A new deep learning model performs a task that biologists have struggled with for centuries — how to measure the incredibly complex process of embryonic development. Scientists have shown that the AI model, known as Dev-ResNet, can identify what happens and when during embryonic development, from video. While used in pond snail embryos for this study, in future the technique could be used to help accelerate understanding on how climate change, and other external factors, affect humans and animals in the earliest stages of life.