<![CDATA[Geophysical interpretation commonly relies on multiple independent software packages, making data processing, visualization, and interpretation inefficient for educational and research purposes. This study presents the development of an integrated open-source geophysical modeling platform that combines gravity, magnetic, and Very Low Frequency (VLF) electromagnetic methods within a single application. The proposed software incorporates deterministic forward modeling together with a Convolutional Neural Network (CNN)-based deep learning module to support rapid subsurface interpretation. The platform was developed using Python and integrates numerical computation, interactive visualization, and AI-assisted inversion into a unified graphical user interface. For VLF processing, Fraser and Karous–Hjelt filters are implemented to enhance conductive anomaly detection, while gravity and magnetic modeling employ prism-based forward calculations with Root Mean Square Error (RMSE) evaluation. In addition, Model Performance and Efficiency Index (MPEI) and Model Resolution Index (MRI) are incorporated to quantitatively assess model quality and computational efficiency. The resulting software provides an integrated workflow from data preprocessing to visualization and model evaluation, reducing interpretation time while improving usability for geophysical education and preliminary subsurface investigations. The proposed platform demonstrates that integrating conventional geophysical modeling with modern deep learning techniques offers a flexible, transparent, and extensible framework suitable for academic research and practical applications.]]>
