“…The existing studies in time series forecasting can be categorized into three groups: traditional linear regression methods [ 19 , 20 ], machine learning methods [ 21 , 22 ], and deep learning methods [ 23 , 24 , 25 , 26 , 27 , 28 , 29 , 30 , 31 , 32 , 33 , 34 , 35 , 36 ]. Traditional models include moving average (MA), autoregressive (AR), and autoregressive moving average (ARIMA) models, all of which are widely used for time series forecasting [ 19 , 20 ]. Coradi et al [ 1 ] developed six linear regression models to predict grain storage quality and evaluated the models to achieve high prediction accuracy; André et al [ 37 ] used machine learning methods such as artificial neural networks, decision tree algorithm REPTree, and random forest to predict the quality of soybean seeds for decision making in the seed storage process.…”