, peak and decline period by changes of temperature. From this perspective, we analyzed the correlation between temperature and sales. Moving average method was applied in order to indicate long-term trend of temperature and sales changes. 7-day moving average temperature at the start/end points of the growth, peak, and decline period of S/S clothing sales was calculated as a reference temperature for sales forecast. According to the 2013 data analysis results, when 7-day moving average temperature value becomes 4^oC or higher, the growth period of S/S clothing sales starts. The peak period of S/S clothing sales starts at 17^oC, up to the highest temperature. When temperature drops below 21^oC after the peak temperature, the decline period of S/S clothing sales is over. The reference temperature was applied to 2014 temperature data to forecast sales period. Through comparing the forecasted sales periods with the actual sales data, validity of the sales forecast system has been verified. Finally this study proposes `clothing sales forecast system using weather information` as the method of clothing sales forecast.