• Journal of Korea Water Resources Association
• /
• v.49 no.9
• /
• pp.761-771
• /
• 2016

The GloSea5 (Global Seasonal forecasting system version 5) is provided and operated by the KMA (Korea Meteorological Administration). GloSea5 provides Forecast (FCST) and Hindcast (HCST) data and its horizontal resolution is about 60km ($0.83^{\circ}{\times}0.56^{\circ}$) in the mid-latitudes. In order to use this data in watershed-scale water management, GloSea5 needs spatial-temporal downscaling. As such, statistical downscaling was used to correct for systematic biases of variables and to improve data reliability. HCST data is provided in ensemble format, and the highest statistical correlation ($R^2=0.60$, RMSE = 88.92, NSE = 0.57) of ensemble precipitation was reported for the Yongdam Dam watershed on the #6 grid. Additionally, the original GloSea5 (600.1 mm) showed the greatest difference (-26.5%) compared to observations (816.1 mm) during the summer flood season. However, downscaled GloSea5 was shown to have only a -3.1% error rate. Most of the underestimated results corresponded to precipitation levels during the flood season and the downscaled GloSea5 showed important results of restoration in precipitation levels. Per the analysis results of spatial autocorrelation using seasonal Moran's I, the spatial distribution was shown to be statistically significant. These results can improve the uncertainty of original GloSea5 and substantiate its spatial-temporal accuracy and validity. The spatial-temporal reproducibility assessment will play a very important role as basic data for watershed-scale water management.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.22 no.6
• /
• pp.36-42
• /
• 2021

With recent developments in the Fourth Industrial Revolution, the manufacturing industry has changed rapidly. Through key aspects of Fourth Industrial Revolution super-connections and super-intelligence, machine learning will be able to make fault predictions during the foam-making process. Polyol and isocyanate are components in polyurethane foam. There has been a lot of research that could affect the characteristics of the products, depending on the specific mixture ratio and temperature. Based on these characteristics, this study collects data from each factor during the foam-making process and applies them to machine learning in order to predict faults. The algorithms used in machine learning are the decision tree, kNN, and an ensemble algorithm, and these algorithms learn from 5,147 cases. Based on 1,000 pieces of data for validation, the learning results show up to 98.5% accuracy using the ensemble algorithm. Therefore, the results confirm the faults of currently produced parts by collecting real-time data from each factor during the foam-making process. Furthermore, control of each of the factors may improve the fault rate.

• Korean Journal of Remote Sensing
• /
• v.39 no.6_1
• /
• pp.1427-1435
• /
• 2023

Vegetation indices based on selected wavelength reflectance measurements are used to represent crop growth and physiological conditions. However, the anisotropic properties of the crop canopy surface can govern spectral reflectance and vegetation indices. In this study, we applied an ensemble of bidirectional reflectance distribution function (BRDF) models to high-resolution Sentinel-2 satellite imagery and compared the differences between correction results before and after reflectance. In the red and near-infrared (NIR) band reflectance images, BRDF-corrected outlier values appeared in certain urban and paddy fields of farmland areas and forest shadow areas. These effects were equally observed when calculating the normalized difference vegetation index (NDVI) and 2-band enhanced vegetation index (EVI2). Furthermore, the outlier values in corrected NIR band were shown in pixels shadowed by mountain terrain. These results are expected to contribute to the development and improvement of BRDF models in high-resolution satellite images.

• Journal of the Korea Society of Computer and Information
• /
• v.28 no.11
• /
• pp.1-11
• /
• 2023

Breast cancer is the disease that affects women the most worldwide. Due to the development of computer technology, the efficiency of machine learning has increased, and thus plays an important role in cancer detection and diagnosis. Deep learning is a field of machine learning technology based on an artificial neural network, and its performance has been rapidly improved in recent years, and its application range is expanding. In this paper, we propose a DNN-SVM hybrid model that combines the structure of a deep neural network (DNN) based on transfer learning and a support vector machine (SVM) for breast cancer classification. The transfer learning-based proposed model is effective for small training data, has a fast learning speed, and can improve model performance by combining all the advantages of a single model, that is, DNN and SVM. To evaluate the performance of the proposed DNN-SVM Hybrid model, the performance test results with WOBC and WDBC breast cancer data provided by the UCI machine learning repository showed that the proposed model is superior to single models such as logistic regression, DNN, and SVM, and ensemble models such as random forest in various performance measures.

• Journal of Korea Water Resources Association
• /
• v.46 no.1
• /
• pp.59-71
• /
• 2013

The lack of sufficient flood data being kept across Korea has made it difficult to assess reliable estimates of the design flood while relatively sufficient rainfall data are available. In this regard, a rainfall simulation based derivation technique of flood frequency curve has been proposed in some of studies. The main issues in deriving the flood frequency curve is to develop the rainfall simulation model that is able to effectively reproduce extreme rainfall. Also the rainfall-runoff modeling that can convey uncertainties associated with model parameters needs to be developed. This study proposes a systematic approach to fully consider rainfallrunoff related uncertainties by coupling a piecewise Kernel-Pareto based multisite daily rainfall generation model and Bayesian HEC-1 model. The proposed model was applied to generate runoff ensemble at Daechung Dam watershed, and the flood frequency curve was successfully derived. It was confirmed that the proposed model is very promising in estimating design floods given a rigorous comparison with existing approaches.

• Proceedings of the Korean Geotechical Society Conference
• /
• 1999.10a
• /
• pp.271-278
• /
• 1999

Soil filters are commonly used to protect the soil structures from eroding and piping. When filters are clogged by fine particles which are progressively accumulated, these may lead to buildup of excessive pore pressures also leading to instability in subsurface infrastructure. A filter in the backfill of a retaining wall, a filter adjacent to the lining of a tunnel, or a filter in the bottom of an earth dam can be clogged by transported fine particles. This causes reduction in the permeability, which in turn may lead to intolerable decreases in their drainage capacity. In this thesis, the extent of this reduction is addressed using results from both experimental and theoretical investigations. In the experimental phase, the permeability reduction of a filter is monitored when an influent of constant concentration flows into the filter (uncoupled test), and when the water flow through the soil-filter system to simulate an in-situ condition (coupled test), respectively. The results of coupled and uncoupled test are compared with among others. In the theoretical phase of the investigation, a representative elemental volume of the soil filter was modeled as an ensemble of capillary tubes and the permeability reduction due to physical clogging was simulated using basic principles of flow in cylindrical tubes. In general, it was found that the permeability was reduced by at least one order of magnitude, and that the results from the uncoupled test and theoretical investigations were in good agreement. It is observed that the amount of deposited particles of the coupled test matches fairly well with that of the uncoupled test, which indicates that the prediction of permeability reduction is possible by preforming the uncoupled test instead of the coupled test, and/or by utilizing the theoretical model.

• Atmosphere
• /
• v.28 no.1
• /
• pp.25-35
• /
• 2018

This study presents future potential sea level change over the seas surrounding Korea using Climate Model Intercomparison Project Phase 5 9 model ensemble result from Representative Concentration Pathways (RCPs), downloaded from icdc.zmaw.de. At the end of 21st century, regional sea level changes are projected to rise 37.8, 48.1, 47.7, 65.0 cm under RCP2.6, RCP4.5, RCP6.0 and RCP8.5 scenario, respectively with the large uncertainty from about 40 to 60 cm. The results exhibit similar tendency with the global mean sea level rise (SLR) with small differences less than about 3 cm. For the East Sea, the Yellow Sea, and the southern sea of Korea, projected SLR in the Yellow Sea is smaller and SLR in the southern sea is larger than the other coastal seas. Differences among the seas are small within the range of 4 cm. Meanwhile, Commonwealth Scientific and Industrial Research Organization (CSIRO) data in 23 years shows that the mean rate of sea level changes around the Yellow Sea is high relative to the other coastal seas. For sea level change, contribution of ice and ocean related components are important, at local scale, Glacial Isostatic Adujstment also needs to be considered.

• Journal of Korea Water Resources Association
• /
• v.38 no.12 s.161
• /
• pp.1051-1060
• /
• 2005

The present study analyzes hydrologic utilization of optimal radar-derived rainfall by using semi-distributed TOPMODEL and evaluates the impacts of radar rainfall and model parametric uncertainty on a hydrologic model. Monte Carlo technique is used to produce the flow ensembles. The simulated flows from the corrected radar rainfalls with real-time bias adjustment scheme are well agreed to observed flows during 22-26 July 2003. It is shown that radar-derived rainfall is useful for simulating streamflow on a basin scale. These results are diagnose with which radar-rainfall Input and parametric uncertainty influence the character of the flow simulation uncertainty. The main conclusions for this uncertainty analysis are that the radar input uncertainty is less influent than the parametric one, and combined uncertainty with radar and Parametric input can be included the highest uncertainty on a streamflow simulation.

• Atmosphere
• /
• v.23 no.4
• /
• pp.377-387
• /
• 2013

Projections of changes in the low latitude atmospheric circulation under global warming are investigated using the results of the CMIP5 ensemble mean. For this purpose, 30-yr periods for the present day (1971~2000) and the end of the $21^{st}$ century (2071~2100) according to the RCP emission scenarios are compared. The wintertime subtropical jet is projected to strengthen on the upper side of the jet due to increase in meridional temperature gradient induced by warming in the tropical upper-troposphere and cooling in the stratosphere except for the RCP2.6. It is also found that a strengthening of the upper side of the wintertime subtropical jet in the RCP2.6 due to tropical upper-tropospheric warmings. Model-based projection shows a weakening of the mean intensity of the Hadley cell, an upward shift of cell, and poleward shift of the Hadley circulation for the winter cell in both hemispheres. A weakening of the Walker circulation, which is one of the most robust atmospheric responses to global warming, is also projected. These results are consistent with findings in the previous studies based on CMIP3 data sets. A weakening of the Walker circulation is accompanied with decrease (increase) in precipitation over the Indo-Pacific warm pool region (the equatorial central and east Pacific). In addition, model simulation shows a decrease in precipitation over subtropical regions where the descending branch of the winter Hadley cell in both hemispheres is strengthened.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.19 no.4
• /
• pp.13-29
• /
• 2020

Automobiles have long been an essential part of daily life, but the social costs of car traffic accidents exceed 9% of the national budget of Korea. Hence, it is necessary to establish prevention and response system for car traffic accidents. In order to present a model that can classify and predict the degree of injury in car traffic accidents, we used big data analysis techniques of K-nearest neighbor, logistic regression analysis, naive bayes classifier, decision tree, and ensemble algorithm. The performances of the models were analyzed by using the data on the nationwide traffic accidents over the past three years. In particular, considering the difference in the number of data among the respective injury severity levels, we used down-sampling methods for the group with a large number of samples to enhance the accuracy of the classification of the models and then verified the statistical significance of the models using ANOVA.