Accurate determination of the temperature of trapped ion Coulomb crystals (ICCs) is critical for advancing quantum technologies. We present a deep learning approach to classify ICC temperature states from fluorescence images. A high-fidelity dataset was generated using the (py)LIon molecular dynamics toolkit, simulating ICCs containing 100–268 ions over a temperature range of 5–20 mK. In the initial 16-class problem (each class a 1-mK interval), a ConvNeXt convolutional network achieved a peak accuracy of 57%, demonstrating its ability to capture fine-grained structural features. To overcome low distinguishability among similar temperature classes, we redefined the task into four broader temperature intervals and applied a vision transformer (ViT). The ViT model achieved a test accuracy of 84%, indicating substantially improved generalization. These results highlight the complementarity of convolutional neural network and transformer architectures for noninvasive temperature diagnostics. We discuss limitations due to dataset diversity and outline future work on larger-scale simulations and physics-guided network designs to further improve ICC temperature estimation in quantum applications.

Close

PrevNext

View figure in article

• Atomic & molecular processes in external fields