Piston sensing for sparse aperture systems with broadband extended objects via a single convolutional neural network

•We demonstrate that using only a single deep convolutional neural network (DCNN) is sufficient to detect pistons from broadband extended images. To the best of our knowledge, the technique, reported in this paper, has never been reported.•Compared to other piston sensing methods using neural network, the reported technology being able to discern pistons directly from the broadband intensity summations rather than the intensities of separated wavelengths uses only a single DCNN, which extremely relaxes the optics complexity.•Above all, we believe this paper is suitable for optics and lasers in engineering.