Supervisory Control and Data Acquisition (SCADA) systems are one of the most common industrial control systems (ICS). As the security threat of SCADA systems has been rising in recent years, intrusion detection has become indispensable. Among SCADA systems, there is a lack of research on intrusion detection of temporal and spatial characteristics, and the effectiveness of the existing intrusion detection approaches could be improved. This paper proposes an intrusion detection model based on spatio-temporal characteristics of SCADA systems, combining the attention mechanism, called STAM, allows a full understanding of the correlation between sensor and controller parameters. Experiments on three typical SCADA system datasets show that STAM proposed in this paper achieves state-of-the-art results and can be better applied to intrusion detection in SCADA systems. The effectiveness of STAM is evaluated by accuracy, precision, recall, and F1-score. The accuracy rates on new gas pipeline, water storage tank, and Secure Water Treatment (SWaT) datasets can reach 95.34%, 98.92% and 99.95% respectively.