Sensor networks are incredibly important. Versatile combinations of sensors are used in a wide array of applications, from urban sensing, to oceanographic sensing, to health and industrial sensing. Failures in individual sensors can have catastrophic consequences. Anomaly detection (AD) is essential to identify these failures and ensure the integrity and reliability of sensor data. This paper introduces a novel approach using Generative Adversarial Networks (GANs) to detect anomalies in time-series data collected from urban sensor networks. Our novel approach involves representing sensor readings as images in which sensor locations and readings are encoded into an image tensor, coupled with post-training the latency vector for more stable anomaly detection. This efficient representation enables GANs to learn whole networks of sensors globally and is capable of identifying differences in sensor data at a single-pixel level. Experimental results demonstrate the efficiency of this approach, where utilizing this approach flags nearly twice as many anomalous readings than without latency post-training.