Peripheral nerve interfaces (PNIs) allow us to extract motor, sensory, and autonomic information from the nervous system and use it as control signals in neuroprosthetic and neuromodulation systems. Recently, the recording selectivity of PNIs has been improved using spatiotemporal patterns from multi-contact nerve cuff electrodes as input to a convolutional neural network (CNN). The performance of this approach during chronic implantations is not known. In this simulation study, approaches were evaluated for maintaining the selective recording performance in the presence of chronic implantation challenges (encapsulation tissue, electrode movements, and contact failures). This study demonstrated that a selective recording algorithm trained at baseline will fail over time due to changes in signal characteristics resulting from the chronic challenges. Results further showed that periodically recalibrating the selective recording algorithm can maintain its performance over time, and that machine learning techniques have the potential to reduce the frequency of recalibration.