• The Journal of the Convergence on Culture Technology
• /
• v.9 no.3
• /
• pp.763-768
• /
• 2023

In this paper, the existing statistical method (ARIMA) and machine learning method (Informer) were developed and compared to predict the distribution volume of pharmaceuticals. It was found that a machine learning-based model is advantageous for daily data prediction, and it is effective to use ARIMA for monthly prediction and switch to Informer as the data increases. The prediction error rate (RMSE) was reduced by 26.6% compared to the previous method, and the prediction accuracy was improved by 13%, resulting in a result of 86.2%. Through this thesis, we find that there is an advantage of obtaining the best results by ensembleing statistical methods and machine learning methods. In addition, machine learning-based AI models can derive the best results through deep learning operations even in irregular situations, and after commercialization, performance is expected to improve as the amount of data increases.

• Proceedings of the Korean Institute of Navigation and Port Research Conference
• /
• 2022.06a
• /
• pp.275-276
• /
• 2022

VTS operators instruct ships to wait for entry and departure to sail in one-way to prevent ship collision accidents in ports with narrow routes. Currently, the instructions are not based on scientific and statistical data. As a result, there is a significant deviation depending on the individual capability of the VTS operators. Accordingly, this study built a 1d-convolutional neural network model by collecting ship and weather data to predict the exact travel time for ship entry/departure waiting for instructions in the port. It was confirmed that the proposed model was improved by more than 4.5% compared to other ensemble machine learning models. Through this study, it is possible to predict the time required to enter and depart a vessel in various situations, so it is expected that the VTS operators will help provide accurate information to the vessel and determine the waiting order.

• Atmosphere
• /
• v.34 no.1
• /
• pp.23-34
• /
• 2024

The Korea Meteorological Administration has improved medium-range weather forecasts by implementing post-processing methods to minimize numerical model errors. In this study, we employ a statistical correction technique known as the minimum continuous ranked probability score (CRPS) to refine medium-range forecast guidance. This technique quantifies the similarity between the predicted values and the observed cumulative distribution function of the Unified Model Ensemble Prediction System for Global (UM EPSG). We evaluated the performance of the medium-range forecast guidance for surface air temperature and relative humidity, noting significant enhancements in seasonal bias and root mean squared error compared to observations. Notably, compared to the existing the medium-range forecast guidance, temperature forecasts exhibit 17.5% improvement in summer and 21.5% improvement in winter. Humidity forecasts also show 12% improvement in summer and 23% improvement in winter. The results indicate that utilizing the minimum CRPS for medium-range forecast guidance provide more reliable and improved performance than UM EPSG.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.24 no.2
• /
• pp.177-184
• /
• 2024

In the situation of increasing data at fast speed, we use all kinds of complex ensemble and deep learning algorithms to get the highest accuracy. It's sometimes questionable how these models predict, classify, recognize, and track unknown data. Accomplishing this technique and more has been and would be the goal of intensive research and development in the data science community. A variety of reasons, such as lack of data, imbalanced data, biased data can impact the decision rendered by the learning models. Many models are gaining traction for such interpretations. Now, LIME and SHAP are commonly used, in which are two state of the art open source explainable techniques. However, their outputs represent some different results. In this context, this study introduces a coupling technique of LIME and Shap, and demonstrates analysis possibilities on the decisions made by LightGBM and Keras models in classifying a transaction for fraudulence on the IEEE CIS dataset.

• Journal of the Korean Society of Environmental Restoration Technology
• /
• v.27 no.3
• /
• pp.29-43
• /
• 2024

Legally protected species are one of the crucial considerations in the field of natural ecology when conducting environmental impact assessments (EIAs). The occurrence of legally protected species, especially 'Endangered Wildlife' designated by Ministry of Environment, significantly influences the progression of projects subject to EIA, necessitating clear investigations and presentations of their habitats. In perspective of statistics, a minimum of 30 occurrence coordinates is required for population prediction, but most of endangered wildlife has insufficient coordinates and it posing challenges for distribution prediction through modeling. Consequently, this study aims to propose modeling methodologies applicable when coordinate data are limited, focusing on Rodgersia podophylla, representing characteristics of endangered wildlife and northern plant species. For this methodology, 30 random sampling coordinates were used as input data, assuming little survey data, and modeling was performed using individual models included in BIOMOD2. After that, the modeling results were evaluated by using discrimination capacity and the reality reflection ability. An optimal modeling technique was proposed by ensemble the remaining models except for the MaxEnt model, which was found to be less reliable in the modeling results. Alongside discussions on discrimination capacity metrics(e.g. TSS and AUC) presented in modeling results, this study provides insights and suggestions for improvement, but it has limitations that it is difficult to use universally because it is not a study conducted on various species. By supporting survey site selection in EIA processes, this research is anticipated to contribute to minimizing situations where protected species are overlooked in survey results.

• Journal of Korean Society of Coastal and Ocean Engineers
• /
• v.29 no.4
• /
• pp.206-216
• /
• 2017

The temporal distribution of the turbulence kinetic energy (TKE) and the vertical component of Reynolds stresses ($-{\bar{u^{\prime}w^{\prime}}}$) was measured during one wave period under high wave energy conditions. The wave data were obtained at Hujeong Beach in the east coast of Korea at January 14~18 of 2017 when an extratropical cyclone was developed in the East Sea. Among the whole thousands of waves measured during the period, hundreds of regular waves that had with similar pattern were selected for the analysis in order to give three representing mean wave patterns using the ensemble average technique. The turbulence properties were then estimated based on the selected wave data. It is interesting to find out that $-{\bar{u^{\prime}w^{\prime}}}$ has one clear peak near the time of flow reversal while TKE has two peaks at the corresponding times of maximum cross-shore velocity magnitudes. The distinguished pattern of Reynolds stress indicates that vertical fluxes of such properties as suspended sediments may be enhanced at the time when the horizontal flow direction is reversed to disturb the flows, supporting the turbulence convection process proposed by Nielsen (1992). The characteristic patterns of turbulence properties are examined using the CADMAS-SURF Reynolds-Averaged Navier-Stokes (RANS) model. Although the model can reasonably simulate the distribution of TKE pattern, it fails to produce the $-{\bar{u^{\prime}w^{\prime}}}$ peak at the time of flow reversal, which indicates that the application of RANS model is limited in the prediction of some turbulence properties such as Reynolds stresses.

• Journal of Environmental Impact Assessment
• /
• v.27 no.6
• /
• pp.562-581
• /
• 2018

This study was designed to predict the changes in species richness of plants under the climate change in South Korea. The target species were selected based on the Plants Adaptable to Climate Change in the Korean Peninsula. Altogether, 89 species including 23 native plants, 30 northern plants, and 36 southern plants. We used the Species Distribution Model to predict the potential habitat of individual species under the climate change. We applied ten single-model algorithms and the pre-evaluation weighted ensemble method. And then, species richness was derived from the results of individual species. Two representative concentration pathways (RCP 4.5 and RCP 8.5) were used to simulate the species richness of plants in 2050 and 2070. The current species richness was predicted to be high in the national parks located in the Baekdudaegan mountain range in Gangwon Province and islands of the South Sea. The future species richness was predicted to be lower in the national park and the Baekdudaegan mountain range in Gangwon Province and to be higher for southern coastal regions. The average value of the current species richness showed that the national park area was higher than the whole area of South Korea. However, predicted species richness were not the difference between the national park area and the whole area of South Korea. The difference between current and future species richness of plants could be the disappearance of a large number of native and northern plants from South Korea. The additional reason could be the expansion of potential habitat of southern plants under climate change. However, if species dispersal to a suitable habitat was not achieved, the species richness will be reduced drastically. The results were different depending on whether species were dispersed or not. This study will be useful for the conservation planning, establishment of the protected area, restoration of biological species and strategies for adaptation of climate change.

• Journal of the Korean earth science society
• /
• v.28 no.2
• /
• pp.214-226
• /
• 2007

Because precipitation is influenced by various atmospheric variables, it is highly nonlinear. Although precipitation predicted by a dynamic model can be corrected by using a nonlinear Artificial Neural Network, this approach has limits such as choices of the initial weight, local minima and the number of neurons, etc. In the present paper, we correct simulated precipitation by using a multiple linear regression (MLR) method, which is simple and widely used. First of all, Ensemble hindcast is conducted by the PNU/CME Coupled General Circulation Model (CGCM) (Park and Ahn, 2004) for the period from April to August in 1979-2005. MLR is applied to precipitation simulated by PNU/CME CGCM for the months of June (lead 2), July (lead 3), August (lead 4) and seasonal mean JJA (from June to August) of the Northeast Asian region including the Korean Peninsula $(110^{\circ}-145^{\circ}E,\;25-55^{\circ}N)$. We build the MLR model using a linear relationship between observed precipitation and the hindcasted results from the PNU/CME CGCM. The predictor variables selected from CGCM are precipitation, 500 hPa vertical velocity, 200 hPa divergence, surface air temperature and others. After performing a leave-oneout cross validation, the results are compared with the PNU/CME CGCM's. The results including Heidke skill scores demonstrate that the MLR corrected results have better forecasts than the direct CGCM result for rainfall.

• Journal of Korea Water Resources Association
• /
• v.50 no.11
• /
• pp.769-779
• /
• 2017

As the occurrence of drought is recently on the rise, the reliable drought forecasting is required for developing the drought mitigation and proactive management of water resources. This study developed a probabilistic hydrological drought forecasting method using the Bayesian Networks and drought propagation relationship to estimate future drought with the forecast uncertainty, named as the Propagated Bayesian Networks Drought Forecasting (PBNDF) model. The proposed PBNDF model was composed with 4 nodes of past, current, multi-model ensemble (MME) forecasted information and the drought propagation relationship. Using Palmer Hydrological Drought Index (PHDI), the PBNDF model was applied to forecast the hydrological drought condition at 10 gauging stations in Nakdong River basin. The receiver operating characteristics (ROC) curve analysis was applied to measure the forecast skill of the forecast mean values. The root mean squared error (RMSE) and skill score (SS) were employed to compare the forecast performance with previously developed forecast models (persistence forecast, Bayesian network drought forecast). We found that the forecast skill of PBNDF model showed better performance with low RMSE and high SS of 0.1~0.15. The overall results mean the PBNDF model had good potential in probabilistic drought forecasting.

• Journal of Korea Water Resources Association
• /
• v.52 no.4
• /
• pp.279-289
• /
• 2019

Unlike other natural disasters, drought is a reoccurring and region-wide phenomenon after being triggered by a prolonged precipitation deficiency. Considering that remote sensing products provide consistent temporal and spatial measurements of precipitation, this study developed a remote sensing data-based drought outlook model. The meteorological drought was defined by the Standardized Precipitation Index (SPI) achieved from PERSIANN_CDR, TRMM 3B42 and GPM IMERG images. Bayesian networks were employed in this study to combine the historical drought information and dynamical prediction products in advance of drought outlook. Drought outlook was determined through a decision-making model considering the current drought condition and forecasted condition from the Bayesian networks. Drought outlook condition was classified by four states such as no drought, drought occurrence, drought persistence, and drought removal. The receiver operating characteristics (ROC) curve analysis were employed to measure the relative outlook performance with the dynamical prediction production, Multi-Model Ensemble (MME). The ROC analysis indicated that the proposed outlook model showed better performance than the MME, especially for drought occurrence and persistence of 2- and 3-month outlook.