Abstract: Objective In regional crustal movement research,mathematical model is always used to estimate with-out observation the points which need attention.Then,we can build up a relatively even and meaning-ful regional crustal movement velocity field.In this paper we analyze the strengths and weaknesses ofthe common Euler and function models,and propose a new model with BP neural network based onEuler vector.This proposed model uses the geological properties of a Euler vector and the superiorityof BP neural network.It considers the various influences and uncertain information found in data pro-cessing.Therefore,the model can distinguish inner elastic strain from rigid-body of the plate.Theproposed model obtains precision through specimen verification.