Efficient and accurate porosity prediction is essential for the fine description of reservoirs, for which an optimized BP neural network (BPNN) prediction model is proposed. Aiming at the problem that the BPNN is sensitive to initialization and converges to local optimum easily, an improved shuffled frog leaping algorithm (ISFLA) is proposed based on roulette and genetic coding. Firstly, a roulette mechanism is introduced to improve the selection probability of elite individuals, thus enhancing the global optimization ability. Secondly, a genetic coding method is carried out by making full use of effective information such as the global and local optimal solutions and the boundary values of subgroups. Subsequently, the ISFLA algorithm is verified on 12 benchmark functions and compared with four intelligent optimization algorithms, and experimental results show its good optimization performance. Finally, the ISFLA algorithm is applied to the optimization of initial weights and thresholds of the BPNN, and a new model named ISFLA_BP is proposed to study the porosity prediction problem. The logging data is preprocessed by grey correlation analysis and deviation normalization, and then the effective prediction of porosity is achieved by natural gamma, density and other relevant parameters. The performance of ISFLA_BP model is compared with the standard three-layer BPNN and four BPNN parameter optimization methods based on swarm intelligence algorithms. Experimental results show that the proposed model has higher training accuracy, stability and faster convergence speed, with a mean square error of 0.02, and its prediction accuracy for porosity is higher than that of the other five methods.

An improved Adam optimization algorithm combining adaptive coefficients and composite gradients based on randomized block coordinate descent is proposed to address issues of the Adam algorithm such as slow convergence, the tendency to miss the global optimal solution, and the ineffectiveness of processing high-dimensional vectors. The adaptive coefficient is used to adjust the gradient deviation value and correct the search direction firstly. Then, the predicted gradient is introduced, and the current gradient and the first-order momentum are combined to form a composite gradient to improve the global optimization ability. Finally, the random block coordinate method is used to determine the gradient update mode, which reduces the computational overhead. Simulation experiments on two standard datasets for classification show that the convergence speed and accuracy of the proposed algorithm are higher than those of the six gradient descent methods, and the CPU and memory utilization are significantly reduced. In addition, based on logging data, the BP neural networks optimized by six algorithms, respectively, are used to predict reservoir porosity. Results show that the proposed method has lower system overhead, higher accuracy, and stronger stability, and the absolute error of more than 86% data is within 0.1%, which further verifies its effectiveness.

In order to avoid the occurrence of caprock integrity damage and gas escape due to injection pressure overrun in CO2 sequestration, an optimized back propagation (BP) neural network model based on Monte Carlo simulation (MCS) and an improved lion swarm optimization (ILSO) algorithm is proposed for the maximum sustainable injection pressure prediction. Firstly, a hydromechanical model is constructed to simulate the damage changes of the reservoir caprock during injection by ABAQUS. Secondly, in view of the uncertainties of formation parameters that could lead to deviations between the model calculation results and actual geological condition, the MCS method is used, and then, the probability distribution interval of the maximum injection pressure with high probability of caprock failure under different formation parameters is obtained by MATLAB. This effectively reduces the uncertainty and improves the calculation accuracy. Finally, based on the numerical simulation results, the maximum injection pressure prediction model is constructed. Aiming at the problems of the sensitivity of the BP neural network to initial weights and its poor convergence, tent chaotic mapping and difference mechanism are introduced to improve the LSO algorithm. Following this, the neural network is optimized by ILSO algorithm whose superiority is verified through 8 benchmark functions, and the maximum injection pressure is effectively predicted according to porosity, permeability, and other parameters. Experimental results show that, compared to the other three optimization methods, the ILSO_BP model has a faster convergence speed, higher prediction accuracy, and stability, which can provide a powerful guide for the safe injection of CO2 and efficient sequestration management.

No abstract

No abstract