We resized and aligned 16-band channels to match those from 3-band channels. Alignment was necessary to remove shifts between channels. Finally all channels were concatenated into single 20-channels input image. Model Our fully convolutional model was inspired by the family of U-Net architectures, where low-level feature maps are combined with higher-level ones, which enables precise localization.
![Deep learning for satellite imagery via image segmentation - deepsense.ai](https://cdn-ak-scissors.b.st-hatena.com/image/square/f7c5f7d5294ddc89274c43b9fba254375f582287/height=288;version=1;width=512/https%3A%2F%2Fdeepsense.ai%2Fwp-content%2Fuploads%2F2019%2F02%2Fdeep-learning-for-satellite-imagery-via-image-segmentation.jpg)