Answers are grounded in this paper and cite their sources.
Flood forecasting is one of the most essential preventative measures for decreasing the damage caused by floods to human life and property. Developing advanced models in conjunction with a significant amount of available data will improve the accuracy of forecasts. This study proposes the concept of discharge forecasting utilizing a neural network model and the application of time response parameters in the watershed. To forecast the hourly discharge in the Upper Nan and Loei watersheds of 12 hours in advance. In this study, we investigated the model in the setting of two case studies: case 1, the application of statistical correlation (Case–Correl) and case 2, the application of the time response parameter (Case–TC). From the study results, it showed that the outcomes of 12-hour advance discharge forecasting at runoff Station N.1 in Upper Nan Basin and runoff station Kh.58A in Loei Basin were as follows: Case 2 (Case–TC) was more accurate than Case 1 (Case–Correl) in predicting flow rates in both watersheds. In addition, it was determined that the model accurately predicted the flow rate during the period of peak flow, with a deviation from the observed discharge approximately 3–8% and 8–11% for Case–TC and Case–Correl examples, respectively. The results indicate that the neural network model applying with time response parameters has a high forecasting capability of flow rate. And the findings of the forecast can be used to monitor the water situation and prepare for flood warning in the target area.
No takes yet. Share an insight, caveat, or question.
Saelo et al. (2023) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: