• The Korean Journal of Applied Statistics
• /
• v.37 no.6
• /
• pp.801-815
• /
• 2024

Future uncertainty means that future results or phenomena cannot be accurately predicted. Since deterministic population projection based on such future uncertainty has clear limitations, so many advanced population research institutes and international organizations have emphasized the importance of probabilistic population prediction. It also presents probabilistic predictions in the research areas of climate, process, precipitation, and weather. However, the KOSTAT and various organizations in korea are only in scenario-based deterministic population projection, and only the need for probabilistic population prediction is raised. Therefore, this paper points out that when future uncertainties exist, the limitations and problems of decisive population projection should be examined, and the future population should be examined with probabilistic population prediction, and the results are presented. As a result of the analysis, in terms of the probabilistic confidence interval (5th quartile, 95th quartile), 5,106 to 51.2 million people in 2025, 5,053 to 5,082 million in 2030, 4,829 to 4,8 million in 2040, 4,425 to 45,5 million in 2050, and the last forecast, in 2062, the number below 40 million, is expected to be 37.33 to 33.3 million, and the rapid population deceleration over 33 years was the biggest factor rapidly decline in the fertility rate.

• The Korean Journal of Applied Statistics
• /
• v.33 no.2
• /
• pp.185-201
• /
• 2020

Scenario population projection reflects the high probability of future realization and ease of statistical interpretation. Statistics Korea (2019) also presents the results of 30 combinations, including special scenarios, as official statistics. However, deterministic population projections provide limited information about future uncertainties with several limitations that are not probabilistic. The deterministic population projections are scenario-based estimates and show a perfect autocorrelation of three factors (birth, death, movement) of population variation over time. Therefore, international organizations UN, the Max Planck Population Research Institute (MPIDR) of Germany and the Vienna Population Research Institute (VID) of Austria have suggested stochastic based population estimates. In addition, some National Statistics Offices have also adopted this method to provide information along with the scenario results. This paper calculates the demographics of Korea based on a probabilistic or stochastic basis and then draws the pros and cons and show implications of the scenario (deterministic) population projections.

• Korea journal of population studies
• /
• v.33 no.1
• /
• pp.161-189
• /
• 2010

Dealing with uncertainty has been a critical issue in demographic and population forecasting since 1980. This study reviews methodological developments in demographic and population forecasting over the last several decades. First, this study reviews the important issue of the uncertainty surrounding demographic forecasts. Several limitations of the traditional scenario approach to dealing with uncertainty are also discussed. Second, in forecasting demographic processes such as mortality, fertility, and migration, three approaches of stochastic forecasting are identified and discussed: expert judgment, statistical modeling, and analysis of historical forecast errors. Finally, this study discusses the current issues and directions for future research in stochastic demographic forecasting.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2004.05b
• /
• pp.267-271
• /
• 2004

2000년도 국내에 소개된 앙상블 유량예측은 한반도 유출특성을 고려한 예측시스템 구축을 위해 꾸준한 수정과 보완을 반복하며 약 5년간의 연구가 진행되었다. 앙상블 유량예측의 연구방향은 크게 예측의 정확성을 향상시키기 위한 이론적 인구와 수자원 계획과 관리에 활용될 수 있도록 GUI를 포함한 유량예측시스템을 구축하는 등의 실무적 연구가 함께 진행되고 있다. 앙상블 유량예측의 정확성을 향상시키기 위해 갈수기에 강우-유출모형의 모의능력을 개선해야 하며, 홍수기에는 기상예보를 효율적으로 이용해야 한다는 기본 전략을 수립하였다. 최근 강우-유출모형의 모의능력을 개선하기 위해 신경망 강우-유출모형을 구축하고, 기존 강우-유출모형의 모의결과를 보정하거나, 두개 이상의 모형을 결합함으로서 유량모의능력을 개선하여 갈수기 앙상블 유량예측 정확성을 향상시킬 수 있음을 증명하는 성과를 거둔 바 있다. 향후 앙상블 유량예측의 연구 방향은 기상예보자료의 적극적인 활용에 초점을 맞추고 있다. 최근 ENSO(El Nino Southern Occillation), PDI(Pacific Decadal Idex) 등 다양한 기후정보의 새로운 발견과 GCM 등 기후모형의 급속한 개선으로 기후 예측의 정확도가 높아지고 있는 추세이므로, 이를 이용하여 홍수기 앙상블 유량예측의 정확도 개선을 목표로 인구가 진행될 전망이다.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2005.05b
• /
• pp.85-89
• /
• 2005

도시발달과 인구증가로 인해 오늘날의 수자원 관리와 계획은 복잡하고 그 중요성은 더욱더 커지고 있으며, 인구와 재산의 집중현상으로 인하여 사소한 수문재해로 인해 막대한 인명과 재산피해를 초래될 수 있다. 이런 이유들로 인해 정확한 수문예측과 이를 통한 적절한 수자원 관리는 그 어느 때보다 중요한 인자로 인식되고 있다. 본 연구에서는 수문예측을 통한 소규모 댐으로의 정확한 월유입량 예측을 실시하여 실측유입량과 비교$\cdot$분석함으로서 수자원관리의 효율성을 향상시키고자 하였다. 수문예측을 위해서 확률론적 예측이 가능한 앙상블 예측기법(Ensemble Prediction Method)을 적용하였으며 과거 1968-1997년까지의 강우데이터와 수정 TANK모형을 이용하여 1998부터 2002년까지의 성주댐의 월유입량 앙상블을 생성하였다. 수문예측뿐만 아니라 유입량예측의 정확성을 향상시키기 위해 수정 TANK모형의 매개변수를 최적화기법 중의 하나인 유전자알고리즘을 이용하여 매개변수를 최적화하였으며 평창강유역과 보청천유역의 실측데이터를 이용하여 모형의 검증을 실시하였다. 또한 강우발생시 과소하게 유출량이 산정되는 것을 보완하기 위해 매개변수를 평수기와 홍수기의 구분하여 모형을 적용하였다. 본 연구에서 제시된 앙상블 예측기법과 최적화된 수정 TANK모형을 이용하여 댐의 수자원을 관리한다면 효율적인 관리가 이루어 질 것으로 판단된다.

• Prospectives of Industrial Chemistry
• /
• v.23 no.6
• /
• pp.3-13
• /
• 2020

저출산 고령화 사회로의 진입은 대한민국뿐만 아니라 전 세계적으로 많은 사회 문제를 야기하고 있다. 그 중에서 고령 인구 증가로 인한 의료 수요 증가와 이를 뒷받침 할 의료인력 부족은 곧 다가올 사회문제이다. 4차 산업 혁명으로 인해 다양한 사회문제에 대한 혁신적인 해법들이 제시되고 있는데, 본 기고문에서는 다가올 고령화 사회에서 의료인력 부족 등에 의한 해결법으로 원격의료 지원을 위한 인공지능 활용을 다루고자 한다. 병 진단 및 예측을 위한 여러 가지 인공지능 알고리즘은 이미 많이 개발 되어 있으나, 일반적으로 딥러닝에 많이 쓰이는 인공신경망 구조인 합성곱 뉴럴네트워크(convolution neural network)나 기존 퍼셉트론(perceptron) 구조에서 벗어나 확률론적 인공신경망 중에 하나인 베이지안 뉴럴네트워크(Bayesian neural network)를 다루고자 한다. 그중에서 연산효율적이며 뉴로모픽 하드웨어로 구현 가능성이 높고 실제 진단 예측(diagnosis prediction) 문제 해결에 강점을 보이는 알고리즘으로써 naive Bayes classifer를 활용한 연구를 소개하고자 한다.

• The Korean Journal of Applied Statistics
• /
• v.32 no.4
• /
• pp.517-541
• /
• 2019

According to the OECD (2015) and UN (2017), Korea was classified as an immigration country. The designation as an immigration country means that net migration will remain positive and international migration is likely to affect population growth. KOSTAT (2011) used a model with more than 15 parameters to divide sexes, immigration and emigration based on the Wilson (2010) model, which takes into account population migration factors. Five years later, we assume the average of domestic net migration rate for the last five years and foreign government policy likely quota. However, both of these results were conservative estimates of international migration and provide different results than those used by the OECD and UN to classify an immigration country. In this paper, we proposed a stochastic projection on international migration using nonparametric model (FDM by Hyndman and Ullah (2007) and Coherent FDM by Hyndman et al. (2013)) that uses a functional data model for the international migration data of Korea from 2000-2017, noting the international migration such as immigration, emigration and net migration is non-linear and not linear. According to the result, immigration rate will be 1.098(male), 1.026(female) in 2018 and 1.228(male), 1.152(female) in 2025 per 1000 population, and the emigration rate will be 0.907(male), 0.879(female) in 2018 and 0.987(male), 0.959(female) in 2025 per 1000 population. Thus the net migration is expected to increase to 0.191(male), 0.148(female) in 2018 and 0.241(male), 0.192(female) in 2025 per 1000 population.

• Korea journal of population studies
• /
• v.33 no.2
• /
• pp.85-111
• /
• 2010

South Korea has experienced a rapid fertility decline and notable mortality improvement. As the drop in TFR was quicker and greater in terms of tempo and magnitude, it cast a new challenge of population projection - how to improve the forecasting accuracy in the country with a super-low fertility pattern. This study begin with the current status of the national population projection as implemented by Statistics Korea by comparing the 2009 interim projection with the 2006 official national population projection. Secondly, this study compare the population projection system including projection agencies, projection horizons, projection intervals, the number of projection scenarios, and the number of assumptions on fertility, mortality and international migration among super-low fertility countries. Thirdly we illustrate a stochastic population projection for Korea by transforming the population rates into one parameter series. Finally we describe the future challenges of the national population projection, and propose the projection scenarios for the 2011 official population projection. To enhance the accuracy, we suggest that Statistics Korea should update population projections more frequently or distinguish them into short-term and long-term projections. Adding more than four projection scenarios including additional types of "low-variant"fertility could show a variety of future changes. We also expect Statistics Korea topay more attention to the determination of a base population that should include both national and non-national populations. Finally we hope that Statistics Korea will find a wise way to incorporate the ideas underlying the system of stochastic population projection as part of the official national population projection.

• Journal of the Economic Geographical Society of Korea
• /
• v.22 no.3
• /
• pp.351-365
• /
• 2019

This study aims to predict the changes in population distribution in Korea by considering spatio-temporal characteristics of major migration reasons. For the purpose, we analyze the spatio-temporal characteristics of each major migration reason(such as job, family, housing, and education) and estimate the transition probability, respectively. By appling Markov chain model processes with the ChapmanKolmogorov equation based on the transition probability, we predict the changes in the population distribution for the next six years. As the results, we found that there were differences of population changes by regions, while there were geographic movements into metropolitan areas and cities in general. The methodologies and the results presented in this study can be utilized for the provision of customized planning policies. In the long run, it can be used as a basis for planning and enforcing regionally tailored policies that strengthen inflow factors and improve outflow factors based on the trends of population inflow and outflow by region by movement factors as well as identify the patterns of population inflow and outflow in each region and predict future population volatility.

• Journal of the Korean Society of Hazard Mitigation
• /
• v.2 no.2 s.5
• /
• pp.73-83
• /
• 2002

HAZUS developed by FEMA is applied to estimation on seismic hazard in Chung-Nam Province using basic data on general building, population, and geology of well-logging. Through the investigation on historical and instrumental earthquakes in Korean Peninsula seismic hazard is estimated in Chung-Nam Province in two ways for calculation of acceleration, deterministically and probabilistically. In deterministic method seismic hazard in Chung-Nam Province is estimated by generation of the maximum event that occurs in Hongsung and has magnitude of 6.0. According to the result, Hongsung Gun, Yesan Gun, and Boryung City are the most severe in building damage. The expected number of people who need hospitalization in Hongsung Gun and Yesan Gun due to the earthquake are 1.1 and 0.4, respectively. In probabilistic(return period of 5,000 year) method seismic hazard in Chung-Nam Province is estimated. According to the result, Gongju City is the most severe in building damage. The expected number of people who need hospitalization in Gongju City and Nonsan City due to the earthquake are 0.1 and 0.15, respectively.