Accurately Estimating Redshifts from CSST Slitless Spectroscopic Survey using Deep Learning

China Space Station Telescope (CSST) has the capability to conduct slitless spectroscopic survey simultaneously with photometric survey. The spectroscopic survey will measure slitless spectra, potentially providing more accurate estimations of galaxy properties, particularly redshift, compared to broadband photometry. However, due to low-resolution and signal-to-noise ratio of slitless spectra, measurement of these properties is significantly challenging. In this study, we employ a Bayesian neural network (BNN) to assess the accuracy of redshift estimations from slitless spectra anticipated to be observed by CSST. The slitless spectra are simulated based on real data from the early data release of the Dark Energy Spectroscopic Instrument (DESI-EDR) and the 16th data release of the Baryon Oscillaton Spectroscopic Survey (BOSS-DR16), combining the 9th data release of the DESI Legacy Survey (DESI LS DR9). The BNN provides redshifts estimates along with corresponding uncertainties, achieving an accuracy of ₍₌₀₃ = 0. 00063, outlier percentage =0. 92\% and weighted mean uncertainty E = 0. 00228. These results successfully meet the requirement for cosmological studies using slitless spectra from CSST.