A model involving meteorological factors for short- to medium-term, water-level predictions of small- and medium-sized urban rivers

With the increase in extreme weather, cities, especially those with small- and medium-sized urban rivers protected areas smaller than 200 square hectares, are experiencing significantly more flood disasters worldwide. Heavy snowfall rainfall can rapidly overflow these cause floods due to unique geographic locations fast runoff confluence speeds of rivers. Therefore, it is particularly important accurately predict short- medium-term water levels reduce avoid floods. In present work, a particle swarm optimization (PSO)-support vector machine (SVM) water-level prediction model was constructed by combining PSO SVM trained meteorological data from Wuhan, China, Yangtze River. The PSO-SVM able lower mean error (MSE) results 70.47% coefficient determination (R2) 7.02% compared alone. highly accurate be used river real time using hourly weather data, thereby providing quantitative support for controlling floods, managing project construction, improving response efficiency reducing safety risks.