Utilizing machine learning to improve the precision of fluorescence imaging of cavity-generated spin squeezed states

Journal Article · 23 January 2022 · Physical Review A

DOI: https://doi.org/10.1103/physreva.105.l010602 · OSTI ID:1979621

Malia, Benjamin K.  ^[1]; Wu, Yunfan ^[2]; Martínez-Rincón, Julián ^[2]; Kasevich, Mark A. ^[2]

---

1. Stanford Univ., CA (United States); OSTI
2. Stanford Univ., CA (United States)

We present a supervised learning model to calibrate the photon collection rate during the fluorescence imaging of cold atoms. The linear regression model finds the collection rate at each location on the sensor such that the atomic population difference equals that of a highly precise optical cavity measurement. This 192 variable regression results in a measurement variance 27% smaller than our previous single variable regression calibration. The measurement variance is now in agreement with the theoretical limit due to other known noise sources. This model efficiently trains in less than a minute on a standard personal computer's CPU and requires less than 10 min of data collection. Furthermore, the model is applicable across a large change in population difference and across data collected on different days.

• Research Organization: Stanford Univ., CA (United States)
• Sponsoring Organization: USDOE Office of Science (SC)
• Grant/Contract Number: SC0019174
• OSTI ID: 1979621
• Journal Information: Physical Review A, Journal Name: Physical Review A Journal Issue: 1 Vol. 105; ISSN 2469-9926
• Publisher: American Physical Society (APS)Copyright Statement
• Country of Publication: United States
• Language: English