• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.39 no.6
• /
• pp.713-723
• /
• 2019

Due to the climate change and various rainfall pattern, it is difficult to estimate a rainfall criterion which cause inundation for urban drainage districts. It is necessary to examine the result of inundation analysis by considering the detailed topography of the watershed, drainage system, and various rainfall scenarios. In this study, various rainfall scenarios were considered with the probabilistic rainfall and Huff's time distribution method in order to identify the rainfall characteristics affecting the inundation of the Hyoja drainage basin. Flood analysis was performed with SWMM and two-dimensional inundation analysis model and the parameters of SWMM were optimized with flood trace map and GA (Genetic Algorithm). By linking SWMM and two-dimensional flood analysis model, the fitness ratio between the existing flood trace and simulated inundation map turned out to be 73.6 %. The occurrence of inundation according to each rainfall scenario was identified, and the rainfall criterion could be estimated through the logistic regression method. By reflecting the results of one/two dimensional flood analysis, and AWS/ASOS data during 2010~2018, the rainfall criteria for inundation occurrence were estimated as 72.04 mm, 146.83 mm, 203.06 mm in 1, 2 and 3 hr of rainfall duration repectively. The rainfall criterion could be re-estimated through input of continuously observed rainfall data. The methodology presented in this study is expected to provide a quantitative rainfall criterion for urban drainage area, and the basic data for flood warning and evacuation plan.

• Korean Journal of Remote Sensing
• /
• v.36 no.5_4
• /
• pp.1179-1194
• /
• 2020

This study investigates the feasibility of three algorithms, K-Nearest Neighbors (K-NN), Random Forest (RF) and Neural Network (NN), for estimating the air temperature of an unobserved area where the weather station is not installed. The satellite image were obtained from Landsat-8 and MODIS Aqua/Terra acquired in 2019, and the meteorological ground weather data were from AWS/ASOS data of Korea Meteorological Administration and Korea Forest Service. In addition, in order to improve the estimation accuracy, a digital surface model, solar radiation, aspect and slope were used. The accuracy assessment of machine learning methods was performed by calculating the statistics of R² (determination coefficient) and Root Mean Square Error (RMSE) through 10-fold cross-validation and the estimated values were compared for each target area. As a result, the neural network algorithm showed the most stable result among the three algorithms with R² = 0.805 and RMSE = 0.508. The neural network algorithm was applied to each data set on Landsat imagery scene. It was possible to generate an mean air temperature map from June to September 2019 and confirmed that detailed air temperature information could be estimated. The result is expected to be utilized for national disaster safety management such as heat wave response policies and heat island mitigation research.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.19 no.5
• /
• pp.480-488
• /
• 2018

The development of information and communication technology has been carried out actively in the field of agriculture to generate valuable information from large amounts of data and apply big data technology to utilize it. Crops and their varieties are determined by the influence of the natural environment such as temperature, precipitation, and sunshine hours. This paper derives the climatic factors affecting the production of crops using the garlic growth process and daily meteorological variables. A prediction model was also developed for the production of garlic per unit area. A big data analysis technique considering the growth stage of garlic was used. In the exploratory data analysis process, various agricultural production data, such as the production volume, wholesale market load, and growth data were provided from the National Statistical Office, the Rural Development Administration, and Korea Rural Economic Institute. Various meteorological data, such as AWS, ASOS, and special status data, were collected and utilized from the Korea Meteorological Agency. The correlation analysis process was designed by comparing the prediction power of the models and fitness of models derived from the variable selection, candidate model derivation, model diagnosis, and scenario prediction. Numerous weather factor variables were selected as descriptive variables by factor analysis to reduce the dimensions. Using this method, it was possible to effectively control the multicollinearity and low degree of freedom that can occur in regression analysis and improve the fitness and predictive power of regression analysis.

• Journal of Digital Convergence
• /
• v.14 no.8
• /
• pp.245-252
• /
• 2016

The purpose of this study is to make up for missing of weather informations from ASOS and AWS using artificial neural networks. We collected temperature, relative humidity and wind velocity for August during 5-yr (2011-2015) and sample designed artificial neural networks, assuming the Seoul weather station was missing. The result of sensitivity study on number of epoch shows that early stopping appeared at 2,000 epochs. Correlation between observation and prediction was higher than 0.6, especially temperature and humidity was higher than 0.9, 0.8 respectively. RMSE decreased gradually and training time increased exponentially with respect to increase of number of epochs. The predictability at 40 epoch was more than 80% effect on of improved results by the time the early stopping. It is expected to make it possible to use more detailed weather information via the rapid missing complemented by quick learning time within 2 seconds.

• Journal of Environmental Science International
• /
• v.23 no.5
• /
• pp.873-885
• /
• 2014

To identify the characteristics of extreme heat events and tropical nights in major cities, the correlations between automated synoptic observing station (ASOS), automatic weather station (AWS), and temperature in seven metropolitan areas were analyzed. Temperatures at ASOS were found to be useful sources of the reference temperature of each area. To set the standard for identifying dates of extreme heat events in relation to regional topography and the natural environment, the monthly and yearly frequency of extreme heat in each region was examined, based on the standards for extreme heat day (EHD), tropical night day (TND), and extreme heat and tropical night day (ETD). All three cases identified 1994 as the year with the most frequent heat waves. The frequency was low according to all three cases in 1993, 2003 and 2009. Meanwhile, the yearly rate of increase was the highest in 1994, followed by 2010 and 2004, indicating that the frequency of extreme heat changed significantly between 1993 and 1994, 2003 and 2004, and 2009 and 2010. Therefore all three indexes can be used as a standard for high temperature events. According to monthly frequency data for EHD, TND, and ETD, July and August accounted for 80% or more of the extreme heat of the entire year.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.05a
• /
• pp.491-493
• /
• 2022

Flood damage due to torrential rains and typhoons is occurring in many parts of the world. In this paper, we propose a water level prediction model using water level, precipitation, and humidity data, which are key parameters for flood prediction, as input data. Based on the LSTM and GRU models, which have already proven time-series data prediction performance in many research fields, different input datasets were constructed using the ASOS(Automated Synoptic Observing System) data and AWS(Automatic Weather System) data provided by the Korea Meteorological Administration, and performance comparison experiments were conducted. As a result, the best results were obtained when using ASOS data. Through this paper, a performance comparison experiment was conducted according to the input data, and as a future study, it is thought that it can be used as an initial study to develop a system that can make an evacuation decision in advance in connection with the flood risk determination model.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2023.05a
• /
• pp.351-351
• /
• 2023

강우 자료는 수문 모델링에서 중요한 입력 요소 중 하나이다. 강우의 공간적 가변성은 모델링 불확실성의 중요한 원인으로 알려져 있다. 강우 관측자료는 많은 경우 유역을 대표하는 평균 면적강수량 (Mean Areal Precipitation, MAP)을 계산하여 수문모형에 입력된다. 선행 연구에서는MAP 예측 결과의 신뢰도를 개선하기 위하여 다양한 보간 방법이 개발되었다. 하지만, 강우특성의 동질성를 고려한 대표 기상 관측소 선정이 MAP 예측과 유출량 모의 결과에 미치는 연구는 아직 미흡한 실정이다. 본 연구에서는 유역의 MAP 예측에 있어 강우특성의 동실성을 고려한 강우 관측소 선정이 수문 모델링 성능 개선에 미치는 영향을 평가하고자 한다. 본 연구에서는 종관 기상관측(ASOS) 74개 지점과 방재기상관측(AWS) 400여개 지점에서 2003~2022년 기간에 대한 일강수량 자료를 수집하였고 강우특성이 동질한 지역을 구분하였다. 또한, 강우특성 동질성의 고려 유무에 따른 MAP를 계산하였다. 이후, 5개의 매개변수로 이루어진 개념적 강우-유출 모형FPHM을 사용하여 우리나라 전역 41개 유역을 대상으로 MAP 계산 결과가 모형 성능에 미치는 민감도를 조사하였다. 분석 결과, 강우특성의 동질성을 고려한 강우 관측소의 선택은 MAP 보간 방법 이상으로 중요한 요소임을 확인할 수 있었다.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2021.06a
• /
• pp.242-242
• /
• 2021

지구온난화에 의해 야기된 기후변화로 인하여 최근 국지성 집중호우의 발생 빈도와 강도가 증가하고 있는 추세이며, 또한 기온, 강수량 등의 변화로 농경지 재배작물과 시설재배와 같은 재배방법의 변화 등 농경지의 재배환경이 빠르게 변화하고 있다. 이러한 극한기상의 발생 빈도 및 강도의 증가와 농경지 재배환경의 변화는 홍수로 인한 하천수 범람, 지하수위 상승, 배수불량, 도달시간의 감소 등 저지대 재배지 및 농경지에서의 침수 위험을 증가 시키는 원인이다. 이로 인해, 매년 농경지 침수로 인하여 많은 농가들이 피해를 겪고 있으며 피해 규모와 빈도 또한 증가하고 있는 추세를 보이고 있다. 따라서 농경지 침수 피해 저감을 위하여 다양한 관계기관과 연구자들이 배수개선사업 및 침수 예측 및 피해 저감을 위한 연구를 수행하고 있다. 본 연구에서는 기후변화 및 재배환경의 변화가 농경지 침수에 미치는 영향을 분석하기 위하여 기상청 종관기상관측장비(ASOS) 및 방재기상관측장비(AWS)의 지점 강수량 자료를 수집하고 기후변화의 변동 특성을 분석하였다. 또한 과거 농경지 재배 현황 및 침수 피해 발생 자료를 수집하여 농경지 재배환경의 변화와 농경지 침수 피해를 분석하였다. 본 연구에서 수행된 기후변화 및 농경지 재배환경 변화 등 복합적인 요인에 의해 발생하는 농경지 침수 피해에 대한 분석을 통하여 추후 기후변화 및 재배환경 변화를 고려한 배수시설물의 효율적인 운영을 위한 기초자료로 활용될 수 있을 것으로 사료된다.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2020.06a
• /
• pp.135-135
• /
• 2020

우리나라의 기후 자료는 일반적으로 기상청에서 발표하는 종관기상관측(ASOS)과 방재기상관측(AWS), 그리고 북한이 세계기상기구(WMO, World Meteorogical Organization)의 기상통신망(GTS)을 통해 보낸 북한기상관측(NKO)을 사용 할 수 있다. 그러나 이 중 40년 이상의 완전한 관측 자료를 얻을 수 있는 건 ASOS가 유일하지만 공간적인 표현에 한계를 갖고 있다. AWS는 관측소가 많다는 장점이 있지만 관측 기간이 길지 않고 이용 가능한 기간에도 관측이 연속적이지 못한 경우가 많다. NKO는 비록 27개의 관측소가 있지만 많은 데이터가 누락되어 일별 기후자료의 사용에 한계를 갖고 있다. 이러한 미관측 기간이나 관측 자료의 누락은 연속적인 시계열 자료분석을 기반으로 하는 수자원 모델링에 있어서 문제를 야기한다. 본 연구는 1973년부터 2019년까지 47년의 신뢰도 높은 한반도 일일 기후 자료를 구축하기 위해 다양한 방법론을 비교하였다. 추정에 사용한 방법은 총 7개로 EM algorithm for probabilistic principal components (PPCA-EM), Inverse distance weight method (IDWM), Nearest neighbor method (NNM), Multivariate normal copulas (Copula), Elastic net model (Elastic), Ordinary kriging (OK), Regularized principal components with EM algorithm (RPCA-EM)를 살펴보았다. 다양한 형태의 결측치를 가정하여 그 결과값을 비교하였고 이는 Root mean squared error(RMSE), Kling-Gupta efficiency(KGE), Nash-Sutcliffe efficiency(NSE)를 통해 평가하였다. 최종 선택된 방법론을 통하여 한반도 전역을 그리드 기반의 강수 및 최저온도/최고온도의 일별자료로 생성하였다.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2021.06a
• /
• pp.134-134
• /
• 2021

Precipitation is a crucial component of water cycle and play a key role in hydrological processes. Traditionally, gauge-based precipitation is the main method to achieve high accuracy of rainfall estimation, but its distribution is sparsely in mountainous areas. Recently, satellite-based precipitation products (SPPs) provide grid-based precipitation with spatio-temporal variability, but SPPs contain a lot of uncertainty in estimated precipitation, and the spatial resolution quite coarse. To overcome these limitations, this study aims to generate new grid-based daily precipitation using Automatic weather system (AWS) in Korea and multiple SPPs(i.e. CHIRPSv2, CMORPH, GSMaP, TRMMv7) during the period of 2003-2017. And this study used a machine learning based Random Forest (RF) model for generating new merging precipitation. In addition, several statistical linear merging methods are used to compare with the results of the RF model. In order to investigate the efficiency of RF, observed data from 64 observed Automated Synoptic Observation System (ASOS) were collected to evaluate the accuracy of the products through Kling-Gupta efficiency (KGE), probability of detection (POD), false alarm rate (FAR), and critical success index (CSI). As a result, the new precipitation generated through the random forest model showed higher accuracy than each satellite rainfall product and spatio-temporal variability was better reflected than other statistical merging methods. Therefore, a random forest-based ensemble satellite precipitation product can be efficiently used for hydrological simulations in ungauged basins such as the Mekong River.