Short-term　origin-destination　(OD)　flow　prediction　in　urban　rail　transit　(URT)　plays　a　crucial　role　in　smart　and　real-time　URT　operation　and　management.　Different　from　other　short-term　traffic　forecasting　methods,　the　short-term　OD　flow　prediction　possesses　three　unique　characteristics:　(1)　data　availability:　real-time　OD　flow　is　not　available　during　the　prediction;　(2)　data　dimensionality:　the　dimension　of　the　OD　flow　is　much　higher　than　the　cardinality　of　transportation　networks;　(3)　data　sparsity:　URT　OD　flow　is　spatiotemporally　sparse.　There　is　a　great　need　to　develop　novel　OD　flow　forecasting　method　that　explicitly　considers　the　unique　characteristics　of　the　URT　system.　To　this　end,　a　channel-wise　attentive　split-convolutional　neural　network　(CAS-CNN)　is　proposed.　The　proposed　model　consists　of　many　novel　components　such　as　the　channel-wise　attention　mechanism　and　split　CNN.　In　particular,　an　inflow/outflow-gated　mechanism　is　innovatively　introduced　to　address　the　data　availability　issue.　We　further　originally　propose　a　masked　loss　function　to　solve　the　data　dimensionality　and　data　sparsity　issues.　The　model　interpretability　is　also　discussed　in　detail.　The　CAS-CNN　model　is　tested　on　two　large-scale　real-world　datasets　from　Beijing　Subway,　and　it　outperforms　the　rest　of　benchmarking　methods.　The　proposed　model　contributes　to　the　development　of　short-term　OD　flow　prediction,　and　it　also　lays　the　foundations　of　real-time　URT　operation　and　management.