• Journal of The Korean Society of Agricultural Engineers
• /
• v.65 no.1
• /
• pp.41-49
• /
• 2023

To utilize the hydraulic and hydrological models when simulating floods in agricultural watersheds, it is necessary to consider agricultural reservoirs, farmland, and farmland drainage system, which are characteristics of agricultural watersheds. However, most of them are developed individually by different researchers, also, each model has a different simulation scope, so it is hard to use them integrally. As a result, there is a need to link each hydraulic and hydrological model. Therefore, this study established an integrated flood simulation system for the comprehensive flood simulation of agricultural reservoir watersheds. The system can be applied easily to various watersheds because historical weather data and the SSP (Shared Socio-economic Pathways) climate change scenario database of ninety weather stations were built-in. Individual hydraulic and hydrological models were coded and coupled through Python. The system consists of multiplicative random cascade model, Clark unit hydrograph model, frequency analysis model, HEC-5 (Hydrologic Engineering Center-5), HEC-RAS (Hydrologic Engineering Center-River Analysis System), and farmland drainage simulation model. In the case of external models with limitations in conceptualization, such as HEC-5 and HEC-RAS, the python interpreter approaches the operating system and gives commands to run the models. All models except two are built based on the logical concept.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.40 no.3
• /
• pp.303-314
• /
• 2020

The hydrological characteristics of watersheds and hydraulic systems of urban and river floods are highly nonlinear and contain uncertain variables. Therefore, the predicted time series of rainfall-runoff data in flood analysis is not suitable for existing neural networks. To overcome the challenge of prediction, a NARX (Nonlinear Autoregressive Exogenous Model), which is a kind of recurrent dynamic neural network that maximizes the learning ability of a neural network, was applied to forecast a flood in real-time. At the same time, NARX has the characteristics of a time-delay neural network. In this study, a hydrological model was constructed for the Taehwa river basin, and the NARX time-delay parameter was adjusted 10 to 120 minutes. As a result, we found that precise prediction is possible as the time-delay parameter was increased by confirming that the NSE increased from 0.530 to 0.988 and the RMSE decreased from 379.9 ㎥/s to 16.1 ㎥/s. The machine learning technique with NARX will contribute to the accurate prediction of flow rate with an unexpected extreme flood condition.