Shear Sonic Prediction Based on DELM Optimized by Improved Sparrow Search Algorithm

In the geophysical exploration field, sonic log (DT) and shear (DTS) are frequently used as quick affordable procedures for reservoir evaluation. Due to high acquisition costs, DTS is only accessible in a few wells within an oil/gas field. Numerous attempts have been made establish precise relationship between other petrophysical data. this study, method based on deep extreme learning machine optimized by improved sparrow search algorithm (ISSA-DELM) proposed improve accuracy stability of prediction. Firstly, (DELM) model constructed combining autoencoder algorithm. Secondly, aimed at defects (SSA), (ISSA) with firefly disturbance merging iterative strategy applied optimize initial input weights DELM. Finally, ISSA-DELM prediction block Ordos Basin China. The quantitative results show that RMSE, MAE, R-square predicted 6.1255, 4.1369, 0.9916, respectively. comprehensive performance better than ELM, DELM, DELM optimization algorithms, such genetic (GA), particle swarm (PSO), SSA. Therefore, it can be concluded provides effective missing estimation.