• 한국농공학회논문집
• /
• 제49권3호
• /
• pp.21-31
• /
• 2007

This study is aimed at the development of a runoff forecasting model by using the Fuzzy inference system and Neural Network model to solve the uncertainties occurring in the process of rainfall-runoff modeling and improve the modeling accuracy of the stream runoff forecasting. The Neuro-Fuzzy (NF) model were used in this study. The NF model, recently received a great deal of attention, improve the existing Neural Networks by the aid of the Fuzzy theory applied to each node. The study area is the downstreams of Naeseung-chun. Therefore, time-dependent data was obtained from the Wolpo water level gauging station. 11 and 2 out of total 13 flood events were selected for the training and testing set of model respectively. The schematic diagram method and the statistical analysis are conducted to evaluate the feasibility of rainfall-runoff modeling. The model accuracy was rapidly decreased as the forecasting time became longer. The NF model can give accurate runoff forecasts up to 4 hours ahead in standard above the Determination coefficient $(R^2)$ 0.7. In the comparison of the runoff forecasting using the NF and TANK models, characteristics of peak runoff in the TANK model was higher than ones in the NF models, but peak values of hydrograph in the NF models were similar.

• 한국환경과학회지
• /
• 제24권1호
• /
• pp.133-150
• /
• 2015

Wind profiler provides vertical profiles of three-dimensional wind vectors with high spatiotemporal resolution. The wind vectors is useful to analyze severe weather phenomena and to validate the various products from numerical weather prediction model. However, the wind measurements are not immune to ground clutter, bird, insect, and aircraft. Therefore, quality of wind vectors from wind profiler must be quantitatively evaluated prior to its application. In this study, wind vectors from UHF wind profiler at Ganwon Regional Meteorological Administration was quantitatively evaluated using 27 radiosonde measurements that were launched every two or three hours according to rainfall intensity during Intensive Observation Period (IOP) from June to July 2013. In comparison between two measurements, wind vectors from wind profiler was relatively underestimated. In addition, the accuracy and quality of wind vectors from wind profiler decrease with increasing beam height. The accuracy and quality of the wind vectors for rainy periods during IOP were higher than for the clear-air measurements. The moderate rainfall intensity lead to multi-peaks in Doppler spectrum. It results in overestimation of vertical air motion, whereas wind vectors from wind profilers shows good agreement with those from radiosonde measurements for light rainfall intensity.

• Environmental Engineering Research
• /
• 제15권2호
• /
• pp.123-126
• /
• 2010

Modeling non-point pollution across multiple scales has become an important environmental issue. As a more representative and practical approach in quantifying and qualifying surface water, a modular neural network (MNN) was implemented in this study. Two different site-scales ($1.5\;{\times}\;10^5$ and $1.62\;{\times}\;10^6\;m^2$) with the same plants, soils, and paddy field management practices, were selected. Hydrologic data (rainfall, irrigation and surface discharge) and water quality data (time-series nutrient loadings) were continuously monitored and then used for the verification of MNN performance. Correlation coefficients (R) for the results predicted from the networks versus measured values were within the range of 0.41 to 0.95. The small block could be extrapolated to the large field for the rainfall-surface drainage process. Nutrient prediction produced less favorable results due to the complex phenomena of nutrients in the drainage water. However, the feasibility of using MNN to generate improved prediction accuracy was demonstrated if more hydrologic and environmental data are provided. The study findings confirmed the estimation accuracy of the upscaling from a small-segment block to large-scale paddy field, thereby contributing to the establishment of water quality management for sustainable agriculture.

• 한국수자원학회:학술대회논문집
• /
• 한국수자원학회 2015년도 학술발표회
• /
• pp.398-398
• /
• 2015

To estimate and forecast runoff by using Aritifitial Neaural Networks model (ANNs). it has been studied in Thailand for the past 10 years. The model was developed in order to be conformed with the conditions in which the collected dataset is short and the amount of dataset is inadequate. Every year, the Northerpart of Thailand faces river overflow and flood inundation. The most important basin in this area is Yom basin. The purpose of this study is to forecast runoff at Y.14 gauge station (Si-Satchanalai district, Sukhothai province) for 3 days in advance. This station located at the upstream area of Yom River basin. Daily rainfall and daily runoff from Royal Irrigation Department and Meteorological Department during flood period 2000-2012 were used as input data. In order to check an accuracy of forecasting, forecasted runoff were compared with observed data by pursuing Nash Sutcliffe Efficiency (NSE) and Coefficient of Determination ($R^2$). The result of the first day gets the highest accuracy and then decreased in day 2 and day 3, consequently. NSE and $R^2$ values for frist day of runoff forecasting is 0.76 and 0.776, respectively. On the second day, those values are 0.61 and 0.65, respectively. For the third day, the aforementioned valves are 0.51 and 0.52, respectively. The results confirmed that the ANNs model can be used when the range of collected dataset is short and insufficient. In conclusion, the ANNs model is suitable for applying during flood incident because it is easy to use and does not require numerous parameters for simulating.

• 한국수자원학회:학술대회논문집
• /
• 한국수자원학회 2023년도 학술발표회
• /
• pp.164-164
• /
• 2023

This study investigates the importance of flood-influencing factors on the accuracy of flood risk mapping using the integration of remote sensing-based and machine learning techniques. Here, the Extreme Gradient Boosting (XGBoost) and Random Forest (RF) algorithms integrated with GIS-based techniques were considered to develop and generate flood risk maps. For the study area of NAPA County in the United States, rainfall data from the 12 stations, Sentinel-1 SAR, and Sentinel-2 optical images were applied to extract 13 flood-influencing factors including altitude, aspect, slope, topographic wetness index, normalized difference vegetation index, stream power index, sediment transport index, land use/land cover, terrain roughness index, distance from the river, soil, rainfall, and geology. These 13 raster maps were used as input data for the XGBoost and RF algorithms for modeling flood-prone areas using ArcGIS, Python, and R. As results, it indicates that XGBoost showed better performance than RF in modeling flood-prone areas with an ROC of 97.45%, Kappa of 93.65%, and accuracy score of 96.83% compared to RF's 82.21%, 70.54%, and 88%, respectively. In conclusion, XGBoost is more efficient than RF for flood risk mapping and can be potentially utilized for flood mitigation strategies. It should be noted that all flood influencing factors had a positive effect, but altitude, slope, and rainfall were the most influential features in modeling flood risk maps using XGBoost.

• 농업과학연구
• /
• 제51권1호
• /
• pp.79-86
• /
• 2024

As the frequency and intensity of heavy rains increase, the vulnerability of agriculture to disasters also increases. Consequently, there is a need to improve flood and inundation predictions. To enhance the accuracy of inundation predictions, it is essential to monitor water level and discharge data within agricultural areas. This study was conducted to monitor water levels and rainfall in the Cheongju Sindae area from 2022 to 2023, and the data was utilized as input and validation data for agricultural inundation modeling. Four irrigation drainage canals were installed to a square-shaped concrete structure where the water level gauge is. It was then confirmed that the water level rises with rainfall. The flow velocities were monitored during periods of heavy rainfall. The rating curve, which estimates water level and flow velocity based on observations, was estimated using the software K-HQ. The resulting curve was presented with the Coefficient of Determination (R²). K-HQ was also used to calculate the equation for the rating curve, taking outliers into account at each data point. Outliers were extracted and the rating curve was recalculated. As the coefficient of determination of three out of four stations exceeded 0.95, the estimated rating curve may be considered reliable for discharge estimation. This study provides critical data for enhancing agricultural inundation modeling accuracy and drainage improvement projects.

• 한국수자원학회논문집
• /
• 제48권11호
• /
• pp.937-944
• /
• 2015

본 연구에서는 실측자료를 기반으로 한 새로운 면적강우량 산정기법인 '레이더 폴리곤 기법(Radar polygon Method, PRM)'을제시하였다. RPM은(1) 강우공간분포의 실측자료인 기상레이더 자료를 이용하여 지점관측소가 위치한 곳에서의 강우강도와 주변지역의 강우강도를 비교하여 유사강우 발생지도 작성; (2) 위의 단계를 관측소별로 반복하여 각 관측소별 유사강우 발생 확률 지도 작성; (3) 주어진 격자에서의 각 관측소의 유사강우 발생 확률의 비교를 통한 지배범위 결정의 알고리즘으로 관측소별 가중치를 결정하는 방법이다. RPM 방법을 안성천 유역에 적용하여 Thiessen법과 결과를 비교하였다. 안성천 유역의 경우 RPM과 Thiessen방법에 근거한 다각형의 공간적 형태는 관측소 위치의 강우 특성에 따라 차이를 보였으나 관측소별 가중치 값의 차이는 크지 않았다. 본 연구는 관측기간 및 정확도의 문제로 인하여 제한적으로 활용되어 온 레이더 강우관측자료의 새로운 활용분야를 개척하였다는 점에서 큰 의미를 찾을 수 있다.

• 한국지리정보학회지
• /
• 제23권3호
• /
• pp.208-219
• /
• 2020

본 연구는 위성강수에 대한 정확도를 비교함으로써 미계측 혹은 비접근 지역에 대한 적용성을 판단하는 것을 목적으로 하고 있다. 정확도 평가 결과 전체적인 강수의 공간분포는 세 개의 이벤트 모두 지상계측강우와 위성강수가 유사한 것으로 분석되었다. 1개월간의 강수의 경우 지상계측강수(ASOS)와 위성강수의 1시간의 시간해상도에서 상관계수는 0.42~0.46정도로 분석되었다. 강수가 집중된 기간에 대한 평가에서 1시간의 시간해상도에 대한 상관계수가 IMERG는 0.55~0.66, GSMaP는 0.56~0.67로 분석되었다. 세 개의 이벤트에 대한 관측소별 총강우의 분석결과 상관계수는 IMERG와 GSMaP이 CMORPH 보다 상대적으로 우수한 것으로 분석되었고, 바이어스는 상대적으로 CMORPH가 우수한 것으로 분석되었다. 그러나 3개 위성강수 모두 지상계측강수와 비교하여 과소하게 추정되고 있는 것으로 분석되었다. 향후에는 본 연구를 통해 얻어진 결과를 반영하여 북한을 포함한 한반도 전체에 대한 강수량을 추정하는 연구를 수행할 계획이다.

• 한국수자원학회논문집
• /
• 제41권7호
• /
• pp.681-692
• /
• 2008

본 연구에서는 자료동화 기법의 가장 간단한 방법이라 할 수 있는 연속수정법(successive correction method)을 이용한 레이더 강우자료와 지상 강우자료의 합성방법에 대한 적용성을 검토하였다. 우선 연속수정법의 적용 시 고려해야 할 사항인 반복계산 횟수 및 영향 반경의 규모를 민감도 분석을 통해 결정하였다. 또한 자료 합성에 대한 정량적인 평가를 위해 밀도 있는 지상 강우자료를 공간분포시켜 실제 강우장을 가정하였다. 최근 자료 합성에 많이 이용되고 있는 co-Kriging을 이용하여 두 자료를 합성하여 연속수정법에 의한 자료 합성 결과를 정량적으로 분석하였다. 그 결과 간단하고 경제적인 자료동화 기법인 연속수정법으로도 co-Kriging을 이용하는 경우의 통계적 특성 및 정확도를 확보할 수 있다는 것을 알 수 있었다.

• 지질공학
• /
• 제20권1호
• /
• pp.61-70
• /
• 2010

지하수위 변동법을 이용하여 지하수 함양량을 추정할 경우 매질의 비산출율은 결과에 대한 오차에 직접 영향을 미치게 되나 비산출율의 추정 방법에 대한 고찰은 거의 이루어지지 않았다. 장기 지하수위 관측이 이루어지는 연구지점에서 강우 발생 후 지하수위의 상승량의 상관관계로부터 비산출율을 추정한 결과 타 방법과 유사한 결과를 얻을 수 있었다. 그러나, 지하수위 변동이 강우에 의해서만 나타나는 것은 아니므로 인위적인 지하수위 변동, 식생에 의한 증발산 및 지하수위의 급상승 등이 배제된 자료를 활용하여야 하며, 갈수기의 12시간 내지 24시간 단위의 평균 강우 및 지하수위 자료를 사용하는 것이 합리적인 비산출율 산정에 바람직한 것으로 나타났다.