• Proceedings of the Korea Water Resources Association Conference
• /
• 2016.05a
• /
• pp.197-197
• /
• 2016

Forecasting future drought events in a region plays a major role in water management and risk assessment of drought occurrences. The creeping characteristics of drought make it possible to mitigate drought's effects with accurate forecasting models. Drought forecasts are inevitably plagued by uncertainties, making it necessary to derive forecasts in a probabilistic framework. In this study, a new probabilistic scheme is proposed to forecast droughts, in which a discrete-time finite state-space hidden Markov model (HMM) is used aggregated with the Representative Concentration Pathway 8.5 (RCP) precipitation projection (HMM-RCP). The 3-month standardized precipitation index (SPI) is employed to assess the drought severity over the selected five stations in South Kore. A reversible jump Markov chain Monte Carlo algorithm is used for inference on the model parameters which includes several hidden states and the state specific parameters. We perform an RCP precipitation projection transformed SPI (RCP-SPI) weight-corrected post-processing for the HMM-based drought forecasting to derive a probabilistic forecast that considers uncertainties. Results showed that the HMM-RCP forecast mean values, as measured by forecasting skill scores, are much more accurate than those from conventional models and a climatology reference model at various lead times over the study sites. In addition, the probabilistic forecast verification technique, which includes the ranked probability skill score and the relative operating characteristic, is performed on the proposed model to check the performance. It is found that the HMM-RCP provides a probabilistic forecast with satisfactory evaluation for different drought severity categories, even with a long lead time. The overall results indicate that the proposed HMM-RCP shows a powerful skill for probabilistic drought forecasting.

• KIPS Transactions on Software and Data Engineering
• /
• v.8 no.2
• /
• pp.67-78
• /
• 2019

Accurate electric load forecasting is very important in the efficient operation of the smart grid. Recently, due to the development of IT technology, many works for constructing accurate forecasting models have been developed based on big data processing using artificial intelligence techniques. These forecasting models usually utilize external factors such as temperature, humidity and historical electric load as independent variables. However, due to diverse internal and external factors, historical electrical load contains many missing data, which makes it very difficult to construct an accurate forecasting model. To solve this problem, in this paper, we propose a random forest-based missing data recovery scheme and construct an electric load forecasting model based on multilayer perceptron using the estimated values of missing data and external factors. We demonstrate the performance of our proposed scheme via various experiments.

• KIPS Transactions on Software and Data Engineering
• /
• v.11 no.2
• /
• pp.81-86
• /
• 2022

Given that time series are used in various fields, such as finance, IoT, and manufacturing, data analytical methods for accurate time-series forecasting can serve to increase operational efficiency. Among time-series analysis methods, multi-horizon forecasting provides a better understanding of data because it can extract meaningful statistics and other characteristics of the entire time-series. Furthermore, time-series data with exogenous information can be accurately predicted by using multi-horizon forecasting methods. However, traditional deep learning-based models for time-series do not account for the heterogeneity of inputs. We proposed an improved time-series predicting method, called the temporal fusion transformer method, which combines multi-horizon forecasting with interpretable insights into temporal dynamics. Various real-world data such as stock prices, fine dust concentrates and electricity consumption were considered in experiments. Experimental results showed that our temporal fusion transformer method has better time-series forecasting performance than existing models.

• The Korean Journal of Applied Statistics
• /
• v.32 no.1
• /
• pp.161-171
• /
• 2019

Varied methods have been researched continuously because the past as the daily maximum electricity demand expectation has been a crucial task in the nation's electrical supply and demand. Forecasting the daily peak electricity demand accurately can prepare the daily operating program about the generating unit, and contribute the reduction of the consumption of the unnecessary energy source through efficient operating facilities. This method also has the advantage that can prepare anticipatively in the reserve margin reduced problem due to the power consumption superabundant by heating and air conditioning that can estimate the daily peak load. This paper researched a model that can forecast the next day's daily peak load when considering the influence of temperature and weekday, weekend, and holidays in the Seasonal ARIMA, TBATS, Seasonal Reg-ARIMA, and NNETAR model. The results of the forecasting performance test on the model of this paper for a Seasonal Reg-ARIMA model and NNETAR model that can consider the day of the week, and temperature showed better forecasting performance than a model that cannot consider these factors. The forecasting performance of the NNETAR model that utilized the artificial neural network was most outstanding.

• Communications for Statistical Applications and Methods
• /
• v.30 no.3
• /
• pp.273-289
• /
• 2023

In this paper, we develop a new time series model for predicting IPO (initial public offering) data with non-negative integer value. The proposed model is based on integer-valued autoregressive (INAR) model with a Poisson thinning operator. Just as the heterogeneous autoregressive (HAR) model with daily, weekly and monthly averages in a form of cascade, the integer-valued heterogeneous autoregressive (INHAR) model is considered to reflect efficiently the long memory. The parameters of the INHAR model are estimated using the conditional least squares estimate and Yule-Walker estimate. Through simulations, bias and standard error are calculated to compare the performance of the estimates. Effects of model fitting to the Korea's IPO are evaluated using performance measures such as mean square error (MAE), root mean square error (RMSE), mean absolute percentage error (MAPE) etc. The results show that INHAR model provides better performance than traditional INAR model. The empirical analysis of the Korea's IPO indicates that our proposed model is efficient in forecasting monthly IPO volumes.

• Research in Plant Disease
• /
• v.8 no.2
• /
• pp.84-91
• /
• 2002

Disease forecasting in Korea was first studied in the Department of Fundamental Research, in the Central Agricultural Technology Institute in Suwon in 1947, where the dispersal of air-borne conidia of blast and brown spot pathogens in rice was examined. Disease forecasting system in Korea is operated based on information obtained from 200 main forecasting plots scattered around country (rice 150, economic crops 50) and 1,403 supplementary observational plots (rice 1,050, others 353) maintained by Korean government. Total number of target crops and diseases in both forecasting plots amount to 30 crops and 104 diseases. Disease development in the forecasting plots is examined by two extension agents specialized in disease forecasting, working in the national Agricul-tural Technology Service Center(ATSC) founded in each city and prefecture. The data obtained by the extension agents are transferred to a central organization, Rural Development Administration (RDA) through an internet-web system for analysis in a nation-wide forecasting program, and forwarded far the Central Forecasting Council consisted of 12 members from administration, university, research institution, meteorology station, and mass media to discuss present situation of disease development and subsequent progress. The council issues a forecasting information message, as a result of analysis, that is announced in public via mass media to 245 agencies including ATSC, who informs to local administration, the related agencies and farmers for implementation of disease control activity. However, in future successful performance of plant disease forecasting system is thought to be securing of excellent extension agents specialized in disease forecasting, elevation of their forecasting ability through continuous trainings, and furnishing of prominent forecasting equipments. Researches in plant disease forecasting in Korea have been concentrated on rice blast, where much information is available, but are substan-tially limited in other diseases. Most of the forecasting researches failed to achieve the continuity of researches on specialized topic, ignoring steady improvement towards practical use. Since disease forecasting loses its value without practicality, more efforts are needed to improve the practicality of the forecasting method in both spatial and temporal aspects. Since significance of disease forecasting is directly related to economic profit, further fore-casting researches should be planned and propelled in relation to fungicide spray scheduling or decision-making of control activities.

• Proceedings of the KIEE Conference
• /
• 2008.11a
• /
• pp.83-85
• /
• 2008

The authors develop and compare the performance of short-term forecasting models on electricity market prices in Korea. The models are based on time-series methods. The outcome shows that the EGARCH model has the best results in the out-of-sample forecasts.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2001.05a
• /
• pp.191-194
• /
• 2001

The ozone forecasting systems have many problems because the mechanism of the ozone concentration is highly complex, nonlinear, and nonstationary. Also, the results of prediction are not a good performance so far, especially in the high-level ozone concentration. This paper describes the modeling method of the ozone prediction system using neuro-fuzzy approaches and fuzzy clustering. The dynamic polynomial neural network (DPNN) based upon a typical algorithm of GMDH (group method of data handling) is a useful method for data analysis, identification of nonlinear complex system, and prediction of a dynamical system.

• Journal of Korean Society of Coastal and Ocean Engineers
• /
• v.32 no.5
• /
• pp.340-350
• /
• 2020

A rapid refresh wave forecasting system has been developed using the sea wind on the Korea Local Analysis and Prediction System. We carried out a numerical experiment for wind-wave interaction as an important parameter in determining the forecasting performance. The simulation results based on the seasons of with typhoon and without typhoon has been compared with the observation of the ocean data buoy to verify the forecasting performance. In case of without typhoon, there was an underestimate of overall forecasting tendency, and it confirmed that an increase in the wind-wave interaction parameter leads to a decrease in the underestimate tendency and root mean square error (RMSE). As a result of typhoon season by applying the experiment condition with minimum RMSE on without typhoon, the forecasting error has increased in comparison with the result without typhoon season. It means that the wave model has considered the influence of the wind forcing on a relatively weak period on without typhoon, therefore, it might be that the wave model has not sufficiently reflected the nonlinear effect and the wave energy dissipation due to the strong wind forcing.

• The Journal of Bigdata
• /
• v.3 no.2
• /
• pp.59-70
• /
• 2018

In order to provide stable district heat supplying service to the certain limited residential area, it is the most important to forecast the short-term future demand more accurately and produce and supply heat in efficient way. However, it is very difficult to develop a universal heat demand forecasting model that can be applied to general situations because the factors affecting the heat consumption are very diverse and the consumption patterns are changed according to individual consumers and regional characteristics. In particular, considering all of the various variables that can affect heat demand does not help improve performance in terms of accuracy and versatility. Therefore, this study aims to develop a demand forecasting model using deep learning based on only limited information that can be acquired in real time. A demand forecasting model was developed by learning the artificial neural network of the Tensorflow using past data consisting only of the outdoor temperature of the area and date as input variables. The performance of the proposed model was evaluated by comparing the accuracy of demand predicted with the previous regression model. The proposed heat demand forecasting model in this research showed that it is possible to enhance the accuracy using only limited variables which can be secured in real time. For the demand forecasting in a certain region, the proposed model can be customized by adding some features which can reflect the regional characteristics.