Microseismic analysis is a valuable tool for fracture characterization in the Earth’s subsurface. Distributed acoustic sensing (DAS) fibers are deployed at depth inside wells, so they hold vast potential for high‐resolution microseismic analysis. However, the accurate detection of microseismic signals in continuous DAS data is challenging and time consuming. We designed, trained, and deployed a deep learning model to detect microseismic events in DAS data automatically. We created a curated dataset of nearly 7000 manually selected events and an equal number of background noise examples. We optimized the deep learning model’s network architecture together with its training hyperparameters by Bayesian optimization. The trained model achieved an accuracy of 98.6% on our benchmark dataset and even detected low‐amplitude events missed during manual labeling. Our methodology detected more than 100,000 events, allowing for a far more accurate and efficient reconstruction of spatiotemporal fracture development than would have been feasible by traditional methods.