• Journal of the Korean Geotechnical Society
• /
• v.25 no.5
• /
• pp.53-64
• /
• 2009

Many slope failures are induced by rainfall infiltration. A lot of recent researches are therefore focused on rainfall-induced slope instability and the rainfall infiltration is recognized as the important triggering factor. The rainfall infiltrates into the soil slope and makes the matric suction lost in the slope and even the positive pore water pressure develops near the surface of the slope. They decrease the resisting shear strength. In Korea, a few public institutions suggested conservative slope design guidelines that assume a fully saturated soil condition. However, this assumption is irrelevant and sometimes soil properties are misused in the slope design method to fulfill the requirement. In this study, a more relevant slope stability evaluation method is suggested to take into account the real rainfall infiltration phenomenon. Unsaturated soil properties such as shear strength, soil-water characteristic curve and permeability for Korean weathered soils were obtained by laboratory tests and also estimated by artificial neural network models. For real-time assessment of slope instability, failure warning criteria of slope based on deterministic and probabilistic analyses were introduced to complement uncertainties of field measurement data. The slope stability evaluation technique can be combined with field measurement data of important factors, such as matric suction and water content, to develop an early warning system for probably unstable slopes due to the rainfall.

• Journal of Forest and Environmental Science
• /
• v.19 no.1
• /
• pp.1-11
• /
• 2003

The effects that the geo-textile mulching sheet has influenced on the runoff-water, suspended solid, sediment yield and vegetation growth are as follows in artificial slope 1. The flora of plots was composed 12 families, 21 genera, 20 species, 2 varieties, total 22 taxa. 2. The geo-textile mulching sheet is effective on increasing of introduced vegetation population, number of species and vegetation coverage, but just only with the mulching sheet it shows limit of was somewhat difficult to expect the increase of the existence ratio. 3. The amount of runoff-water increased in proportion to rainfall and at mulched plots were about 1/15.5 as decreased as that of un-mulched plots. 4. The amount of suspended sediment increased in proportion to rainfall and at mulched plots were about 1/47 as decreased as that of un-mulched plots. 5. Also, the amount of sediment yield increased in proportion to rainfall and at mulched plots were about 1/151 as decreased as that of un-mulched plots. so, multi-function- filter is very effective on prevention of soil erosion.

• Journal of Wetlands Research
• /
• v.20 no.1
• /
• pp.54-62
• /
• 2018

Nutrients generated from various land uses lead to eutrophication during the influx of water, and it is necessary to apply the LID techniques to reduce nutrients from nonpoint sources in order to mitigate the occurrence of the algal bloom. This study was carried out to derive the design factors of hybrid artificial wetland (HCW) to increase the removal efficiency of nutrients. HCW system was constructed in the year 2010 for the treatment of rainfall runoffs from parking lots and roads composed of 100% impervious floors in the Cheonan campus of Kongju University. The average nutrients removal efficiency of TN and TP was 74% and 72%, respectively. Both TN and TP removal efficiencies were higher than those of free surface wetlands and subsurface flow wetlands due to activated physical and ecological mechanisms. The critical design parameters for the efficient nutrients removal in the artificial wetlands were the ratio of the surface area to the catchment area (SA/CA), land use, the rainfall runoff, and the rainfall intensity. The optimal carbon to nitrogen (C/N) ratio was estimated at 5: 1 to 10.3: 1. The results of this study can be applied to the efficient design of hybrid artificial wetlands to treat nutrients in urban runoff with high efficiency.

• Journal of Korea Water Resources Association
• /
• v.57 no.2
• /
• pp.127-137
• /
• 2024

Physical models, which are often used for water resource management, are difficult to build and operate with input data and may involve the subjective views of users. In recent years, research using data-driven models such as machine learning has been actively conducted to compensate for these problems in the field of water resources, and in this study, an artificial neural network was used to simulate long-term rainfall runoff in the Osipcheon watershed in Samcheok-si, Gangwon-do. For this purpose, three input data groups (meteorological observations, daily precipitation and potential evapotranspiration, and daily precipitation - potential evapotranspiration) were constructed from meteorological data, and the results of training the LSTM (Long Short-term Memory) artificial neural network model were compared and analyzed. As a result, the performance of LSTM-Model 1 using only meteorological observations was the highest, and six LSTM-MLP ensemble models with MLP artificial neural networks were built to simulate long-term runoff in the Fifty Thousand Watershed. The comparison between the LSTM and LSTM-MLP models showed that both models had generally similar results, but the MAE, MSE, and RMSE of LSTM-MLP were reduced compared to LSTM, especially in the low-flow part. As the results of LSTM-MLP show an improvement in the low-flow part, it is judged that in the future, in addition to the LSTM-MLP model, various ensemble models such as CNN can be used to build physical models and create sulfur curves in large basins that take a long time to run and unmeasured basins that lack input data.

• The Journal of Engineering Geology
• /
• v.23 no.2
• /
• pp.137-147
• /
• 2013

For the effective management of groundwater resources, it is necessary to predict groundwater level fluctuations in response to rainfall events. In the present study, time series models using artificial neural networks (ANNs) and support vector machines (SVMs) have been developed and applied to groundwater level data from the Gasan, Shingwang, and Cheongseong stations of the National Groundwater Monitoring Network. We designed four types of model according to input structure and compared their performances. The results show that the rainfall input model is not effective, especially for the prediction of groundwater recession behavior; however, the rainfall-groundwater input model is effective for the entire prediction stage, yielding a high model accuracy. Recursive prediction models were also effective, yielding correlation coefficients of 0.75-0.95 with observed values. The prediction errors were highest for Shingwang station, where the cross-correlation coefficient is lowest among the stations. Overall, the model performance of SVM models was slightly higher than that of ANN models for all cases. Assessment of the model parameter uncertainty of the recursive prediction models, using the ratio of errors in the validation stage to that in the calibration stage, showed that the range of the ratio is much narrower for the SVM models than for the ANN models, which implies that the SVM models are more stable and effective for the present case studies.

• Proceedings of the Korean Society of Agricultural Engineers Conference
• /
• 2002.10a
• /
• pp.277-280
• /
• 2002

An artificial neural network model was developed to analyze and forecast real time river runoff from the Naju watershed, in Korea. Model forecasts are very accurate (i.e., relative error is less than 3% and $R^2$ is great than 0.99) for calibration data sets. Increasing the time horizon for validation data sets, thus making the model suitable for flood forecasting, decreases the accuracy of the model. The resulting optimal EBPN models for forecasting real time runoff consists of ten rainfall and four and ten runoff data (ANN0410 and ANN1010 models). Performances of the ANN0410 and ANN1010 models remain satisfactory up to 6 hours (i.e., $R^2$ is great than 0.92).

• Magazine of the Korean Society of Agricultural Engineers
• /
• v.45 no.1
• /
• pp.102-114
• /
• 2003

The objectives of the paper are to evaluate cell based pollutant loadings for different storm events, to monitor the hydrology and water quality of the Baran HP#6 watershed, and to validate AGNPS with the field data. Simplification was made to AGNPS in estimating storm erosivity factors from a triangular rainfall distribution. GIS-AGNPS interface model consists of three subsystems; the input data processor based on a geographic information system. the models. and the post processor Land use patten at the tested watershed was classified from the Landsat TM data using the artificial neural network model that adopts an error back propagation algorithm. AGNPS model parameters were obtained from the GIS databases, and additional parameters calibrated with field data. It was then tested with ungauged conditions. The simulated runoff was reasonably in good agreement as compared with the observed data. And simulated water quality parameters appear to be reasonably comparable to the field data.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2010.05a
• /
• pp.1269-1273
• /
• 2010

이러한 강우자료의 결측값이나 오자료를 보정하는 것은 그 유역의 정확한 수문학적 특성 파악 및 안전한 수공구조물의 설계에 영향을 미치게 되므로 매우 중요하다고 할 수 있다. 최근 이러한 강우자료를 비선형적 모델인 인공신경망(Artificial Neural Network)을 이용하여 보정하는 연구가 활발히 진행되고 있다(오재우 등, 2008). 그러나 이러한 인공신경망을 적용하는 경우, 선택한 신경망 구조의 형태와 학습(training)을 위해 사용되는 자료가 전체 자료의 특성을 반영하고 있는 정도에 따라 정확도에 차이를 보인다(한광희 등, 2010). 따라서 자료보정을 위한 입력 자료의 선택은 인공신경망을 이용한 결측치 보정의 중요한 과정이다. 본 연구에서는 이러한 입력 자료의 선택을 위한 여러 가지 기법 중 입력 변수간의 상호정보량 (Mutual Information)을 이용한 방법을 적용하여 대상 결측 지점을 보정할 강우지점을 선별한 후 선택된 지점만으로 인공신경망을 구성하여 강우자료를 보정하고 주변 자료를 모두 이용한 결과와 상관성분석으로 얻어진 결과와 비교하였다.

• Journal of the Korean Geotechnical Society
• /
• v.22 no.7
• /
• pp.55-64
• /
• 2006

Shallow failures of slopes in weathered soils are caused by infiltration caused by prolonged rainfall. These failures are mainly triggered by the deepening of the wetting band accompanied by a decrease in suction induced by the water infiltration. In this paper, hysteresis on soil-water characteristic curve (SWCC) of granite and gneiss weathered soils is investigated using transient flow analysis respectively. Each case was subjected to artificial rainfall intensities and time duration depending on the laboratory-based drying and wetting processes. The results show that the unsaturated seepage on weathered slopes are very much affected by the initial suction of soils and unsaturated permeability of the soils. In addition, a granite weathered soil has a lower air-entry value, residual matric suction, and wetting front suction and less hysteresis loop than a gneiss weathered soil.

• The Journal of Engineering Geology
• /
• v.27 no.4
• /
• pp.475-487
• /
• 2017

We performed landslide flume tests to analyze characteristics of landslide occurrence and change in the ground materials due to rainfall infiltration. The test apparatus is composed of flume, rainfall simulator, and measurement sensors and landslides were triggered by heavy rainfall (Intensity=200 mm/hr) sprinkled at the above of an artificial slope. The measurement sensors for matric suction and volumetric water content were installed with 3 sets at shallow (GL-0.2 m), middle (GL-0.4 m), and deep depth (GL-0.6 m) in the slope and the tests were performed with in-situ, loose, and dense condition of each weathered soils of granite, gneiss, and mudstone. The analyses show that surface erosion was dominant in initial time of the test due to heavy rainfall and then landslides occur following locally happened transverse tension cracks. The characteristics of landslide were both shallow failure because of a spread of wetting front induced by the rainfall infiltration and retrogressive failure. While the matric suction was decreased rapidly without any precursor in the soil saturation, the volumetric water content was increased gradually, reached its maximum value, and then decreased rapidly with landslide.