• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제15권5호
• /
• pp.1690-1707
• /
• 2021

Precipitation prediction during flood season has been a key task of climate prediction for a long time. This type of prediction is linked with the national economy and people's livelihood, and is also one of the difficult problems in climatology. At present, there are some precipitation forecast models for the flood season, but there are also some deviations from these models, which makes it difficult to forecast accurately. In this paper, based on the measured precipitation data from the flood season from 1993 to 2019 and the precipitation return data of CWRF, ANN cycle modeling and a weighted integration method is used to correct the CWRF used in today's operational systems. The MAE and TCC of the precipitation forecast in the flood season are used to check the prediction performance of the proposed algorithm model. The results demonstrate a good correction effect for the proposed algorithm. In particular, the MAE error of the new algorithm is reduced by about 50%, while the time correlation TCC is improved by about 40%. Therefore, both the generalization of the correction results and the prediction performance are improved.

• 한국산림과학회지
• /
• 제86권3호
• /
• pp.334-341
• /
• 1997

솔잎혹파리 유충(幼蟲)은 대부분(大部分) 강우시(降雨時)에 낙하(落下)하는 생태적(生態的) 특성(特性)을 이용(利用), 추기(秋期)의 자연낙하기(自然落下期) 동안 피해임지내(被害林地內)의 수관상부(樹冠上部)에 분수장치(噴水裝置)를 설치(設置)하고 강수량별(降水量別), 강수시기별(降水時期別) 및 강수시각별(降水時刻別)로 인공강수(人工降水)를 실시(實施)하여 인공강수(人工降水)가 솔잎혹파리 유충낙하(幼蟲落下)에 미치는 영향(影響)을 분석검토(分析檢討), 인공강수(人工降水)에 의(依)한 새로운 천적사육용(天敵飼育用) 솔잎혹파리 유충채집법(幼蟲採集法)을 개발(開發)코자 하였으며 얻어진 결과(結果)는 다음과 같다. 1. 인공강수(人工降水)에 의(依)한 솔잎혹파리 천적사육용(天敵飼育用) 유충채집법(幼蟲採集法)은 매우 효과적(效果的)이었으며 유충채집(幼蟲採集)에 필요(必要)한 적정강수량(適正降水量)은 5.3-9.4mm, 이때에 소요(所要)된 살수량(撒水量) 및 살수시간(撒水時間)은 각각(各各) $8,000-16,000{\ell}$와 180-360분(分) 이었다. 2. 인공강수(人工降水)에 의(依)한 효과적(效果的)인 유충채집시기(幼蟲採集時期)는 중부지방(中部地方) 소나무림(林)의 경우 11월(月) 초순(初旬)부터 중순(中旬)까지 약(約) 20일간(日間)이며 이 기간(期間)에 낙하(落下)한 유충수(幼蟲數)는 전체(全體) 낙하수(落下數)의 93.4%였다. 3. 하루중에 있어서의 인공강수(人工降水)에 의(依)한 유충낙하(幼蟲落下)는 강수시각(降水時刻)에 영향(影響)을 받지 않았다. 4. 인공강수(人工降水)에 의(依)한 유충(幼蟲)의 채집시기별(採集時期別) 천적기생율(天敵寄生率)은 11월(月)의 것이 비교적(比較的) 높았으며 12월(月) 채집분(採集分)은 다소 떨어지는 경향(傾向)을 보였다. 5. 인공강수(人工降水)에 의(依) 유충채집적지(幼蟲採集跡地)의 1년후(年後)의 밀도변동(密度變動)은 채집전(採集前)과 비교(比較)하여 약(約) 34%의 밀도감소효과(密度減少效果)가 있었다. 6. 인공강수(人工降水)에 의(依)한 유충채집방법(幼蟲採集方法)은 현행방법(現行方法)인 충영채집법(蟲癭採集法)에 비(比)하여 약(約) 14-50%의 채집비용(採集費用)(경제적(經濟的)) 절감효과(節減效果)가 있었다.

• 한국지하수토양환경학회지:지하수토양환경
• /
• 제16권6호
• /
• pp.66-78
• /
• 2011

It is getting difficult to manage water resources in South Korea because more than half of annual precipitation is concentrated in the summer season and its intensity is increasing due to global warming and climate change. Artificial recharge schemes such as well recharge of surface water and roof-top rainwater harvesting can be a useful method to manage water resources in Korea. In this study, potential artificial recharge site is evaluated using geographic information system with hydrogeological and social factors. The hydrogeological factors include annual precipitation, geological classification based on geological map, specific capacity and depth to water level of national groundwater monitoring wells. These factors were selected to evaluate potential artificial recharge site because annual precipitation is closely related to source water availability for artificial recharge, geological features and specific capacity are related to injection capacity and depth to water is related to storage capacity of the subsurface medium. In addition to those hydrogeological factors, social aspect was taken into consideration by selecting the areas that is not serviced by national water works and have been suffered from drought. These factors are graded into five rates and integrated together in the GIS system resulting in spatial distribution of artificial recharge potential. Cheongsong, Yeongdeok in Gyeongsangbuk-do and Hadong in Gyeongsangnam-do, and Suncheon in Jeollanam-do were proven as favorable areas for applying artificial recharge schemes. Although the potential map for artificial recharge in South Korea developed in this study need to be improved by using other scientific factors such as evaporation and topographical features, and other social factors such as water-curtain cultivation area, hot spring resorts and industrial area where groundwater level is severely lowered, it can be used in a rough site-selection, preliminary and/or feasibility study for artificial recharge.

• Geomechanics and Engineering
• /
• 제17권5호
• /
• pp.421-427
• /
• 2019

Coastal erosion is becoming a significant problem in Greece, Bangladesh, and globally. For the prevention and minimization of damage from coastal erosion, combinations of various structures have been used conventionally. However, most of these methods are expensive. Therefore, creating artificial beachrock using local ureolytic bacteria and the MICP (Microbially Induced Carbonate Precipitation) method can be an alternative for coastal erosion protection, as it is a sustainable and eco-friendly biological ground improvement technique. Most research on MICP has been confined to land ureolytic bacteria and limited attention has been paid to coastal ureolytic bacteria for the measurement of urease activity. Subsequently, their various environmental effects have not been investigated. Therefore, for the successful application of MICP to coastal erosion protection, the type of bacteria, bacterial cell concentration, reaction temperature, cell culture duration, carbonate precipitation trend, pH of the media that controls the activity of the urease enzyme, etc., are evaluated. In this study, the effects of temperature, pH, and culture duration, as well as the trend in carbonate precipitation of coastal ureolytic bacteria isolated from two coastal regions in Greece and Bangladesh, were evaluated. The results showed that urease activity of coastal ureolytic bacteria species relies on some environmental parameters that are very important for successful sand solidification. In future, we aim to apply these findings towards the creation of artificial beachrock in combination with a geotextile tube for coastal erosion protection in Mediterranean countries, Bangladesh, and globally, for bio-mediated soil improvement.

• 한국수자원학회:학술대회논문집
• /
• 한국수자원학회 2006년도 학술발표회 논문집
• /
• pp.51-56
• /
• 2006

Biases embedded in numerical weather precipitation forecasts by the RDAPS model was determined, quantified and corrected. The ultimate objective is to eventually enhance the reliability of reservoir operation by Korean Water Resources Corporation (KOWACO), which is based on precipitation-driven forecasts of stream flow. Statistical post-processing, so called MOS (Model Output Statistics) was applied to RDAPS to improve their performance. The Artificial Neural Nwetwork (ANN) model was applied for 4 cases of 'Probability of Precipitation (PoP) for wet and dry season' and 'Quantitative Precipitation Forecasts (QPF) for wet and dry season'. The reduction on the large systematic bias was especially remarkable. The performance of both networks may be improved by retraining, probably every month. In addition, it is expected that performance of the networks will improve once atmospheric profile data are incorporated in the analysis. The key to the optimal performance of ANN is to have a large data set relevant to the predictand variable. The more complex the process to be modeled by the ANN, the larger the data set needs to be.

• 한국습지학회지
• /
• 제25권3호
• /
• pp.167-175
• /
• 2023

강우 데이터는 습지관리, 수문모의, 수자원 관리와 같은 다양한 분야에서 활용되는 필수 입력자료 중 하나이다. 강우 데이터를 활용하여 효율적인 수자원관리를 위해서는 기본적으로 데이터의 결측률을 최소화 시킴으로써 최대한 많은 데이터를 확보하는 것이 필수적이다. 또한 미계측 지역에 대한 강우 데이터를 확보한다면 보다 효율적인 수문모의가 가능하다. 그러나 결측 강우 데이터는 주로 통계학적 기법에 의해 추정되어 왔다. 본 연구의 목적은 데이터 간의 상관관계를 기반으로 새로운 데이터를 예측할 수 있는 머신러닝 알고리즘을 활용하여 결측 강우 데이터를 복원할 수 있는 새로운 방법을 제안하고자 한다. 또한, 기존의 통계적 방법들과 비교하여 머신러닝 기법의 결측 강우 데이터 복원을 위한 활용가치를 평가하고자 한다. 평가를 위해 대표적인 머신러닝 알고리즘인 Artificial Neural Network (ANN)과 Random Forest (RF)을 적용하였다. 강우의 발생 유무를 분류하는 성능은 RF 알고리즘이 ANN 알고리즘보다 강우 발생유무의 분류 정확도가 높은 것으로 나타났다. 분류 모형의 평가 지표인 F1-score나 Accuracy값이 RF는 0.80, 0.77인 반면에, ANN은 0.76, 0.71로 계산되었다. 또한 강우량을 추정하는 성능 역시 RF가 ANN 알고리즘보다 보다 높은 정확도를 보였다. RF과 ANN 알고리즘의 RMSE은 2.8mm/day과 2.9mm/day이고, R²값은 0.73, 0.68으로 계산되었다.

• 한국수자원학회:학술대회논문집
• /
• 한국수자원학회 2022년도 학술발표회
• /
• pp.330-330
• /
• 2022

우리나라에서 발생하는 기상 재해 현상은 주로 태풍, 집중호우, 장마 등 인명 및 경제적인 피해가 크며, 단기간에 국지적으로 나타난다. 현재 재해 감시 및 예보는 주로 종관기상관측체계를 이용하고 있다. 하지만, 우리나라의 복잡한 지형, 인구 밀집 지형, 관측 시기가 일정하지 않은 지형과 같은 조건에서 미계측 자료 및 지역이 다수 존재 때문에 강수의 공간 분포와 강도에 대한 정밀한 정보를 제공하지 못하는 실정이다. 최근 광범위한 관측영역과 공간 분해능의 개선, 자료추출 알고리즘의 개발로 전세계적으로 위성영상 기반 기상관측 자료의 활용성이 증대되고 있다. 본 연구에서는 한반도 지역의 지상 관측데이터와 전지구 격자형 위성 강우자료를 비교하여 한반도의 적용성을 분석하고자 한다. 다양한 위성영상 기반 기상자료인 Climate Hazards Groups InfraRed Precipitation with Station (CHIRPS), Precipitation Estimation From Remotely Sensed Information Using Artificial Neural Networks-Climate Data Record (PERSIANN-CDR), Global Precipitation Climatology Centre (GPCC), Precipitation Estimation From Remotely Sensed Information Using Artificial Neural Networks-Cloud Classification System (PERSIANN-CCS) 4개의 강우위성영상을 수집하여, 1991년부터 2020년까지 30년 데이터를 활용하였다. 강수량 변동성 비교를 위하여 기상청의 종관기상관측장비 (Automated Synoptic Observation System, ASOS), 자동기상관측시설 (Automatic Weather System, AWS) 데이터와 상관 분석을 수행하고, 강우위성영상의 국내 적합성을 판단하고자 한다.

• 한국재난정보학회 논문집
• /
• 제17권2호
• /
• pp.329-340
• /
• 2021

연구목적: 본 연구는 인공신경망 라이브러리 기술을 이용하여, 기상 데이터 변화 예측을 통한 한반도 가뭄 취약지역 분석을 목적으로 하였다. 연구방법: 연구지역 중 북한 지역의 다양한 기상데이터의 확보가 힘든 특수성을 고려하여 연구지역의 월별 누적강수량 데이터를 활용하였으며, 통계프로그램 R을 이용하여 인공신경망 알고리즘을 통한 기상데이터 추정을 수행하였다. 연구결과: 본 논문에서 진행한 연구 결과, 실제 데이터와 예측 데이터 간의 상관계수 값은 인공신경망 알고리즘을 활용한 결과가 회귀분석 결과보다 평균 0.043879 더 높은 것으로 확인되었다. 결론: 연구의 결과는 가뭄 대응을 위한 재난대응 기초 연구 자료로 활용 가능할 것으로 기대한다.

• 한국지구과학회지
• /
• 제31권5호
• /
• pp.465-474
• /
• 2010

Real-time rainfall monitoring is of great practical importance over the highly populated Indochina area, which is prone to natural disasters, in particular in association with rainfall. With the goal of d etermining near real-time half-hourlyrain estimates from satellite, the three-layer, artificial neural networks (ANN) approach was used to train the brightness temperatures at 6.7, 11, and $12-{\mu}m$ channels of the Japanese geostationary satellite MTSAT against passive microwavebased rain rates from Tropical Rainfall Measuring Mission (TRMM) Microwave Imager (TMI) and TRMM Precipitation Radar (PR) data for the June-September 2005 period. The developed model was applied to the MTSAT data for the June-September 2006 period. The results demonstrate that the developed algorithm is comparable to the PERSIANN (Precipitation Estimation from Remotely Sensed Information using Artificial Neural Networks) results and can be used for flood monitoring across the Indochina area on a half-hourly time scale.

• 한국수자원학회:학술대회논문집
• /
• 한국수자원학회 2020년도 학술발표회
• /
• pp.120-120
• /
• 2020

Spatial precipitation data is one of the essential components in modeling hydrological problems. The estimation of these data has achieved significant achievements own to the recent advances in remote sensing technology. However, there are still gaps between the satellite-derived rainfall data and observed data due to the significant dependence of rainfall on spatial and temporal characteristics. An effective approach based on the Convolutional Neural Network (CNN) model to correct the satellite-derived rainfall data is proposed in this study. The Mekong River basin, one of the largest river system in the world, was selected as a case study. The two gridded precipitation data sets with a spatial resolution of 0.25 degrees used in the CNN model are APHRODITE (Asian Precipitation - Highly-Resolved Observational Data Integration Towards Evaluation) and PERSIANN-CDR (Precipitation Estimation from Remotely Sensed Information using Artificial Neural Networks). In particular, PERSIANN-CDR data is exploited as satellite-based precipitation data and APHRODITE data is considered as observed rainfall data. In addition to developing a CNN model to correct the satellite-based rain data, another statistical method based on standard deviations for precipitation bias correction was also mentioned in this study. Estimated results indicate that the CNN model illustrates better performance both in spatial and temporal correlation when compared to the standard deviation method. The finding of this study indicated that the CNN model could produce reliable estimates for the gridded precipitation bias correction problem.