The　guided　wave　is　an　efficient　and　reliable　tool　for　the　structural　health　monitoring　(SHM)　of　the　composite　laminates.　In　the　guided　wave-based　SHM　methods,　extracting　the　dispersion　curves　is　essential　for　integrity　evaluation.　In　this　study,　a　sparse　wavenumber　analysis　based　on　hybrid　least　absolute　shrinkage　and　selection　operator　(Lasso)　regression　is　proposed　to　extract　the　dispersion　curves　in　the　frequency-wavenumber　distribution　(FKD)　for　the　composite　laminate.　The　hybrid　Lasso　regression　model　is　constructed　based　on　the　guided　wave　propagation　mechanism.　Considering　that　responses　of　some　wave　modes　are　very　weak　at　specific　frequencies　due　to　the　guided　wave　attenuation　in　the　composite　laminates,　the　group-sparsity　and　continuity　regularizations　are　imposed　in　this　model　to　improve　frequency-wavenumber　resolution　and　remove　noises.　Only　few　sensors　are　required　for　the　proposed　method　to　extract　the　dispersion　curves.　Both　the　simulation　and　the　experiment　are　used　to　verify　the　effectiveness　of　the　proposed　method.　Furthermore,　the　material　property　of　the　composite　laminate　in　the　experiment　is　non-destructively　estimated　by　using　the　dispersion　curves　extracted　by　the　proposed　method.