<![CDATA[Natural gas prices are a critical economic indicator influencing various sectors of the global economy. Accurate forecasting is essential for effective policy formulation and strategic decision making. However, natural gas price movements often exhibit complex non-linear patterns that traditional statistical time series models fail to capture. Furthermore, many deep learning architectures struggle to effectively model these intricate dynamics. To address this challenge, we employ the Patch-Based Transformer (PatchTST) model for natural gas price forecasting. The comparative results reveal that PatchTST achieves substantially higher predictive accuracy than both statistical and other deep learning models. Its Transformer-based architecture, combined with patching and channel independence, enables the model to effectively capture both temporal dependencies and localized variations. The model achieved mean squared error (MSE) and mean absolute percentage error (MAPE) values of 0.1176 and 7.57%, respectively. These findings demonstrate that PatchTST provides robust and precise forecasts, offering valuable insights for decision-making in the energy market]]>
