Abstract: In order to solve the problem of low accuracy of existing hydraulic engineering slope mechanical parameter prediction models， the least squares support vector machine LSSAR is used to predict the hydraulic engineering slope mechanical parameters （elastic modulus E）， and the improved firefly algorithm is used to optimize the model. A hydraulic engineering slope mechanical parameter prediction model based on DEFA-LSSAR is proposed. We compare the model proposed in this article with the LSSAR model optimized by the Salp Swarm Algorithm， Drosophila Algorithm， and Harris Eagle Optimization Algorithm， respectively. The analysis results show that the proposed model has the highest prediction accuracy， reaching over 94%， and has the smallest fitness value， verifying the effectiveness and correctness of the proposed model in this article.

Key words: water conservancy project, slope stability, least squares support vector machine, firefly algorithm, parameter prediction