Abstract: Homotopy algorithm is a new method for solving nonlinear optimization problems. This paper introduces the homotopy algorithm into back-propagation neural network and indicates that the convergence speed can be improved and the defects of converging to local extremum can be eliminated. It is of rapid convergence speed, high convergence precision and good stability. Application of the algorithm to predicting reservoir parameters could improve the reliability of the parameter prediction. Case study proves its effectivity in prediction of reservoir parameters.

Key words: neural network, homotopy algorithm, reservoir rock, parameter, prediction