The real-time observation of surface temperature using remote satellite sensors is a critical parameter to analyse the greenhouse effect on the Earth. However, the transmission of satellite imaging in high resolution may cause high latency in geo-science applications to achieve real-time manner. In this paper, the deployment of deep learning architecture using Generative Adversarial Network (GAN) is applied to increase super-resolution reconstruction using low resolution imaging captured from the South China Sea sea surface temperature data. In addition, the development of spectral normalization is added to the Enhanced Super Resolution GAN (ESRGAN) architecture to improve the training mechanism of generator and discriminator. This improved ESRGAN is compared with its super resolution performance against peak signal-to-noise ratio and structural similarity index evaluation metrics. The experiment shows that the low resolution of South China Sea data can be inferred to obtain a higher resolution with a more realistic resolution as compared to the conventional upsampling approaches.