Beyşehir Lake is the largest freshwater lake in the Mediterranean region of Turkey that is used for drinking and irrigation purposes. The aim of this paper is to examine the potential for data-driven methods to predict long-term lake levels. The surface water level variability was forecast using conventional machine learning models, including autoregressive moving average (ARMA), autoregressive integrated moving average (ARIMA), and seasonal autoregressive integrated moving average (SARIMA). Based on the monthly water levels of Beyşehir Lake from 1992 to 2016, future water levels were predicted up to 24 months in advance. Water level predictions were obtained using conventional time series stochastic models, including autoregressive moving average, autoregressive integrated moving average, and seasonal autoregressive integrated moving average. Using historical records from the same period, prediction models for precipitation and evaporation were also developed. In order to assess the model’s accuracy, statistical performance metrics were applied. The results indicated that the seasonal autoregressive integrated moving average model outperformed all other models for lake level, precipitation, and evaporation prediction. The obtained results suggested the importance of incorporating the seasonality component for climate predictions in the region. The findings of this study demonstrated that simple stochastic models are effective in predicting the temporal evolution of hydrometeorological variables and fluctuations in lake water levels.

The operating temperature of the transmission line in the traction network is affected by geographical and climatic factors, especially the wind speed. To make better use of the thermal stability transmission capacity of the traction power supply system in improving the short-term emergency transmission capacity, the dynamic rating technology is introduced into the traction power supply system. According to the time-varying characteristics of the actual wind speed, a dynamic rating method of the traction network based on wind speed prediction is proposed and constructed. Based on the time series model in predicting the wind speed series along the corridor of the traction network, the temperature curve of each transmission line under different currents is calculated by combining it with the heat balance equation of an IEEE-738 capacity expansion model, thus the relationship between the peak operating temperature and current of each transmission line in the prediction period is obtained. According to the current distribution coefficient, the capacity increase limit of the traction network is determined. The example shows that the proposed dynamic rating method based on wind speed prediction is an effective method to predict the short-term safe capacity increase limit of the traction network, which can increase the comprehensive capacity of the traction network by about 45% in the next six hours, and the capacity increase effect is obvious, which can provide reference and technical support for short-term emergency dispatching of traction power supply dispatching centres.