The　study　of　coastal　processes　is　critical　for　the　protection　and　development　of　beach　amenities,　infrastructure,　and　properties.　Many　studies　of　beach　evolution　rely　on　data　collected　using　remote　sensing　and　show　that　beach　evolution　can　be　characterized　by　a　finite　number　of　＂beach　states　＂.　However,　due　to　practical　constraints,　long-term　data　displaying　all　beach　states　are　rare.　Additionally,　when　the　dataset　is　available,　the　accuracy　of　the　classification　is　not　entirely　objective　since　it　depends　on　the　operator.　To　address　this　problem,　we　collected　hourly　coastal　images　and　corresponding　tidal　data　for　more　than　20　years　(November　1998-August　2019).　We　classified　the　images　into　eight　categories　according　to　the　classic　beach　state　classification,　defined　as　(1)　reflective,　(2)　incident　scaled　bar,　(3)　non-rhythmic,　attached　bar,　(4)　attached　rhythmic　bar,　(5)　offshore　rhythmic　bar,　(6)　non-rhythmic,　3-D　bar,　(7)　infragravity　scaled　2-D　bar,　(8)　dissipative.　We　developed　a　classification　model　based　on　convolutional　neural　networks　(CNN).　After　image　pre-processing　with　data　enhancement,　we　compared　different　CNN　models.　The　improved　ResNext　obtained　the　best　and　most　stable　classification　with　F1-score　of　90.41%　and　good　generalization　ability.　The　classification　results　of　the　whole　dataset　were　transformed　into　time　series　data.　MDLats　algorithms　were　used　to　find　frequent　temporal　patterns　in　morphology　changes.　Combining　the　pattern　of　coastal　morphology　change　and　the　corresponding　tidal　data,　we　also　analyzed　the　characteristics　of　beach　morphology　and　the　changes　in　morphodynamic　states.