MCANet: A joint semantic segmentation framework of optical and SAR images for land use classification

•Optical and SAR images are remarkably complementary.•We developed the first and largest joint optical and SAR land use classification dataset, WHU-OPT-SAR.•A joint semantic segmentation framework MCANet for multimodal images is designed.•The land use classification accuracy of MCANet on the WHU-OPT-SAR dataset was 5% higher than that of optic-image-based approaches.