• 대기
• /
• 제22권3호
• /
• pp.345-356
• /
• 2012

The UK Met Office Unified Model at the KMA has been operationally utilized as the next generation numerical prediction system since 2010 after it was first introduced in May, 2008. Researches need to be carried out regarding various physical processes inside the model in order to improve the predictability of the newly introduced Unified Model. We first performed a preliminary experiment for the domain ($170{\times}170$, 10 km, 38 layers) smaller than that of the operating system using the version 7.4 of the UM local model to optimize its physical processes. The result showed that about 7~8% of the improvement ratio was found at each stage by integrating four factors (u, v, th, q), and the final improvement ratio was 25%. Verification was carried out for one month of August, 2008 by applying the optimized combination to the domain identical to the operating system, and the result showed that the precipitation verification score (ETS, equitable threat score) was improved by 9%, approximately.

• 한국태양에너지학회 논문집
• /
• 제39권3호
• /
• pp.59-66
• /
• 2019

New and renewable energy forecasts are key technology to reduce the annual operating cost of new and renewable facilities, and accuracy of forecasts is paramount. In this study, we intend to build a model for the prediction of short-term solar power generation for 1 hour to 3 hours. To this end, this study applied two time series technique, ARIMA model without considering seasonality and SARIMA model with considering seasonality, comparing which technique has better predictive accuracy. Comparing predicted errors by MAE measures of solar power generation for 1 hour to 3 hours at four locations, the solar power forecast model using ARIMA was better in terms of predictive accuracy than the solar power forecast model using SARIMA. On the other hand, a comparison of predicted error by RMSE measures resulted in a solar power forecast model using SARIMA being better in terms of predictive accuracy than a solar power forecast model using ARIMA.

• Communications for Statistical Applications and Methods
• /
• 제17권3호
• /
• pp.441-450
• /
• 2010

In this paper we consider the problem of forecasting binomial time series, modelled by the binomial autoregressive model. This paper considers proposed by McKenzie (1985) and is extended to a higher order by $Wei{\ss}$(2009). Since the binomial autoregressive model is a Markov chain, we can apply the earlier work of Bu and McCabe (2008) for integer valued autoregressive(INAR) model to the binomial autoregressive model. We will discuss how to compute the h-step-ahead forecast of the conditional probabilities of $X_{T+h}$ when T periods are used in fitting. Then we obtain the maximum likelihood estimator of binomial autoregressive model and use it to derive the maximum likelihood estimator of the h-step-ahead forecast of the conditional probabilities of $X_{T+h}$. The methodology is illustrated by applying it to a data set previously analyzed by $Wei{\ss}$(2009).

• Structural Monitoring and Maintenance
• /
• 제10권2호
• /
• pp.175-190
• /
• 2023

This article aims to quantitatively predict the snowmelt in extreme cold regions, considering a combination of grayscale and neural models. The traditional non-equidistant GM(1,1) prediction model is optimized by adjusting the time-distance weight matrix, optimizing the background value of the differential equation and optimizing the initial value of the model, and using the BP neural network for the first. The adjusted ice forecast model has an accuracy of 0.984 and posterior variance and the average forecast error value is 1.46%. Compared with the GM(1,1) and BP network models, the accuracy of the prediction results has been significantly improved, and the quantitative prediction of the ice sheet is more accurate. The monitoring and maintenance of the structure by quantitative prediction model by gray models was clearly demonstrated in the model.

• 대기
• /
• 제17권4호
• /
• pp.327-337
• /
• 2007

In this study, we examined the new ensemble training approach to reduce the systematic error and improve prediction skill of wind by using the Short-range Ensemble prediction system (SENSE), which is the mesoscale multi-model ensemble prediction system. The SENSE has 16 ensemble members based on the MM5, WRF ARW, and WRF NMM. We evaluated the skill of surface wind prediction compared with AWS (Automatic Weather Station) observation during the summer season (June - August, 2006). At first stage, the correction of initial state for each member was performed with respect to the observed values, and the corrected members get the training stage to find out an adaptive weight function, which is formulated by Root Mean Square Vector Error (RMSVE). It was found that the optimal training period was 1-day through the experiments of sensitivity to the training interval. We obtained the weighted ensemble average which reveals smaller errors of the spatial and temporal pattern of wind speed than those of the simple ensemble average.

• Communications for Statistical Applications and Methods
• /
• 제25권2호
• /
• pp.199-215
• /
• 2018

Interest in $PM_{10}$ concentrations have increased greatly in Korea due to recent increases in air pollution levels. Therefore, we consider a forecasting model for next day $PM_{10}$ concentration based on the principal elements of air pollution, weather information and Beijing $PM_{2.5}$. If we can forecast the next day $PM_{10}$ concentration level accurately, we believe that this forecasting can be useful for policy makers and public. This paper is intended to help forecast a daily mean $PM_{10}$, a daily max $PM_{10}$ and four stages of $PM_{10}$ provided by the Ministry of Environment using various data mining techniques. We use seven models to forecast the daily $PM_{10}$, which include five regression models (linear regression, Randomforest, gradient boosting, support vector machine, neural network), and two time series models (ARIMA, ARFIMA). As a result, the linear regression model performs the best in the $PM_{10}$ concentration forecast and the linear regression and Randomforest model performs the best in the $PM_{10}$ class forecast. The results also indicate that the $PM_{10}$ in Seoul is influenced by Beijing $PM_{2.5}$ and air pollution from power stations in the west coast.

• International Journal of Computer Science & Network Security
• /
• 제23권8호
• /
• pp.190-198
• /
• 2023

To enhance customer satisfaction for higher profits, an e-commerce sector can establish a continuous relationship and acquire new customers. Utilize machine-learning models to analyse their customer's behavioural evidence to produce their competitive advantage to the e-commerce platform by helping to improve overall satisfaction. These models will forecast customers who will churn and churn causes. Forecasts are used to build unique business strategies and services offers. This work is intended to develop a machine-learning model that can accurately forecast retainable customers of the entire e-commerce customer data. Developing predictive models classifying different imbalanced data effectively is a major challenge in collected data and machine learning algorithms. Build a machine learning model for solving class imbalance and forecast customers. The satisfaction accuracy is used for this research as evaluation metrics. This paper aims to enable to evaluate the use of different machine learning models utilized to forecast satisfaction. For this research paper are selected three analytical methods come from various classifications of learning. Classifier Selection, the efficiency of various classifiers like Random Forest, Logistic Regression, SVM, and Gradient Boosting Algorithm. Models have been used for a dataset of 8000 records of e-commerce websites and apps. Results indicate the best accuracy in determining satisfaction class with both gradient-boosting algorithm classifications. The results showed maximum accuracy compared to other algorithms, including Gradient Boosting Algorithm, Support Vector Machine Algorithm, Random Forest Algorithm, and logistic regression Algorithm. The best model developed for this paper to forecast satisfaction customers and accuracy achieve 88 %.

• 응용통계연구
• /
• 제29권3호
• /
• pp.525-537
• /
• 2016

본 연구에서는 시계열 자료의 비정상성과 비선형성과 같은 복잡성을 효과적으로 포용할 수 있는 경험적모드분해법(empirical mode decomposition; EMD)을 토대로 시계열 자료의 분석 및 예측을 위한 혼합(hybrid) 모형을 연구한다. EMD에 의하여 생성되는 내재모드함수(intrinsic mode function; IMF)는 해석 및 예측의 편리성을 개선하기 위하여 누적에너지의 개념을 사용하여 그룹화하였으며, 그룹화된 IMF 및 residue의 성분들은 그 성질에 따라서 ARIMA 모형 및 지수평활법과 결합된 혼합 모형으로 예측된다. 제안된 방법은 일별 코스피 지수의 예측을 위해서 적용하였다. 다양한 형태의 혼합 모형을 사용하여 코스피 지수를 예측하였으며 전통적인 예측 방법과 비교하였다. 분석 결과, 그룹화된 성분들은 코스피 지수의 움직임을 단기적, 중기적, 장기적으로 해석하는데 편리함을 주었으며, 그룹화된 IMF 및 residue를 각각 ARIMA 모형과 지수평활법으로 조합한 혼합 모형이 우수한 예측력을 보여주었다.

• 대기
• /
• 제34권2호
• /
• pp.217-231
• /
• 2024

The Korea Integrated Model (KIM)-based real-time volcanic ash dispersion prediction system, which employs the Hybrid Single Particle Lagrangian Integrated Trajectory (HYSPLIT) model, has been developed to quantitatively predict volcanic ash dispersion in East Asia and the Northwest Pacific airspace. This system, known as KIM-HYSPLIT, automatically generates forecasts for the vertical and horizontal spread of volcanic ash up to 72 hours. These forecasts are initiated upon the receipt of a Volcanic Ash Advisory (VAA) from the Tokyo Volcanic Ash Advisory Center by the server at the Korea Meteorological Administration (KMA). This system equips KMA forecasters with diverse volcanic ash prediction information, complemented by the Unified Model (UM)-based HYSPLIT (UM-HYSPLIT) system. Extensive experiments have been conducted using KIM-HYSPLIT across 128 different volcanic scenarios, along with qualitative comparisons with UM-HYSPLIT. The results indicate that the ash direction predictions from KIM-HYSPLIT are consistent with those from UM-HYSPLIT. However, there are slight differences in the horizontal extent and movement speed of the volcanic ash. Additionally, quantitative verifications of the KIM-HYSPLIT forecasts have been performed, including threat score evaluations, based on recent eruption cases. On average, the KIMHYSPLIT forecasts for 6 and 12 hours show better quantitative alignment with the VAA forecasts compared to UM-HYSPLIT. Nevertheless, both models tend to predict a broader horizontal spread of the ash cloud than indicated in the VAA forecasts, particularly noticeable in the 6-hour forecast period.

• 대기
• /
• 제30권1호
• /
• pp.17-30
• /
• 2020

KMA performed the special observation program to provide information about severe weather and to monitor typhoon PRAPIROON using the ship which called the Gisang 1 from 29 June 2018 to 4 July 2018 (UTC). For this period, upper-air was observed 21 times with 6 hour intervals using rawinsonde in the Gisang 1. We investigated the impact of upper-air observation data from the Gisang 1 on the performance of the operational convective scale model (we called LDAPS). We conducted two experiments that used all observation data including upper-air observation data from the Gisang 1 (OPER) and without it (EXPR). For a typhoon PRAPIROON case, track forecast error of OPER was lower than EXPR until forecast 24 hours. The intensity forecast error of OPER for minimum sea level pressure was lower than EXPR until forecast 12 hours. The intensity forecast error of OPER for maximum wind speed was mostly lower than EXPR until forecast 30 hours. OPER showed good performance for typhoon forecast compared with EXPR at the early lead time. Two precipitation cases occurred in the south of the Korean peninsula due to the impact of Changma on 1 July and typhoon on 3 July. The location of main precipitation band predicted from OPER was closer to observations. As assimilating upper-air data observed in the Gisang 1 to model, it showed positive results in typhoon and precipitation cases.