Microwave kinetic inductance detectors (MKIDs) are superconducting photon counting detectors that simultaneously measure the energy and arrival time of individual photons and are suitable for large-format arrays. The energy resolving power $R=E/\mathrm{\Delta }E$ is the primary figure of merit for spectrophotometric applications. It is limited in practice by the assumptions underlying the Wiener optimal filter used to estimate photon energy: stationary noise, linear response, and energy independent pulse shapes, all of which MKIDs structurally violate. We present Very Efficient Neural Optimal-filter for MKIDs (Venom), a selective state-space model based on the Mamba architecture that replaces the coordinate transform and optimal filter, operating directly on raw in-phase and quadrature timestream data, carrying 3314 trainable parameters, and targeting deployment on the MKIDGen3 and future system-on-chip readout platforms. To deal with the small calibration datasets typical of MKID experiments, we train on synthetic pulses drawn from a streaming principal component analysis that samples photon energy continuously between calibration wavelengths. All numbers are reported on a stratified 15% held-out validation set, with $R$ measured from a kernel density estimate. On an InHf bilayer resonator (ten wavelengths, 254–1310 nm), Venom reaches a mean $R$ of 26.4 vs 24.2 for the published per-wavelength optimal filter baseline, a 9% improvement from one model in place of ten per-laser filter templates. The $R$ of 38.6 at 254 nm is the highest ever recorded for an ultraviolet-to-near-infrared MKID suitable for use in a dense array. On a PtSi resonator (five wavelengths, 808–1310 nm), where the published analysis used one shared 920 nm template, Venom matches the optimal filter, with a mean $R$ of 9.1 vs 8.8 at the three interior wavelengths.

Close

PrevNext

View figure in article

• Superconducting devices
• Machine learning
• Microwave techniques
• Neural network simulations
• Photon counting
• Radiation detectors