capture, utilization, and storage (CCUS) is a necessary task that received wide attention. Due to this fact, numerous studies proposed underground carbon storage to reduce CO2 emissions in the atmosphere. However, there are some drawbacks about estimation accuracy trapping efficiency in deep saline aquifers. Also, the time computation of conventional reservoir simulators requires weeks or months to complete the simulation tasks. Hence, a new approach about accuracy and a fast predictive model needs to propose for promoting the appli- cation of carbon capture and storage projects. Therefore, this paper proposes an optimized Adaptive Neuro fuzzy inference system (ANFIS) to predict two indices of the CO2 Trapping in deep saline aquifers, namely, solubility trapping index (STI) residual trapping index (RTI), using 6810 simulation samples, 8 input features of subsurface information from 33 fields of ten previous studies. We utilize the recently developed optimization algorithms, called Aquila optimizer (AO) and Salp Swarm Algorithm (SSA), to train the ANFIS model and to optimize its parameters to boost the prediction performance of the traditional ANFIS. The search mechanism of the SSA is used instead of the original one of the AO algorithm, which enhances the exploration process of the traditional AO. The proposed AOSSA-ANFIS is outperformed to seven optimized ANFIS models. Futhermore, AOSSA-ANFIS schemes achieves overall Mean Relative Absolute Error (MRAE) of 0.69495 and 0.36304, Mean Absolute Error (MAE) of 0.09771 and 0.04594, Root Mean Square Error (RMSE) of 0.15001 and 0.06904, and Mean Square Error (MSE) of 0.02269 and 0.00484 for RTI and STI, respectively. Additionally, the developed AOSSA-ANFIS demonstrated the superiority to existing study that used SVR, ANN, Liner regression and MLP. Due to this latter, the findings of this study provide a better understanding of the role of optimized hybrid ANFIS for CCUS as well as other subsurface disciplines. Finally, this study consider as template is easy to adapt to the similar effort of fast computational modeling.