A Hybrid Deep Learning Approach for Integrating Transient Electromagnetic and Magnetic Data to Enhance Subsurface Anomaly Detection

Recent advancements in geophysical exploration have highlighted the importance of integrating electromagnetic (EM) and magnetic data to enhance subsurface target detection. Conventional inversion techniques often struggle with the non-uniqueness of solutions and sensitivity to noise when relying on a single data modality. In this study, we introduce a novel deep learning framework, MagEMNet, designed to jointly invert EM and magnetic responses. This convolutional neural network (CNN)-based model effectively combines these two complementary data types, improving the estimation of target characteristics such as location, orientation, and physical properties. Trained on synthetic datasets generated through forward modeling, MagEMNet leverages the adaptive moment estimation (Adam) optimizer and a dynamic learning rate strategy to enhance convergence. Our results show that MagEMNet not only outperforms traditional inversion techniques in terms of accuracy but also accelerates the inversion process, offering an efficient solution for real-world applications, including unexploded ordnance (UXO) detection and subsurface resource assessment.