 The proposed method is able to enhance the spatial resolution of hyperspectral images by fusing them with high resolution, multispectral images. It uses a deep convolutional neural network to extract features from both the hyperspectral image and the multispectral image, and then combines these features using a fully connected layer. This allows for better spatial resolution than existing methods. The proposed method was tested on a virus and N-MAP data sets, as well as real Hyperion Sentinel data, and showed promising results. This article was authored by Jingxiong Yang, Yongchang Zhao, and Jonathan Chung-Wai-Chang.