Search Results (2)

Forecasting streamflow in stream basin systems plays a crucial role in facilitating effective urban planning to mitigate floods. In addition to employing intricate hydrological modeling systems, machine learning and statistical techniques offer an alternative means for streamflow forecasts. Nonetheless, the precision and dependability of these methods are subjects of paramount importance. This study rigorously investigates the effectiveness of three distinct machine learning techniques and two statistical approaches when applied to streamflow data from the Göksu Stream in the Marmara Region of Turkey, spanning from 1984 to 2022. Through a comparative analysis of these methodologies, this examination aims to contribute innovative advancements to the existing methodologies used in the prediction of streamflow data. The methodologies employed include machine learning methods such as Extreme Gradient Boosting (XGBoost), Random Forest (RF), and Support Vector Machine (SVM) and statistical methods such as Simple Exponential Smoothing (SES) and Autoregressive Integrated Moving Average (ARIMA) model. In the study, 444 data points between 1984 and 2020 were used as training data, and the remaining data points for the period 2021–2022 were used for streamflow forecasting in the test validation period. The results were evaluated using various metrics, such as the correlation coefficient (r), mean absolute error (MAE), root mean square error (RMSE), mean absolute percentage error (MAPE), coefficient of determination (R²), and Nash–Sutcliffe efficiency (NSE). Upon analyzing the results, it was found that the model generated using the XGBoost algorithm outperformed other machine learning and statistical techniques. Consequently, the models implemented in this study demonstrate a high level of accuracy in predicting potential streamflow in the river basin system. Full article

Floods are among the most devastating disasters in terms of socio-economics and casualties. However, these natural disasters can be managed and their effects can be minimized by flood modeling performed before the occurrence of a flood. In this study, flood modeling was developed for the Göksu River Basin, Mersin, Türkiye. Flood hazard and risk maps were prepared by using GIS, HEC-RAS, and HEC-HMS. In hydraulic modeling, Manning’s n values were obtained from 2018 CORINE data, return period flow rates (Q25, Q50, Q100, Q500) were obtained from HEC-HMS, and the application was carried out on a 5 m resolution digital surface model. In the study area, the water depths could reach up to 10 m, and water speeds were approximately 0.7 m/s. Considering these values and the fact that the study area is an urban area, hazard maps were obtained according to the UK Department for Environment, Food and Rural Affairs (DEFRA) method. The results indicated that possible flood flow rates from Q25 to Q500, from 1191.7 m³/s to 1888.3 m³/s, were detected in the study area with HEC-HMS. Flooding also occurred under conditions of the Q25 flow rate (from 4288 km² to 5767 km²), and the impacted areas were classified as extremely risky by the DEFRA method. Full article