• Economic and Environmental Geology
• /
• v.56 no.1
• /
• pp.65-73
• /
• 2023

As one of the most vulnerable countries to floods, there should be an increased necessity for accurate and reliable flood forecasting in Indonesia. Therefore, a new prediction model using a machine learning algorithm is proposed to provide daily flood prediction in Indonesia. Data crawling was conducted to obtain daily rainfall, streamflow, land cover, and flood data from 2008 to 2021. The model was built using a Random Forest (RF) algorithm for classification to predict future floods by inputting three days of rainfall rate, forest ratio, and stream flow. The accuracy, specificity, precision, recall, and F1-score on the test dataset using the RF algorithm are approximately 94.93%, 68.24%, 94.34%, 99.97%, and 97.08%, respectively. Moreover, the AUC (Area Under the Curve) of the ROC (Receiver Operating Characteristics) curve results in 71%. The objective of this research is providing a model that predicts flood events accurately in Indonesian regions 3 months prior the day of flood. As a trial, we used the month of June 2022 and the model predicted the flood events accurately. The result of prediction is then published to the website as a warning system as a form of flood mitigation.

• Communications for Statistical Applications and Methods
• /
• v.31 no.5
• /
• pp.535-556
• /
• 2024

Measuring stock market volatility and its determinants is critical for stock market participants, as volatility spillover effects affect corporate performance. This study adopted a novel approach to analysing and implementing GARCH-MIDAS modelling methods. The classical GARCH as a benchmark and the univariate GARCH-MIDAS framework are the GARCH family models whose forecasting outcomes are examined. The outcome of GARCH-MIDAS analyses suggests that inflation, interest rate, exchange rate, and oil price are significant determinants of the volatility of the Johannesburg Stock Market All Share Index. While for Nigeria, the volatility reacts significantly to the exchange rate and oil price. Furthermore, inflation, exchange rate, interest rate, and oil price significantly influence Ghanaian equity volatility, especially for the long-term volatility component. The significant shock of the oil price and exchange rate to volatility is present in all three markets using the generalized autoregressive conditional heteroscedastic-mixed data sampling (GARCH-MIDAS) framework. The GARCH-MIDAS, with a powerful fusion of the GARCH model's volatility-capturing capabilities and the MIDAS approach's ability to handle mixed-frequency data, predicts the volatility for all variables better than the traditional GARCH framework. Incorporating these two techniques provides an innovative and comprehensive approach to modelling stock returns, making it an extremely useful tool for researchers, financial analysts, and investors.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.19 no.8
• /
• pp.312-321
• /
• 2018

The Korean DR market proposes suppression of peak demand under reliability crisis caused a natural disaster or unexpected power plant accidents as well as saving power plant construction costs and expanding amount of reserve as utility's perspective. End-user is notified a DR event signal DR execution before one hour, and executes DR based on requested amount of load reduction. This paper proposes a DR energy management algorithm that can be scheduled the optimal operations of chiller system and ESS in the next day considering the TOU tariff and DR scheme. In this DR algorithm is divided into two scheduling's; day-ahead operation scheduling with temperature forecasting error and operation rescheduling on DR operation. In day-ahead operation scheduling, the operations of DR resources are scheduled based on the finite number of ambient temperature scenarios, which have been generated based on the historical ambient temperature data. As well as, the uncertainties in DR event including requested amount of load reduction and specified DR duration are also considered as scenarios. Also, operation rescheduling on DR operation day is proposed to ensure thermal comfort and the benefit of a COB owner. The proposed method minimizes the expected energy cost by a mixed integer linear programming (MILP).

• Journal of Radiation Protection and Research
• /
• v.28 no.4
• /
• pp.311-319
• /
• 2003

We developed a grid-based Gaussian plume model to evaluate tracer release data measured at Young Gwang nuclear site in 1996. Downwind distance was divided into every 10m from 0.1km to 20km, and crosswind distance was divided into every 10m centering released point from -5km to 5km. We determined dispersion factors, ${\sigma}_y\;and\;{\sigma}_z$ using Pasquill-Gifford method computed by atmospheric stability. Forecasting ability of the grid-based Gaussian plume model was better at the 3km away from the source than 8km. We confirmed that dispersion band must be modified if receptor is far away from the source, otherwise P-G method is not appropriate to compute diffusion distance and diffusion strength in case of growing distance. So, we developed an empirical equation using linear programming. An objective function was designed to minimize sum of the absolute value between observed and computed values. As a result of application of the modified dispersion equation, prediction ability was improved rather than P-G method.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.62 no.11
• /
• pp.1495-1504
• /
• 2013

Renewable energy integration and increased system complexities make system operator maintain supply and demand balance harder than before. To keep the grid frequency in a stable range, an appropriate spinning reserve margin should be procured with consideration of ever-changing system situation, such as demand, wind power output and generator failure. This paper propose a novel concept of dynamic reserve, which arrange different spinning reserve margin depending on time. To investigate the effectiveness of the proposed dynamic reserve, we developed a new short-term reliability criterion that estimates the probability of a spinning reserve shortage events, thus indicating grid frequency stability. Uncertainties of demand forecast error, wind generation forecast error and generator failure have been modeled in probabilistic terms, and the proposed spinning reserve has been applied to generation scheduling. This approach has been tested on the modified IEEE 118-bus system with a wind farm. The results show that the required spinning reserve margin changes depending on the system situation of demand, wind generation and generator failure. Moreover the proposed approach could be utilized even in case of system configuration change, such as wind generation extension.

• Ocean and Polar Research
• /
• v.42 no.3
• /
• pp.211-223
• /
• 2020

With the increasing demand for improved marine environments and safety, greater ability to minimize damages to coastal areas from harmful organisms, ship accidents, oil spills, etc. is required. In this regard, an accurate assessment and understanding of current systems is a crucial step to improve forecasting ability. In this study, we examine spatial and temporal characteristics of current systems in the adjacent seas of Jeju Island using a high-resolution regional ocean circulation model. Our model successfully captures the features of tides and tidal currents observed around Jeju Island. The tide form number calculated from the model result ranges between 0.3 and 0.45 in the adjacent seas of Jeju Island, indicating that the dominant type of tides is a combination of diurnal and semidiurnal, but predominantly semidiurnal. The spatial pattern of tidal current ellipses show that the tidal currents oscillate in a northwest-southeast direction and the rotating direction is clockwise in the adjacent seas of Jeju Island and counterclockwise in the Jeju Strait. Compared to the mean kinetic energy, the contribution of tidal current energy prevails the most parts of the region, but largely decreases in the eastern seas of Jeju Island where the Tsushima Warm Current is dominant. In addition, a Lagrangian particle-tracking experiment conducted suggests that particle trajectories in tidal currents flowing along the coast may differ substantially from the mean current direction. Thus, improving our understanding of tidal currents is essential to forecast the transport of marine pollution and harmful organisms in the adjacent seas of Jeju Island.

• Atmosphere
• /
• v.28 no.1
• /
• pp.53-67
• /
• 2018

This study examined the lake effect of the Yellow Sea which was induced by the Siberian High pressure system moving over the open waters. The development mechanism of the convective cells over the ocean was studied in detail using the Weather Research and Forecasting model. Numerical experiments consist of the control experiment (CTL) and an experiment changing the yellow sea to dry land (EXP). The CTL simulation result showed distinct high area of relative vorticity, convergence and low-level atmospheric instability than that of the EXP. The result indicates that large surface vorticity and convergence induced vertical motion and low level instability over the ocean when the arctic Siberian air mass moved south over the Yellow Sea. The sensible heat flux at the sea surface gradually decreased while latent heat flux gradually increased. At the beginning stage of air mass modification, sensible heat was the main energy source for convective cell generation. However, in the later stage, latent heat became the main energy source for the development of convective cells. In conclusion, the mechanism of the west coast heavy snowfall caused by modification of the Siberian air mass over the Yellow Sea can be explained by air-sea interaction instability in the following order: (a) cyclonic vorticity caused by diabatic heating induce Ekman pumping and convergence at the surface, (b) sensible heat at the sea surface produce convection, and (c) this leads to latent heat release, and the development of convective cells. The overall process is a manifestation of air-sea interaction and enhancement of convection from positive feedback mechanism.

• Journal of the Korean Society for Marine Environment & Energy
• /
• v.1 no.2
• /
• pp.96-108
• /
• 1998

The management of water quality and fishery resources with a major environmental problem in eutrophic coastal sea is studied. The numerical experiments using the water-sediment quality model (WSQM) were carried out for the management of water quality at the Seto Inland Sea in Japan. The results of long-term water quality simulation showed responses of seawater quality to input loads to vary in different localities. A formula roughly forecasting water qualify to estimate the effect of loading abatement was proposed. The simulation for the improvement of seawater quality showed the abatements of nutrient loads such as total phosphorus (TP) and total nitrogen (TN) as well as organic loads such as chemical oxygen demand (COD) to be peformed in the eastern Seto Inland Sea from Bisan Seto to Osaka Bay. On the other hand, it is indicated that the increase of loading leads to the increase of primary production. while not straightly to the increase of fish production for the catch of fisheries.

• Journal of the Korean Society for Marine Environment & Energy
• /
• v.19 no.2
• /
• pp.99-110
• /
• 2016

When a riser is damaged, the oil spills to sea. Oil spills cause huge economic losses as well as a destruction of the marine environment. To reduce losses, it is needed to predict spilled oil volume from risers and the excursion of the oil. The present paper simulated the oil spill for a damaged riser using open source libraries, called Open-FOAM. To verify numerical methods, jet flow and Rayleigh-Taylor instability were simulated. The oil spill was simulated for various damaged leak size, spilled oil volume rates, damaged vertical locations of a riser, and current speeds. From results, the maximum excursion of the spilled oil at the certain time was predicted, and a forecasting model for various parameters was suggested.

• Journal of IKEEE
• /
• v.23 no.1
• /
• pp.120-126
• /
• 2019

Recently, accurate prediction of power consumption based on machine learning techniques in Internet of Energy (IoE) has been actively studied using the large amount of electricity data acquired from advanced metering infrastructure (AMI). In this paper, we propose a deep learning model based on Gated Recurrent Unit (GRU) as an artificial intelligence (AI) network that can effectively perform pattern recognition of time series data such as the power consumption, and analyze performance of the prediction based on real household power usage data. In the performance analysis, performance comparison between the proposed GRU-based learning model and the conventional learning model of Long Short Term Memory (LSTM) is described. In the simulation results, mean squared error (MSE), mean absolute error (MAE), forecast skill score, normalized root mean square error (RMSE), and normalized mean bias error (NMBE) are used as performance evaluation indexes, and we confirm that the performance of the prediction of the proposed GRU-based learning model is greatly improved.