In　this　research,　we　present　a　novel　application　of　Spike　Neural　Networks　(SNN)　for　automating　solitary　wave　recognition.　Through　the　utilization　of　Nonlinear　Transmission　Lines　(NLTL),　we　established　waveform　categories　encompassing　solitary　waves　and　others.　Notably,　our　proprietary　CNN-RNN　algorithm　exhibited　exceptional　accuracy,　achieving　0.9904　(train),　0.9630　(validate),　and　0.9778　(test)　accuracies.　This　achievement　carries　significant　implications　across　diverse　domains,　such　as　tele-communications,　optics,　nonlinear　electronics,　and　nonlinear　physics.　The　demonstrated　efficacy　of　SNN　opens　avenues　for　enhanced　automated　waveform　classification　with　broad　interdisciplinary　relevance.　©　2024　IEEE.