<p>This paper examines synchronization of reaction–diffusion neural networks via event-triggered control (ETC) with delays. As a result, a sampled-data-based event-triggering condition is proposed. The ETC updates only when specific trigger conditions are met, leading to a substantial decrease in communication requirements and energy preservation. The proposed sampled-data based ETC effectively eliminates the Zeno phenomenon, ensuring efficient and reliable system performance. The synchronization criteria can be derived using the Lyapunov–Krasovskii functional and employing inequality techniques which are then formulated as linear matrix inequalities. These sufficient conditions ensure the asymptotic stability of the drive-response reaction–diffusion neural networks. Two numerical examples are provided to demonstrate the efficiency of the designed ETC.</p>