• The Bulletin of The Korean Astronomical Society
• /
• v.41 no.1
• /
• pp.80.1-80.1
• /
• 2016

There are probabilistic forecast models for solar flare occurrence, which can be evaluated by various skill scores (e.g. accuracy, critical success index, heidek skill score, and true skill score). Since these skill scores assume that two types of forecast errors (i.e. false alarm and miss) are equal or constant, which does not take into account different situations of users, they may be unrealistic. In this study, we make an evaluation of a probabilistic flare forecast model [Lee et al., 2012] which use sunspot groups and its area changes as a proxy of flux emergence. We calculate daily solar flare probabilities from 2011 to 2014 using this model. The skill scores are computed through contingency tables as a function of forecast probability, which corresponds to the maximum skill score depending on flare class and type of a skill score. We use a value score with cost/loss ratio, relative importance between the two types of forecast errors. The forecast probability (y) is linearly changed with the cost/loss ratio (x) in the form of y=ax+b: a=0.88; b=0 (C), a=1.2; b=-0.05(M), a=1.29; b=-0.02(X). We find that the forecast model has an effective range of cost/loss ratio for each class flare: 0.536-0.853(C), 0.147-0.334(M), and 0.023-0.072(X). We expect that this study would provide a guideline to determine the probability threshold and the cost/loss ratio for space weather forecast.

• Journal of Korea Water Resources Association
• /
• v.52 no.7
• /
• pp.451-461
• /
• 2019

The dam reservoir inflow prediction is utilized to ensure for water supply and prevent future droughts. In this study, we predicted the dam reservoir inflow and analyzed how seasonal weather forecasting affected the accuracy of the inflow for even multi-purpose dams. The hindcast and forecast of GloSea5 from KMA were used as input for rainfall-runoff models. TANK, ABCD, K-DRUM and PRMS models which have individual characteristics were applied to simulate inflow prediction. The dam reservoir inflow prediction was assessed for the periods of 1996~2009 and 2015~2016 for the hindcast and forecast respectively. The results of assessment showed that the inflow prediction was underestimated by comparing with the observed inflow. If rainfall-runoff models were calibrated appropriately, the characteristics of the models were not vital for accuracy of the inflow prediction. However the accuracy of seasonal weather forecasting, especially precipitation data is highly connected to the accuracy of the dam inflow prediction. It is recommended to consider underestimation of the inflow prediction when it is used for operations. Futhermore, for accuracy enhancement of the predicted dam inflow, it is more effective to focus on improving a seasonal weather forecasting rather than a rainfall-runoff model.

• Proceedings of the Korean Society of Crop Science Conference
• /
• 2017.06a
• /
• pp.303-303
• /
• 2017

Japanese agriculture has faced to several threats: aging and decrease of farmer population, global competition, and the risk of climate change as well as harsh and variable weather. On the other hands, the number of large scale farms is increasing, because farm lands have been being aggregated to fewer numbers of farms. Cost cutting, development of efficient ways to manage complicatedly scattered farm lands, maintaining yield and quality under variable weather conditions, are required to adapt to changing environments. Information and communications technology (ICT) would contribute to solve such problems and to create innovative technologies. Thus we have been developing an early warning and decision support system to reduce weather and climate risks for rice, wheat and soybean production in Japan. The concept and prototype of the system will be shown. The system consists of a weather data system (Agro-Meteorological Grid Square Data System, AMGSDS), decision support contents where information is automatically created by crop models and delivers information to users via internet. AMGSDS combines JMA's Automated Meteorological Data Acquisition System (AMeDAS) data, numerical weather forecast data and normal values, for all of Japan with about 1km Grid Square throughout years. Our climate-smart system provides information on the prediction of crop phenology, created with weather forecast data and crop phenology models, as an important function. The system also makes recommendations for crop management, such as nitrogen-topdressing, suitable harvest time, water control, pesticide spray. We are also developing methods to perform risk analysis on weather-related damage to crop production. For example, we have developed an algorism to determine the best transplanting date in rice under a given environment, using the results of multi-year simulation, in order to answer the question "when is the best transplanting date to minimize yield loss, to avoid low temperature damage and to avoid high temperature damage?".

• Journal of Advanced Navigation Technology
• /
• v.21 no.6
• /
• pp.643-650
• /
• 2017

Photovoltaic generation which has unlimited energy sources are very intermittent because they depend on the weather. Therefore, it is necessary to get accurate generation prediction with reducing the uncertainty of photovoltaic generation and improvement of the economics. The Meteorological Agency predicts weather factors for three days, but doesn't predict the sunshine and solar radiation that are most correlated with the prediction of photovoltaic generation. In this study, we predict sunshine and solar radiation using weather, precipitation, wind direction, wind speed, humidity, and cloudiness which is forecasted for three days at Meteorological Agency. The photovoltaic generation forecasting model is proposed by using predicted solar radiation and sunshine. As a result, the proposed model showed better results in the error rate indexes such as MAE, RMSE, and MAPE than the model that predicts photovoltaic generation without radiation and sunshine. In addition, DNN showed a lower error rate index than using SVM, which is a type of machine learning.

• Journal of the Korea Convergence Society
• /
• v.8 no.10
• /
• pp.1-8
• /
• 2017

Accurate forecasting enables to effectively prepare for future phenomenon. Especially, meteorological phenomenon is closely related with human life, and it can prevent from damage such as human life and property through forecasting of weather and disaster that can occur. To respond quickly and effectively to oil spill accidents, it is important to accurately predict the movement of oil spills and the weather in the surrounding waters. In this paper, we selected four representative machine learning techniques: support vector machine, Gaussian process, multilayer perceptron, and radial basis function network that have shown good performance and predictability in the previous studies related to oil spill detection and prediction in meteorology such as wind, rainfall and ozone. we suggest the applicability of oil spill prediction model based on machine learning.

• Korean Journal of Agricultural and Forest Meteorology
• /
• v.3 no.1
• /
• pp.37-43
• /
• 2001

Crop status monitoring and yield prediction at higher spatial resolution is a valuable tool in various decision making processes including agricultural policy making by the national and local governments. A prototype crop forecasting system was developed to project the size of rice crop across geographic areas nationwide, based on daily weather pattern. The system consists of crop models and the input data for 1,455 cultivation zone units (the smallest administrative unit of local government in South Korea called "Myun") making up the coterminous South Korea. CERES-rice, a rice crop growth simulation model, was tuned to have genetic characteristics pertinent to domestic cultivars. Daily maximum/minimum temperature, solar radiation, and precipitation surface on 1km by 1km grid spacing were prepared by a spatial interpolation of 63 point observations from the Korea Meteorological Administration network. Spatial mean weather data were derived for each Myun and transformed to the model input format. Soil characteristics and management information at each Myun were available from the Rural Development Administration. The system was applied to the forecasting of national rice production for the recent 3 years (1997 to 1999). The model was run with the past weather data as of September 15 each year, which is about a month earlier than the actual harvest date. Simulated yields of 1,455 Myuns were grouped into 162 counties by acreage-weighted summation to enable the validation, since the official production statistics from the Ministry of Agriculture and Forestry is on the county basis. Forecast yields were less sensitive to the changes in annual climate than the reported yields and there was a relatively weak correlation between the forecast and the reported yields. However, the projected size of rice crop at each county, which was obtained by multiplication of the mean yield with the acreage, was close to the reported production with the $r^2$ values higher than 0.97 in all three years.

• Korean Journal of Organic Agriculture
• /
• v.25 no.3
• /
• pp.555-567
• /
• 2017

This study suggests the yield forecast model for chilli pepper using artificial neural network. For this, we select the most suitable network models for chilli pepper's yield and compare the predictive power with adaptive expectation model and panel model. The results show that the predictive power of artificial neural network with 5 weather input variables (temperature, precipitation, temperature range, humidity, sunshine amount) is higher than the alternative models. Implications for forecasting of yields are suggested at the end of this study.

• Journal of Korea Multimedia Society
• /
• v.22 no.11
• /
• pp.1300-1312
• /
• 2019

BSTRACT In this paper, PM10 forecast model using DNN(Deep Neural Network) is developed for Seoul region. The previous Julian forecast model has been developed using weather and air quality data of Seoul region only. This model gives excellent results for accuracy and false alarm rates, but poor result for POD(Probability of Detection). To solve this problem, an WA(Wide Area) forecasting model that uses Chinese data is developed. The data is highly correlated with the emergence of high concentrations of PM10 in Korea. As a result, the WA model shows better accuracy, and POD improving of 3%(D+0), 21%(D+1), and 36%(D+2) for each forecast period compared with the Julian model.

• Proceedings of the KIEE Conference
• /
• 2000.07a
• /
• pp.292-294
• /
• 2000

This paper is presented the method peak load forecast based on multiple regression Model. Forecasting model was composed with the temperature-humidity and the discomfort index. Also the week periodicity was excluded from weekday change coefficient of two types. Forecasting result was good with about 3[%]. And, utility of presented forecast model using statistical tests has been proved. Therefore, This results establish appropriateness and fitness of forecast models using peak power demand forecasting.

• Journal of Korea Multimedia Society
• /
• v.24 no.8
• /
• pp.1122-1137
• /
• 2021

PM_2.5 concentration in Seoul could be predicted by deep neural network model. In this paper, the contribution of input factors to the model's prediction results is analyzed using the LRP(Layer-wise Relevance Propagation) technique. LRP analysis is performed by dividing the input data by time and PM concentration, respectively. As a result of the analysis by time, the contribution of the measurement factors is high in the forecast for the day, and those of the forecast factors are high in the forecast for the tomorrow and the day after tomorrow. In the case of the PM concentration analysis, the contribution of the weather factors is high in the low-concentration pattern, and that of the air quality factors is high in the high-concentration pattern. In addition, the date and the temperature factors contribute significantly regardless of time and concentration.