Accurately　delineating　sediment　export　dynamics　using　high-quality　vegetation　factors　remains　challenging　due　to　the　spatio-temporal　resolution　imbalance　of　single　remote　sensing　data　and　persistent　cloud　contamination.　To　address　these　challenges,　this　study　proposed　a　new　framework　for　estimating　and　analyzing　monthly　sediment　inflow　to　rivers　in　the　cloud-prone　Minjiang　River　Basin.　We　leveraged　multi-source　remote　sensing　data　and　the　Continuous　Change　Detection　and　Classification　model　to　reconstruct　monthly　vegetation　factors　at　30　m　resolution.　Then,　we　integrated　the　Chinese　Soil　Loss　Equation　model　and　the　Sediment　Delivery　Ratio　module　to　estimate　monthly　sediment　inflow　to　rivers.　Lastly,　the　Optimal　Parameters-based　Geographical　Detector　model　was　harnessed　to　identify　factors　affecting　sediment　export.　The　results　indicated　that:　(1)　The　simulated　sediment　transport　modulus　showed　a　strong　Coefficient　of　Determination　(R2　=　0.73)　and　a　satisfactory　Nash–Sutcliffe　Efficiency　coefficient　(0.53)　compared　to　observed　values.　(2)　The　annual　sediment　inflow　to　rivers　exhibited　a　spatial　distribution　characterized　by　lower　levels　in　the　west　and　higher　in　the　east.　The　monthly　average　sediment　value　from　2016　to　2021　was　notably　high　from　March　to　July,　while　relatively　low　from　October　to　January.　(3)　Erosive　rainfall　was　a　decisive　factor　contributing　to　increased　sediment　entering　the　rivers.　Vegetation　factors,　manifested　via　the　quantity　(Fractional　Vegetation　Cover)　and　quality　(Leaf　Area　Index　and　Net　Primary　Productivity)　of　vegetation,　exert　a　pivotal　influence　on　diminishing　sediment　export.　©　2024　by　the　authors.