Space telescopes maintain optical alignment through periodic, resource-intensive wavefront calibration, leaving their optical state unobserved between measurements. In this work, we explore whether engineering telemetry already collected by the James Webb Space Telescope (JWST) can serve as a virtual wavefront sensor.
We propose a machine learning framework that uses thermal and pointing telemetry to estimate spatially resolved optical path difference (OPD) at nanometer precision, without requiring dedicated wavefront measurements at inference time. Our approach combines principal component analysis (PCA) with a two-stage gradient boosting regressor, trained and evaluated on six months of on-orbit JWST data.
Despite the limited number of available measurements, the method achieves statistically significant results in 13 of the 18 mirror segments, with 7 segments exceeding 50% explained variance and the best reaching 91.1%.
These findings demonstrate the potential of telemetry-driven wavefront estimation to support continuous optical monitoring and more efficient calibration scheduling for future space observatories.
Lahav Buzi is an M.Sc. candidate in Electrical Engineering at the Technion, under the supervision of Prof. Yoav Schechner. His research focuses on computational imaging, machine learning, and data-driven wavefront estimation for space telescopes.