Improved Hippopotamus Optimization Algorithm for Deep Learning Denoising of Controlled Source Electromagnetic Method Data

To address the limitations of the hippopotamus optimization (HO) algorithm, primarily its insufficient global exploration capability and susceptibility to premature convergence to local optima, this paper proposes a hybrid-strategy-improved HO (HSIHO) algorithm for deep learning denoising of controlled source electromagnetic method (CSEM) data. Initially, various strategies are evaluated, and the most effective strategy incorporating lens opposite-based learning (LOBL) and adaptive t-distribution perturbation (ATP) is selected to enhance the hippopotamus optimization algorithm. Subsequently, the HSIHO algorithm is employed to optimize key hyperparameters of the deep learning model, including the learning rate, number of neurons, and number of iterations. Finally, the optimized deep learning model is applied to CSEM data denoising, and its performance is compared with that of the unoptimized deep learning model. Experimental results demonstrate that the proposed HSIHO algorithm outperforms other intelligent optimization algorithms in terms of convergence speed, solution accuracy, flexibility, and scalability in benchmark functions tests. In the application of CSEM data denoising, the optimized bidirectional long short-term memory (BiLSTM) network significantly surpasses the probabilistic neural network (PNN), convolutional neural network (CNN), long short-term memory network (LSTM) and unoptimized BiLSTM methods in noise identification and denoising accuracy. The quality of the processed CSEM data is notably enhanced, with a more stable electric field curve profile. The satisfactory performance in the results verifies the effectiveness of the design and optimization method.