In this research, we explore the application of artificial neural networks, specifically the vector-quantized temporal associative memory (VQTAM) and VQTAM coupled with locally linear embedding (VQTAM-LLE) techniques, for simulating 2-D magnetotelluric forward modeling. The study introduces the concepts of VQTAM and VQTAM-LLE in the context of simulating 2-D magnetotelluric responses, outlining their underlying principles. We rigorously evaluate the accuracy and efficiency of both VQTAM variants through extensive numerical experiments conducted on diverse benchmark resistivity and real-terrain models. The results demonstrate the remarkable capability of VQTAM and VQTAM-LLE in accurately and efficiently predicting apparent resistivity and impedance phases, surpassing the performance of traditional numerical methods. This study underscores the potential of VQTAM and VQTAM-LLE as valuable computational alternatives for simulating magnetotelluric responses, offering a viable choice alongside conventional methods.

中文翻译：

---

使用基于矢量量化时间联想记忆人工神经网络的方法模拟二维大地电磁响应

在这项研究中，我们探索了人工神经网络的应用，特别是矢量量化时间关联记忆（VQTAM）和VQTAM与局部线性嵌入（VQTAM-LLE）技术相结合，用于模拟二维大地电磁正演建模。该研究在模拟二维大地电磁响应的背景下介绍了 VQTAM 和 VQTAM-LLE 的概念，概述了它们的基本原理。我们通过对各种基准电阻率和真实地形模型进行广泛的数值实验，严格评估两种 VQTAM 变体的准确性和效率。结果表明，VQTAM和VQTAM-LLE在准确有效地预测视电阻率和阻抗相位方面具有卓越的能力，超越了传统数值方法的性能。这项研究强调了 VQTAM 和 VQTAM-LLE 作为模拟大地电磁响应的有价值的计算替代方案的潜力，为传统方法提供了可行的选择。