Modern spacecraft communication systems rely on concatenated error correction schemes, typically combining convolutional and Reed-Solomon (RS) codes. This paper presents a decoder-side method that uses a machine learning model to estimate the likelihood of byte-level corruption in received data frames. These estimates are used to mark erasures prior to RS decoding, enhancing its correction capacity without requiring changes to spacecraft hardware or encoding standards. The approach enables improved data recovery under degraded signal conditions at a gain of 0.3 decibels.