Extended Data Fig. 8: Latent variable analysis reveals sclerite function using an encoder–decoder.

a, The network architecture consists of an encoder (red), muscle activity decoder (green), and wing kinematics decoder (blue). The encoder splits the input data into five streams corresponding to different muscle groups and frequency. Feature extraction is performed using convolutional and fully connected layers with SELU activation. Each stream is projected onto a single latent variable. In the muscle activity decoder, the latent variables are transformed back into the input data. A backpropagation stop prevents weight adjustments in the encoder based on the muscle activity reconstruction. The wing kinematics decoder predicts the Legendre coefficients of wing motion using the latent variables. See Supplementary Information for more details. b, Predicted muscle activity (replotted from Fig. 6) and normalized wingbeat frequency as a function of each latent parameter varied within the range of −3σ to +3σ. Color bar indicates the latent variable value in panels (c) and (e). c, Predicted wing motion by the wing kinematics decoder for the five latent parameters. d, Absolute angle-of-attack (|α|), wingtip velocity (u_tip) in mm s⁻¹, non-dimensional lift (L mg⁻¹), and non-dimensional drag (D mg⁻¹). The non-dimensional lift and drag were computed using a quasi-steady model as described in Supplementary Information.