MostofthestudiesonArtificialNeuralNetwork(ANN)modelsremainrestrictedtosmallerriversandcatchments.Inthispaper,anattempthasbeenmadetocorrelatevariabilityofsedimentloadswithrainfallandrunoffthroughtheapplicationoftheBackPropagationNeuralNetwork(BPNN)algorithmforalargetropicalriver.ThealgorithmandsimulationaredonethroughMATLABenvironment.Themethodologycomprisedofacollectionofdataonrainfall,waterdischarge,andsedimentdischargefortheNarmadaRiveratvariouslocations(alongwithtimevariables)andapplicationtodevelopathreelayerBPNNmodelforthepredictionofsedimentdischarges.Fortrainingandvalidationpurposesasetof549datapointsforthemonsoon(16June-15November)periodofthreeconsecutiveyears(1996–1998)wasused.Fortestingpurposes,theBPNNmodelwasfurthertrainedusingasetof732datapointsofmonsoonseasonoffouryears(2006–07to2009–10)atninestations.Themodelwastestedbypredictingdailysedimentloadforthemonsoonseasonoftheyear2010–11.ToevaluatetheperformanceoftheBPNNmodel,errorswerecalculatedbycomparingtheactualandpredictedloads.Thevalidationandtestingresultsobtainedatalltheselocationsaretabulatedanddiscussed.Resultsobtainedfromthemodelapplicationarerobustandencouragingnotonlyforthesub-basinsbutalsofortheentirebasin.Theseresultssuggestthattheproposedmodeliscapableofpredictingthedailysedimentloadevenatdownstreamlocations,whichshownonlinearityinthetransportationprocess.Overall,theproposedmodelwithfurthertrainingmightbeusefulinthepredictionofsedimentdischargesforlargeriverbasins.
