• Journal of Wetlands Research
• /
• v.19 no.3
• /
• pp.366-374
• /
• 2017

The objective of this study is to explore the applicability of very short-range-forecast rainfall for the early warning of mud-debris flows. An artificial neural network was applied to use the very short-range-forecast rainfall data. The neural network is learned by using the relationship between the radar and the AWS, and forecasted rainfall is estimated by replacing the radar rainfall with the MAPLE data as the very short-range-forecast rainfall data. The applicability of forecasted rainfall by the MAPLE was compared with the AWS rainfall at the test-bed using the rainfall criteria for cumulative rainfall of 6hr, 12hr, and 24hr respectively. As a result, it was confirmed that forecasted rainfall using the MAPLE can be issued prior to the AWS warning.

• Journal of Environmental Science International
• /
• v.30 no.12
• /
• pp.1101-1111
• /
• 2021

In this study, among the W-S-R(Wiper-Signal-Rainfall) relationship methods used to produce sensor-based rain information in real time, we sought to produce actual rainfall information by applying machine learning techniques to account for the effects of wiper operation. To this end, we used the gradient descent and threshold map methods for pre-processing the cumulative value of the difference before and after wiper operation by utilizing four sensitive channels for optical sensors which collected rain sensor data produced by five rain conditions in indoor artificial rainfall experiments. These methods produced rainfall information by calculating the average value of the threshold according to the rainfall conditions and channels, creating a threshold map corresponding to the 4 (channel) × 5 (considering rainfall information) grid and applying Optima Rainfall Intensity among the big data processing techniques. To verify these proposed results, the application was evaluated by comparing rainfall observations.

• KOREAN JOURNAL OF CROP SCIENCE
• /
• v.41 no.2
• /
• pp.131-138
• /
• 1996

Soil crusting and hardening as a result of drying after rainfall were examined in relation to seedling emergence by employing five rice varieties (Italiconaverneco, Dadazo, and Galsaekggarakshare, Dongjinbyeo and Sumjinbyeo) and two barnyardgrass species (E. crus-gallj var. oryzjcola and E. crus-galli var. praticola). Sandy loam, loam, and silty loam soils were used. The artificial rainfall of 0, 20 and 40mm were applied after sowing and covering with 4cm soil. Air temperature and solar radiation averaged over 9 days after seeding was 31.3$^{\circ}C$ and 16.9MJ /m$^2$, respectively. Soil strength increased rapidly by drying after artificial rainfall, being greater in soils with greater amount of clay and artificial rainfall. Soil crust was formed on the surface with artificial rainfall in all soils tested. However, soil crust was exfoliated in silty loam and loam soil, and lifted as seedlings emerge. Seedling emergence of rice varieties was decreased by rainfall treatments. Sumjinbyeo and Dongjinbyeo showed much poorer seedling emergence especially in sandy loam soil than the other varieties. Poor seedling emergence of these varieties might have been caused by delayed seedling emergence which had made them expose to greater soil strength. Seedling emergence of barnyardgrasses showed no differences among soil textures and rainfall treatments, because they emerged rapidly before soil crusting and hardening were proceeded enough to hamper seedling emergence. Seedling emergence of Sumjinbyeo and Dongjinbyeo decreased with increasing soil strength averaged over 3 days to 5 days after seeding, being lowered to 80% at soil strength of 1.0kg/cm$^2$ and to 50% at 1.7kg/cm$^2$. Emergence speed of barnyardgrasses was faster than rice varieties, and E. crus-galli var. oryzjcola than E. crus-galli var. praticola. Italiconaverneco and Dadazo showed faster emergence in rice varieties. Galsaekggarakshare showed slower emergence speed than these two varieties with similar seedling emergence percentage. The greater and faster elongations of mesocotyl and incomplete leaf in rice, and of mesocotyl in barnyardgrass were the characteristics responsible for higher seedling emergence rate in the environment examined.

• Proceedings of the Korean Geotechical Society Conference
• /
• 2006.03a
• /
• pp.28-33
• /
• 2006

Shallow failures of slopes in weathered soils are caused by infiltration due to 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 are 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.

• Proceedings of the IEEK Conference
• /
• 2002.07a
• /
• pp.262-264
• /
• 2002

The characteristic features of Malaysia's climate is has stable temperature, with high humidity and copious rainfall. Weather forecasting is an important task in Malaysia as it could affetcs man irrespective of mans job, lifestyle and activities especially in the agriculture. In Malaysia, numerical method is the common used method to forecast weather which involves a complex of mathematical computing. The models used in forecasting are supplied by other counties such as Europe and Japan. The goal of this project is to forecast weather using another technology known as artificial neural network. This system is capable to learn the pattern of rainfall in order to produce a precise forecasting result. The supervised learning technique is used in the loaming process.

• Magazine of the Korean Society of Agricultural Engineers
• /
• v.43 no.2
• /
• pp.69-77
• /
• 2001

An artificial neural network model was developed to analyze and forecast daily steamflow flow a small watershed. Error Back propagation neural networks (EBPN) of daily rainfall and runoff data were found to have a high performance in simulating stremflow. The model adopts a gradient descent method where the momentum and adaptive learning rate concepts were employed to minimize local minima value problems and speed up the convergence of EBP method. The number of hidden nodes was optimized using Bayesian information criterion. The resulting optimal EBPN model for forecasting daily streamflow consists of three rainfall and four runoff data (Model34), and the best number of the hidden nodes were found to be 13. The proposed model simulates the daily streamflow satisfactorily by comparison compared to the observed data at the HS#3 watershed of the Baran watershed project, which is 391.8 ha and has relatively steep topography and complex land use.

• Proceedings of the Korean Geotechical Society Conference
• /
• 2010.03a
• /
• pp.1294-1301
• /
• 2010

This study is an experimental research for the dispersion behavior and impact characteristics of debris flow according to change of slope. Large scale experimental setup for the debris flow was established to simulate the artificial rainfall and control the ground slope. Parameters such as materials of debris flow, slope, and length of slope were used for the experiments. After the experiments, it was found that the speed of ground material components was increased about 28~47%. It was found that speed can be increased by increasing the particle size. Furthermore, maximum/final loads for ground material components were increased 89% for the coarse aggregate and 68% for the fine aggregate comparing with sand.

• Proceedings of the Korean Radioactive Waste Society Conference
• /
• 2003.11a
• /
• pp.306-314
• /
• 2003

Engineered barrier test facility is specially designed to demonstrate the performance of engineered barrier system for the near-surface disposal facility under the domestic environmental conditions. Comprehensive measurement systems for the water content, temperature, matric potential are installed within each test cell. In this study, short-term monitoring of the behavior of multi-layered cover system is implemented with artificial rainfall system. The periodic measurement data are collected and analyzed by a dedicated database management system, and provide a basis for performance verification of the disposal cover design.

• The Journal of Engineering Geology
• /
• v.32 no.2
• /
• pp.209-219
• /
• 2022

To experimentally investigate the variation of soil characteristics in slope during rainfall and the shape of slope failure, the model test was performed using soil box and artificial rainfall simulator. The model test of slope formed by the homogenous sand was performed, and the saturation pattern in the model slope due to rainfall infiltration was observed. The slope model with the inclination of 35° was set up on the slope of 30°, and the rainfall intensity of 50 mm/hr was applied in the test. The soil depth of 35 cm was selected by considering the size of soil box, and the TDR (time domain reflectometry) sensors were installed at various depths to investigate the change of soil characteristics with time. As the result of model test, the slope model during rainfall was saturated from the soil surface to the subsurface, and from the toe part to the crest part due to rainfall infiltration. That is, the toe part of slope was firstly saturated by rainfall infiltration, and then due to continuous rainfall the saturation range was enlarged from the toe part to the crest part in the slope model. The failure of slope model was started at the toe part of slope and then enlarged to the crest part, which is called as the retrogressive failure. At the end of slope failure, the collapsed area increased rapidly. Also, the mode of slope failure was rotational. Meanwhile, the slope failure was occurred when the matric suction in the slope was reached to the air entry value (AEV) estimated in soil-water characteristic curve (SWCC).

• Journal of the Korean Society of Hazard Mitigation
• /
• v.7 no.4
• /
• pp.85-95
• /
• 2007

The variation of hydraulic and hydrologic aspect of urban area according to the strongly seasonal variation of rainfall and the increment of urbanization has caused the runoff variation and increased the flood damage, and thus made a difficulty to manage water resources in urban area. Recently, as a part of efforts to resolve these problems, the facilities for reducing runoff increasing due to urbanization have a tendency to install in our country. In this study, more effective Infiltration-Storage System(ISS) is proposed and its reducing effect is analyzed by hydraulic experimental study. The infiltration characteristics of runoff reduction facilities are examined as varying artificial rainfall and a material of infiltration layers being able to consider the influence of urban development. As a result of comparison of infiltration rate of the upper and lower parts, the infiltration rate in the lower part is larger than that of the upper part. Thus, the ISS is more available than existing runoff reduction facilities. Results obtained in this study can be provided fundamental data for improvement of existing runoff reduction facilities and practical use of ISS.