• 자원환경지질
• /
• 제56권1호
• /
• pp.65-73
• /
• 2023

As one of the most vulnerable countries to floods, there should be an increased necessity for accurate and reliable flood forecasting in Indonesia. Therefore, a new prediction model using a machine learning algorithm is proposed to provide daily flood prediction in Indonesia. Data crawling was conducted to obtain daily rainfall, streamflow, land cover, and flood data from 2008 to 2021. The model was built using a Random Forest (RF) algorithm for classification to predict future floods by inputting three days of rainfall rate, forest ratio, and stream flow. The accuracy, specificity, precision, recall, and F1-score on the test dataset using the RF algorithm are approximately 94.93%, 68.24%, 94.34%, 99.97%, and 97.08%, respectively. Moreover, the AUC (Area Under the Curve) of the ROC (Receiver Operating Characteristics) curve results in 71%. The objective of this research is providing a model that predicts flood events accurately in Indonesian regions 3 months prior the day of flood. As a trial, we used the month of June 2022 and the model predicted the flood events accurately. The result of prediction is then published to the website as a warning system as a form of flood mitigation.

• 한국수자원학회:학술대회논문집
• /
• 한국수자원학회 2021년도 학술발표회
• /
• 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.

• 한국작물학회지
• /
• 제41권2호
• /
• pp.131-138
• /
• 1996

건답직파재배에서 가장 중요한 입모율의 확보와 잡초 방제에 대한 기초 자료를 얻기 위하여 강우 후 토양이 건조하면서 형성되는 토양 피막과 토양 경도의 변화가 벼와 피의 출아에 미치는 영향을 검토하고자 본 연구를 하였다. 실험은 강우를 차단하기 위하여 사방이 트인 비닐하우스에서 실시하였으며 사양토, 양토, 미사질양토를 공시하여 파종 . 복토(4cm)후 0, 20, 40mm의 강우를 인위적으로 처리하며 출아율과 유아 특성을 조사하였다. 벼는 이탤리코나베르네코, 다다조, 갈색까락샤레벼, 동진벼, 섬진벼를 공시하였으며, 피는 돌피와 강피를 공시하였다. 실험기간 중 평균기온은 31.3$^{\circ}C$였고, 일사량은 16.6MJ/m$^2$/day였다. 1. 파종 .복토 후 강우 처리를 한 경우 토양이 건조됨에 따라 토양 피막이 형성되었으며 토양 경도가 급격히 증가하였다. 토양 경도는 강우량이 많을수록, 점토 함량이 높을수록 높았다. 2. 벼는 강우 처리로 출아율이 감소하였으며, 특히 동진벼와 섬진벼는 점토 함량이 높은 사양토에서 현저히 낮아졌다. 피의 평균 출아율은 벼보다 낮았으나 토성 및 강우 처리에 의한 출아율의 차이는 없었다. 3. 섬진벼와 동진벼의 출아율은 출아기의 평균토양경도가 증가할수록 감소하여, 토양경도가 1.0kg/$cm^2$이하일 때는 80%, 1.7kg/$cm^2$이상일 때는 50%이하로 감소하였다. 4. 출아속도는 피가 벼보다 빨랐고, 강피는 돌피보다 빨랐다. 벼 품종 중에서는 이탤리코나베르네코와 다다조가 빨랐으며 갈색까락샤레벼는 출아율은 이들 품종과 비슷하였으나 출아 속도는 늦었다. 5. 피는 벼에 비하여 중배축의 신장 정도가 현저히 컸다. 벼 품종중 이탤리코나베르네코와 다다조는 불완전엽과 중배축이, 갈색까락샤레벼는 중배축의 신장이 잘 되어 본엽이 지상에서 전개되었으나 동진벼와 섬진벼 는 유아의 신장이 잘 안되어 지중에서 본엽이 전개되었다. 6. 강우 처리 후 토양의 경화와 토막 형성에 의하여 벼 특히 우리 나라 장려품종들의 출아가 현저하게 저하된 데 반하여 돌피와 강피, 벼 품종 중 이탤리코나베르네코, 다다조, 잡초성 벼인 갈색까락샤레벼는 출아율의 저하가 적었는데 이는 피와 이들 벼 품종이 출아 속도가 빠르고 또한 중배축과 불완전엽의 신장성이 크기 때문인 것으로 판단되었다.

• 한국환경복원기술학회지
• /
• 제6권4호
• /
• pp.1-7
• /
• 2003

Artificial ground greening, which is considered as a way for the greening of cities, should be constructed easily and maintained continuously. Thus it is necessary to use light soils for keeping in flexible formation and light load. And the garden should be managed optimally taking account for the characteristics of the soil and plant. But in most landscape green area, they are not under management. Mostly they are occasionally irrigated without nutrient by hand-operating. So this study was conducted to investigate plant growth by management methods and soil depth(15cm, 30cm). As a results of the different methods of management had effect on the plant growth and on the rate of flowering. When Hosta longipes were grown in different three management methods, control(rainfall), periodical irrigation, and nutri-irrigation(fertigation), the content of chlorophyll, the plant growth and the rate of flowering were higher in nutri-irrigation (fertigation) treatment than those in control(rainfall) and periodic irrigation. And nutrient contents of leaf are also higher. Between 15cm and 30cm soil depth, the plant growth of 15cm soil depth is better than that of 30 soil depth. According to these results on artificial ground greening, determination of optimal soil depth by plant species is required, And a specialist for nutrient management is demanded.

• 한국지반공학회논문집
• /
• 제31권2호
• /
• pp.5-11
• /
• 2015

비탈면의 안정성은 강우지속시간, 확률강우강도, 지반의 불포화특성, 지반강도 등에 의해 영향을 받는다. 최근 비탈면안정성 해석은 지반의 침투특성을 고려한 불포화해석을 수행하고 있으며, 불포화 토사비탈면에 대한 연구는 시간변화에 따라 지반의 변형과 응력분포해석을 고려할 수 있도록 하는 방향으로 진행되고 있다. 그러나 이와는 별개로 불포화사면의 침투특성은 강우강도나 지속시간 뿐만 아니라 비탈면의 지형여건과 녹화상태에 따라서도 침투정도가 다르지만, 이에 대한 영향은 고려하지 않고 있다. 본 연구에서는 비탈면경사 및 표면상태에 따른 침투를 고려하기 위하여 토양의 수리특성을 고려한 모형을 사용하고, 토사비탈면에 대한 불포화해석을 수행하여 비탈면 경사에 따른 영향을 파악하였다. 연구결과 비탈면 안정해석시 동일한 강우조건 하에서도 비탈면경사에 따른 침투율이 고려되어야 할 필요성을 제시하였다.

• 한국물환경학회지
• /
• 제26권5호
• /
• pp.740-746
• /
• 2010

Rainwater has been used in many countries as a way of minimizing water availability problems. Rainwater harvesting system (RHS) has been successfully implemented as alternative water supply sources even in Korea. Although RHS is an effective alternative to water supply, its efficiency is often heavily influenced by temporal distribution of rainfall. Since natural precipitation is a random process and has probabilistic characteristics, it will be more appropriate to describe these probabilistic features of rainfall and its relationship with design storage capacity as well as supply deficit of RHS. This study presents the methodology to establish the relationships between storage capacities and deficit rates using probability distributions. In this study, the real three-story building was considered and nine scenaries were developed because the daily water usage pattern of the study one was not identified. GEV, Gumbel and the generalized logistic distribution ware selected according to the results of Kolmogorov-Smirnov test and Chi-Squared test. As a result, a set of curves describing the relationships under different exceedance probabilities were generated as references to RHS storage design. In case of the study building, the deficit rate becomes larger as return period increases and will not increase any more if the storage capacity becomes the appropriate quantity. The uncertainties between design storage and the deficit can be more understood through this study on the probabilistic relationships between storage capacities and deficit rates.

• 한국물환경학회지
• /
• 제29권3호
• /
• pp.354-364
• /
• 2013

The performance of the stormwater wetlands can be significantly influenced by antecedent stormwater in storage at the commencement of a stormevent. As inflows are intermittent and stochastic in nature, the evaluation of the treatment efficiency of a stormwater wetland should be considered by runoff capture and water treatment characteristics during interevent periods. In this study, analytical probabilistic model is applied to identity runoff capture rate and treatment efficiency of the stormwater wetland. To achieve this, continuous rainfall data recorded in Busan for 31 years has been analyzed to derive the runoff capture rate, and 1st order kinetic decay constants ($k_V$, 1/d) are calculated from regression analysis to identify pollutants removal during interevent periods. The results show that about 60.9% of annual average runoff is captured through the stormwater wetland. The annual average treatment efficiencies of SS, BOD, COD, TN and TP is about 11.4, 8.9, 9.8, 4.3 and 9.6%, respectively. The analytical model has been compared with the numerical model and it shows that analytical model is valid. Performance evaluation methods developed in this study has the advantages of considering characteristics of rainfall-runoff, facility type and pollutant removal.

• 한국방재학회 논문집
• /
• 제10권5호
• /
• pp.109-116
• /
• 2010

강우로 인한 침투 및 지하수위 상승은 산사태나 사면 활동의 주요 원인이다. 이러한 경우 사면의 안전율을 확보하기 위하여 사면 경사를 완만하게 하거나, 보강재를 이용하여 저항력을 높여주는 공법이 사용된다. Mass Nail 공법은 Nail 보강공과 경사면 배수공, 표면 녹화공을 동시에 적용할 수 있는 환경 친화적인 경사면 보강 공법이다. 본 연구에서는 Mass Nail로 보강된 사면의 보강효과를 확인하기 위해 강우로 인한 사면의 함수비 변화를 고려하여 실내 모형 실험을 수행하였다. 그 결과, 무보강 사면에 대한 Mass Nail 보강 사면의 안전율은 약 1.4~2.3배 증가하였고, 함수비를 10%에서 22%로 증가 할 경우 무보강 사면에서 최대 응력은 12%~24%, 평균 18% 감소하였고, Mass Nail 경사면 보강법을 적용한 사면은 4%~23%, 평균 14% 감소함을 알 수 있었다.

• 한국농공학회논문집
• /
• 제54권2호
• /
• pp.95-102
• /
• 2012

The objective of this research was to experimentally test the effect of rice straw mats on the reduction of runoff, sediment discharge and turbidity under a laboratory scale. We used the small runoff plots of 1 m ${\times}$ 1 m ${\times}$ 0.65 m ($L{\times}W{\times}H$) in size filled with loamy sand. Experimental treatments were bare (control), rice straw mat cover of straw mats + PAM + Gypsum (SPG), rice straw mats + Chaff + PAM + Gypsum (SCPG) and rice straw mats + Sawdust + PAM + Gypsum (SSPG); slope of 10 % or 20 %; and rainfall intensity of 30 mm/hr. Runoff volume and rate of covered plots were significantly lower than those of control plot. Average runoff rate of covered plots, slope of 10 % and 20 %, decreased 85.6 % and 72 % in respectively. Sediment reduction ratio was more than 99 % regardless of slope. The differences runoff and sediment discharge among different cover materials were not significant. It was also shown that even if runoff reduction by surface cover were low, sediment discharge reduction could be very significant and contribute to improve the water quality of streams in sloping agricultural regions. It was concluded that the use of straw mat and soil amendments (PAM and Gypsum) on sloping agricultural fields could reduce soil erosion and muddy runoff significantly and help improve the water quality and aquatic ecosystem in receiving waters. But mixing effect of PAM and Gypsum was minimal.

• 한국농공학회논문집
• /
• 제50권2호
• /
• pp.65-71
• /
• 2008

A monsoon season monitoring data from June to September, 2005 of a small forested watershed located at the upstream of the North Han River system in Korea was conducted to analyze the flow variations, the NPS pollutant concentrations, and the pollution load characteristics with respect to sampling frequencies. During the 4-month period, 1,423 mm or 79.2% of annual rainfall(1,797 mm) were occurred and more than 77%, 54% and 68% of annual T-N, $NO_3$-N and T-P loads discharged. Flow rate was continuously measured with automatic velocity and water level meters and 58 water quality samples were taken and analyzed. It was analyzed that the flow volume by random measurement varied very widely and ranged from 79% to 218% of that of continuous measurement. It was recommended that flow measurement of small forested watersheds should be continuously measured with automated flow meters to precisely measure flow rates. Flow-weighted mean concentrations of T-N, $NO_3$-N and T-P during the period were 2.114 mg/L, 0.836 mg/L, and 0.136 mg/L, respectively. T-N, $NO_3$-N and T-P loads were sensitive to the number of samples. And it was analyzed that in order to measure the pollution load within the error of 10% to the true load, the rate of sampling frequency should be higher than 89.7% of the sample numbers that were required to compute the true pollution load. If it is compared to selected foreign research results, about 10 water samples for each rainfall event were needed to compute the pollution load within 10% error. It is unlikely in Korea and recommended that thorough NPS pollution monitoring studies are required to develop the standard monitoring procedures for reliable NPS pollution quantification.