• Korean Journal of Agricultural and Forest Meteorology
• /
• v.22 no.1
• /
• pp.1-12
• /
• 2020

As one of the essential resources in the agricultural process, soil moisture has been carefully managed by predicting future changes and deficits. In recent years, statistics and machine learning based approach to predict soil moisture has been preferred in academia for its generalizability and ease of use in the field. However, little is known that machine learning based soil moisture prediction is applicable in the situation of South Korea. In this sense, this paper aims to examine 1) whether publicly available weather data generated in South Korea has sufficient quality to predict soil moisture, 2) which machine learning algorithm would perform best in the situation of South Korea, and 3) whether a single machine learning model could be generally applicable in various regions. We used various machine learning methods such as Support Vector Machines (SVM), Random Forest (RF), Extremely Randomized Trees (ET), Gradient Boosting Machines (GBM), and Deep Feedforward Network (DFN) to predict future soil moisture in Andong, Boseong, Cheolwon, Suncheon region with open source weather data. As a result, GBM model showed the lowest prediction error in every data set we used (R squared: 0.96, RMSE: 1.8). Furthermore, GBM showed the lowest variance of prediction error between regions which indicates it has the highest generalizability.

• Journal of Practical Engineering Education
• /
• v.14 no.1
• /
• pp.61-74
• /
• 2022

Recently, youth unemployment, especially the unemployment problem of university graduates, has emerged as a social problem. Unemployment of university graduates is both a pan-national issue and a university-level issue, and each university is making many efforts to increase the employment rate of graduates. In this study, we present a model that predicts employment availability of D-university graduates by utilizing Machine Learning. The variables used were analyzed using up to 138 personal information, admission information, bachelor's information, etc., but in order to reflect them in the future curriculum, only the data after admission works effectively, so by department / student. The proposal was limited to the recommended ability to improve the separate employment rate. In other words, since admission grades are indicators that cannot be improved due to individual efforts after enrollment, they were used to improve the degree of prediction of employment rate. In this research, we implemented a employment prediction model through analysis of the core ability of D-University, which reflects the university's philosophy, goals, human resources awards, etc., and machined the impact of the introduction of a new core ability prediction model on actual employment. Use learning to evaluate. Carried out. It is significant to establish a basis for improving the employment rate by applying the results of future research to the establishment of curriculums by department and guidance for student careers.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.38 no.4
• /
• pp.587-593
• /
• 2018

The current road traffic noise prediction programs of Korea, which are widely used, are based upon foreign prediction model. Thus, it is necessary to verify foreign prediction models to find out whether they are suitable for the domestic road traffic environment. In addition, an analysis and an in-depth study on the main factors should be conducted in advance as the influence factors on the occurrence of traffic noise vary for each prediction model. Therefore, this study examined the influence factors and the existing prediction models used to forecast road traffic noise. Also, analyzed their relationship with the factors influencing the noise generated by driving vehicles through multiple regression analysis using a prediction model, taking into consideration of the traffic environment and the road geometric structure. In addition, this study will apply experimental values to the existing road traffic noise prediction model (NIER, RLS-90) and the deducted road traffic noise prediction model. As a result, the order of the absolute value sum of the errors are NIER, RLS-90, model value. Through comparison and verification, developed models are to be analyzed for providing basic research results for future study on road traffic noise prediction modeling.

• Journal of Korean Society of Forest Science
• /
• v.101 no.3
• /
• pp.509-516
• /
• 2012

In this research, it was intended to examine the vulnerability of Pinus rigida to climate changes, a major planting species in Korea. For this purpose, the distribution of Pinus rigida and its changes caused by climate changes were estimated based on the 'A1B' climate change scenario suggested by IPCC. Current distribution of Pinus rigida was analyzed by using the $4^{th}$Forest Type Map and its potential distribution in the recent year (2000), the near future (2050) and the further future (2100) were estimated by analyzing the optimized ranges of three climate indices - warmth index(WI), minimum temperature index of the coldest month (MTCI) and precipitation effectiveness index(PEI). The results showed that the estimated potential distribution of Pinus rigida declines to 56% in the near future(2050) and 15% in the further future (2100). This significant decline was found in most provinces in Korea. However, in Kangwon province where the average elevation is higher than other provinces, the area of potential distribution of Pinus rigida increases in the near future and the further future. Also the result indicated that the potential distribution of Pinus rigida migrates to higher elevation. The potential distributions estimated in this research have relatively high accuracy with consideration of classification accuracy (44.75%) and prediction probability (62.56%).

• Journal of Wetlands Research
• /
• v.17 no.4
• /
• pp.348-358
• /
• 2015

Impacts of climate change are being observed in the globe as well as the Korean peninsula. In the past 100 years, the average temperature of the earth rose about 0.75 degree in celsius, while that of Korean peninsula rose about 1.5 degree in celsius. The fifth Assessment Report of IPCC(Intergovermental Panel on Climate Change) predicts that the water pollution will be aggravated by change of hydrologic extremes such as floods and droughts and increase of water temperature (KMA and MOLIT, 2009). In this study, future runoff was calculated by applying climate change scenario to analyze the future water quality for each targe period (Obs : 2001 ~ 2010, Target I : 2011 ~ 2040, Target II : 2041 ~ 2070, Target III : 2071 ~ 2100) in Hongcheon river basin, Korea. In addition, The future water quality was analyzed by using multiple linear regression analysis and artificial neural networks after flow-duration curve analysis. As the results of future water quality prediction in Hongcheon river basin, we have known that BOD, COD and SS will be increased at the end of 21 century. Therefore, we need consider long-term water and water quality management planning and monitoring for the improvement of water quality in the future. For the prediction of more reliable future water quality, we may need consider various social factors with climate components.

• Atmosphere
• /
• v.26 no.4
• /
• pp.495-508
• /
• 2016

In order to determine the prediction possibility of heavy rainfall, a variety of analyses was conducted by using three-dimensional data obtained from Korea Local Analysis and Prediction System (KLAPS) re-analysis data. Strong moisture convergence occurring around the time of the heavy rainfall is consistent with the results of previous studies on such continuous production. Heavy rainfall occurred in the cloud system with a thick convective clouds. The moisture convergence, temperature and potential temperature advection showed increase into the heavy rainfall occurrence area. The distribution of integrated liquid water content tended to decrease as rainfall increased and was characterized by accelerated convective instability along with increased buoyant energy. In addition, changes were noted in the various characteristics of instability indices such as K-index (KI), Showalter Stability Index (SSI), and lifted index (LI). The meteorological variables used in the analysis showed clear increases or decreases according to the changes in rainfall amount. These rapid changes as well as the meteorological variables changes are attributed to the surrounding and meteorological conditions. Thus, we verified that heavy rainfall can be predicted according to such increase, decrease, or changes. This study focused on quantitative values and change characteristics of diagnostic variables calculated by using numerical models rather than by focusing on synoptic analysis at the time of the heavy rainfall occurrence, thereby utilizing them as prognostic variables in the study of the predictability of heavy rainfall. These results can contribute to the identification of production and development mechanisms of heavy rainfall and can be used in applied research for prediction of such precipitation. In the analysis of various case studies of heavy rainfall in the future, our study result can be utilized to show the development of the prediction of severe weather.

• Atmosphere
• /
• v.23 no.1
• /
• pp.73-83
• /
• 2013

In recent several years, East Asia, Europe and North America have suffered successive cold winters and a number of historical records on the extreme weathers are replaced with new record-breaking cold events. As a possible explanation, several studies suggested that cryospheric conditions of Northern Hemisphere (NH), i.e. Arctic sea-ice and snow cover over northern part of major continents, are changing significantly and now play an active role for modulating midlatitude atmospheric circulation patterns that could bring cold winters for some regions in midlatitude. In this study, a dynamical seasonal prediction system for NH winter is newly developed using the snow depth initialization technique and statistically predicted sea-ice boundary condition. Since the snow depth shows largest variability in October, entire period of October has been utilized as a training period for the land surface initialization and model land surface during the period is continuously forced by the observed daily atmospheric conditions and snow depths. A simple persistent anomaly decaying toward an averaged sea-ice condition has been used for the statistical prediction of sea-ice boundary conditions. The constructed dynamical prediction system has been tested for winter 2012/13 starting at November 1 using 16 different initial conditions and the results are discussed. Implications and a future direction for further development are also described.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.19 no.4
• /
• pp.138-142
• /
• 2018

This study used HILS to test an expansion joint, which is vulnerable to the water hammer effect. The operation data for the HIL simulator was the length rate of the expansion joint by the water hammer, which was used for life prediction based on the vibration durability. For the vibration durability test, the internal pressure of the expansion joint was assumed to be a factor of the durability life, and the lifetime prediction model equation was obtained by curve fitting the lifetime data at each pressure. During the test, the major failure modes of crack and water leakage occurred on the surface of the bellows part. The lifetime prediction model typically follows an inverse power law model. The pressure is a stress factor, and the model is effective in only a specific environment. Therefore, another stress factor such as temperature will be added and considered for a mixed lifetime prediction model in the future.

• Fire Science and Engineering
• /
• v.30 no.6
• /
• pp.130-136
• /
• 2016

A university needs to analyze and improve its curricula with the perspective of the consumer to develop a syllabus for the training of industry-demand customized human resources. Accordingly, this paper surveyed the demand of fire-related industry workers to evaluate the major fitness of the curriculum of fire risk prediction and assessment and carried out descriptive statistical analysis, factor analysis, cluster analysis, and one-way ANOVA based on the results. According to the analysis, fire-related industry workers reported that the curriculum of fire risk prediction and assessment is suitable for majors. In addition, they were greatly aware of the necessity of basic major and common major subjects among subjects of fire risk prediction and assessment. The results of this analysis will provide the basic data to improve the curriculum continuously in the future.

• Journal of the Korea Society of Computer and Information
• /
• v.16 no.2
• /
• pp.225-233
• /
• 2011

Stock market prices, economic indices, trends and changes of social phenomena, etc. are categorized as time series data. Research on time series data has been prevalent for a while as it could not only lead to valuable representation of data but also provide future trends as well as changes in direction. We take a conventional model based approach, known as Markov chain modeling for the prediction on stock market prices. To improve prediction accuracy, we apply Markov modeling over carefully selected intervals of training data to fit the trend under consideration to the model. Another method we take is to apply clustering to data and build models of the resultant clusters. We confirmed that clustered models are better off in predicting, however, with the loss of prediction rate.