Evaluating deep learning and machine learning algorithms for forecasting daily pan evaporation during COVID-19 pandemic

In this study, a deep learning algorithm namely long short-term memory (LSTM) has been developed for forecasting daily pan evaporation at Sydney airport, Australia. The accuracy of the developed LSTM model has been compared with a commonly used machine learning model, namely multilayer perceptron neural network (MLP-NN). The evaporation rate as a single parameter was used with one time-lag based on autocorrelation function (ACF). The utilized data duration was from January 2021 to February 2022 (during Covid-19 pandemic). Different statistical measurements have been applied in order to evaluate the performance of the proposed models. The results showed that the developed LSTM model outperformed MLP-NN. The LSTM performed well with RMSE=1.074, MAE=0.771, R-2=0.97, while the MLP-NN had least performance with RMSE=2.801, MAE=1.994, and R-2=0.57. The developed LSTM model could be utilized in other locations for forecasting daily pan evaporation.