Emergency departments are vital units that work full-time, serve critically ill patients and provide immediate emergency care according to the triage code of the admitted patients. The efficient operation of emergency services depends on adequate human and medical resources and early planning efforts. The increase in the intensity of emergency services due to covid-19, which is a biological disaster, has limited the effective use of resources and planning studies. The patient density in the emergency services can endanger the lives of the patients and disrupt the service if no preparation is made. For this reason, it is important to organize emergency service units according to patient estimates, to reduce the density, to provide the service at an optimum level, to provide ease of planning and management, to use medical and human resources effectively, and to patient satisfaction. This study was conducted to predict patient arrivals in the emergency department in the context of meteorological data. This study, hourly forecasting results are obtained using estimation methods seasonal autoregressive integrated moving average (SARIMAX), artificial neural network (ANN), nonlinear autoregressive models with exogenous inputs with exogenous regressionists (NARX). For the study, patient arrival data from a training and research hospital for December 2021 and meteorological data such as temperature, humidity, and wind were used. The performance of the estimation plot using multiple methods was measured by the mean absolute percent error (MAPE). The SARIMAX model showed a better performance than other methods in terms of prediction accuracy with a MAPE value of 31%.