• The Plant Pathology Journal
• /
• v.24 no.1
• /
• pp.46-51
• /
• 2008

With the goal of achieving better integrated pest management for hot pepper, a disease-forecasting system was compared to a conventional disease-control method. Experimental field plots were established at Asan, Chungnam, in 2005 to 2006, and hourly temperature and leaf wetness were measured and used as model inputs. One treatment group received applications of a protective fungicide, dithianon, every 7 days, whereas another received a curative fungicide, dimethomorph, when the model-determined infection risk (IR) exceeded a value of 3. In the unsprayed plot, fruits showed 18.9% (2005) and 14.0% (2006) anthracnose infection. Fruits sprayed with dithianon at 7-day intervals had 4.7% (2005) and 15.4% (2006) infection. The receiving model-advised sprays of dimethomorph had 9.4% (2005) and 10.9% (2006) anthracnose infection. Differences in the anthracnose levels between the conventional and model-advised treatments were not statistically significant. The efficacy of 10 (2005) and 8 (2006) applications of calendar-based sprays was same as that of three (2005 and 2006) sprays based on the disease-forecast system. In addition, we found much higher the IRs with the leaf wetness sensor from the field plots comparing without leaf wetness sensor from the weather station at Asan within 10km away. Since the wetness-periods were critical to forecast anthracnose in the model, the measurement of wetness-period in commercial fields must be refined to improve the anthracnose-forecast model.

• Atmosphere
• /
• v.30 no.2
• /
• pp.141-154
• /
• 2020

Seasonal forecast is growing in demand, as it provides valuable information for decision making and potential to reduce impact on weather events. This study examines how operational climate prediction systems can be reliable, producing the probability forecast in seasonal scale. A reliability diagram was used, which is a tool for the reliability by comparing probabilities with the corresponding observed frequency. It is proposed for a method grading scales of 1-5 based on the reliability diagram to quantify the reliability. Probabilities are derived from ensemble members using hindcast data. The analysis is focused on skill for 2 m temperature and precipitation from climate prediction systems in KMA, UKMO, and ECMWF, NCEP and JMA. Five categorizations are found depending on variables, seasons and regions. The probability forecast for 2 m temperature can be relied on while that for precipitation is reliable only in few regions. The probabilistic skill in KMA and UKMO is comparable with ECMWF, and the reliabilities tend to increase as the ensemble size and hindcast period increasing.

• The Plant Pathology Journal
• /
• v.31 no.4
• /
• pp.350-362
• /
• 2015

A disease forecast model for bacterial grain rot (BGR) of rice, which is caused by Burkholderia glumae, was developed in this study. The model, which was named 'BGRcast', determined daily conduciveness of weather conditions to epidemic development of BGR and forecasted risk of BGR development. All data that were used to develop and validate the BGRcast model were collected from field observations on disease incidence at Naju, Korea during 1998-2004 and 2010. In this study, we have proposed the environmental conduciveness as a measure of conduciveness of weather conditions for population growth of B. glumae and panicle infection in the field. The BGRcast calculated daily environmental conduciveness, $C_i$, based on daily minimum temperature and daily average relative humidity. With regard to the developmental stages of rice plants, the epidemic development of BGR was divided into three phases, i.e., lag, inoculum build-up and infection phases. Daily average of $C_i$ was calculated for the inoculum build-up phase ($C_{inf}$) and the infection phase ($C_{inc}$). The $C_{inc}$ and $C_{inf}$ were considered environmental conduciveness for the periods of inoculum build-up in association with rice plants and panicle infection during the heading stage, respectively. The BGRcast model was able to forecast actual occurrence of BGR at the probability of 71.4% and its false alarm ratio was 47.6%. With the thresholds of $C_{inc}=0.3$ and $C_{inf}=0.5$, the model was able to provide advisories that could be used to make decisions on whether to spray bactericide at the preand post-heading stage.

• The Journal of Asian Finance, Economics and Business
• /
• v.9 no.10
• /
• pp.159-168
• /
• 2022

The time series of foreign trade turnover is complex and variable and contains linear and nonlinear information. This paper proposes preprocessing the dataset by the EMD algorithm and combining the linear prediction advantage of the SARIMA model with the nonlinear prediction advantage of the EMD-LSTM model to construct the SARIMA-EMD-LSTM hybrid model by the weight assignment method. The forecast performance of the single models is compared with that of the hybrid models by using MAPE and RMSE metrics. Furthermore, it is confirmed that the weight assignment approach can benefit from the hybrid models. The results show that the SARIMA model can capture the fluctuation pattern of the time series, but it cannot effectively predict the sudden drop in foreign trade turnover caused by special reasons and has the lowest accuracy in long-term forecasting. The EMD-LSTM model successfully resolves the hysteresis phenomenon and has the highest forecast accuracy of all models, with a MAPE of 7.4304%. Therefore, it can be effectively used to forecast the Sino-Russia foreign trade turnover time series post-epidemic. Hybrid models cannot take advantage of SARIMA linear and LSTM nonlinear forecasting, so weight assignment is not the best method to construct hybrid models.

• The Bulletin of The Korean Astronomical Society
• /
• v.46 no.1
• /
• pp.42.1-42.1
• /
• 2021

In this study, we present a visual explanation of a deep learning solar flare forecast model and its relationship to physical parameters of solar active regions (ARs). For this, we use full-disk magnetograms at 00:00 UT from the Solar and Heliospheric Observatory/Michelson Doppler Imager and the Solar Dynamics Observatory/Helioseismic and Magnetic Imager, physical parameters from the Space-weather HMI Active Region Patch (SHARP), and Geostationary Operational Environmental Satellite X-ray flare data. Our deep learning flare forecast model based on the Convolutional Neural Network (CNN) predicts "Yes" or "No" for the daily occurrence of C-, M-, and X-class flares. We interpret the model using two CNN attribution methods (guided backpropagation and Gradient-weighted Class Activation Mapping [Grad-CAM]) that provide quantitative information on explaining the model. We find that our deep learning flare forecasting model is intimately related to AR physical properties that have also been distinguished in previous studies as holding significant predictive ability. Major results of this study are as follows. First, we successfully apply our deep learning models to the forecast of daily solar flare occurrence with TSS = 0.65, without any preprocessing to extract features from data. Second, using the attribution methods, we find that the polarity inversion line is an important feature for the deep learning flare forecasting model. Third, the ARs with high Grad-CAM values produce more flares than those with low Grad-CAM values. Fourth, nine SHARP parameters such as total unsigned vertical current, total unsigned current helicity, total unsigned flux, and total photospheric magnetic free energy density are well correlated with Grad-CAM values.

• Korean Management Science Review
• /
• v.26 no.1
• /
• pp.77-91
• /
• 2009

It is the most important sucess factor for the electricity generation industry to minimize operations cost of surplus electricity generation through accurate demand forecasts. Temperature forecast is a significant input variable, because power demand is mainly linked to the air temperature. This study estimates the information value of the temperature forecast by analyzing the relationship between electricity load and daily air temperature in Korea. Firstly, several characteristics was analyzed by using a population-weighted temperature index, which was transformed from the daily data of the maximum, minimum and mean temperature for the year of 2005 to 2007. A neural network-based load forecaster was derived on the basis of the temperature index. The neural network then was used to evaluate the performance of load forecasts for various types of temperature forecasts (i.e., persistence forecast and perfect forecast) as well as the actual forecast provided by KMA(Korea Meteorological Administration). Finally, the result of the sensitivity analysis indicates that a $0.1^{\circ}C$ improvement in forecast accuracy is worth about $11 million per year.

• Atmosphere
• /
• v.17 no.2
• /
• pp.115-123
• /
• 2007

The present study uses the GOES IR brightness temperature to examine the temporal and spatial variability of cloud activity over the region $25^{\circ}N-45^{\circ}N$, $105^{\circ}E-135^{\circ}E$ and analyzes the coherence of eastern Asian summer season rainfall in Weather Research and Forecast (WRF) model. Time-longitude diagram of the time period from June to July 2005 shows a signal of eastward propagation in the WRF model and convective index derived from GOES IR data. The rain streaks in time-latitude diagram reveal coherence during the experiment period. Diurnal and synoptic scales are evident in the power spectrum of the time series of convective index and WRF rainfall. The diurnal cycle of early morning rainfall in the WRF model agrees with GOES IR data in the Korean Peninsula, but the afternoon convection observed by satellite observation in China is not consistent with the WRF rainfall which is represented at the dawn. Although there are errors in strength and timing of convection, the model predicts a coherent tendency of rainfall occurrence during summer season.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.57 no.11
• /
• pp.2061-2065
• /
• 2008

In the conventional operation of ice-storage system based on operator's experience and judgement, the failure in forecast of cooling load occurs frequently due to operator's misjudgement and unskilled operation. This study presents the method of constructing self-organizing fuzzy models which forecast tomorrow temperature, humidity and cooling load periodically for economic and efficient operation of ice-storage system. To check the effectiveness and feasibility of the suggested algorithm, the actual example for forecasting temperature, humidity and cooling load of ice- storage system in KEPCO training institute, Sokcho, is examined. The computer simulation results show that the accuracy of temperature, humidity, cooling load forecast of the suggested algorithm is higher than that of the conventional methods.

• Industrial Engineering and Management Systems
• /
• v.14 no.2
• /
• pp.196-209
• /
• 2015

Retail sales forecast is a special area of forecasting. Its unique characteristics call for unique data models and treatment, and unique forecasting processes. In this paper, we will address lessons learned and challenges encountered in retail sales forecast from a practical and technical perspective. In particular, starting with the data models of retail sales data, we proceed to address issues existing in estimating and processing each component in the data model. We will discuss how to estimate the multi-seasonal cycles in retail sales data, and the limitations of the existing methodologies. In addition, we will talk about the distinction between business events and forecast events, the methodologies used in event detection and event effect estimation, and the difficulties in compound event detection and effect estimation. For each of the issues and challenges, we will present our solution strategy. Some of the solution strategies can be generalized and could be helpful in solving similar forecast problems in different areas.

• Atmosphere
• /
• v.16 no.3
• /
• pp.247-257
• /
• 2006

The Yeong-dong heavy snowfall forecast supporting system has been developed during the last several years. In order to construct the conceptual model, we have examined the characteristics of heavy snowfalls in the Yeong-dong region classified into three precipitation patterns. This system is divided into two parts: forecast and observation. The main purpose of the forecast part is to produce value-added data and to display the geography based features reprocessing the numerical model results associated with a heavy snowfall. The forecast part consists of four submenus: synoptic fields, regional fields, precipitation and snowfall, and verification. Each offers guidance tips and data related with the prediction of heavy snowfalls, which helps weather forecasters understand better their meteorological conditions. The observation portion shows data of wind profiler and snow monitoring for application to nowcasting. The heavy snowfall forecast supporting system was applied and tested to the heavy snowfall event on 28 February 2006. In the beginning stage, this event showed the characteristics of warm precipitation pattern in the wind and surface pressure fields. However, we expected later on the weak warm precipitation pattern because the center of low pressure passing through the Straits of Korea was becoming weak. It was appeared that Gangwon Short Range Prediction System simulated a small amount of precipitation in the Yeong-dong region and this result generally agrees with the observations.