Seismology modeling agent: A smart assistant for geophysical researchers

Seismology modeling agent: A smart assistant for geophysical researchers Yukun Ren1,2, Siwei Yu1, and Kai Chen2, JianWei Ma1 1Harbin Institute of Technology, Harbin, China 2Zhongguancun Academy, Beijing, China Key Points: • We develop MCP servers for the SPECFEM seismic modeling suite, which can be integrated into modern AI agent systems. • The agentic workflow supports both fully automated and interactive human-in-the-loop seismic simulations. • The agent-driven framework lowers the barrier to seismic modeling, paving the way for future automated scientific research. Corresponding author: Siwei Yu, siweiyu@hit.edu.cn Corresponding author: Kai Chen, kaichen@zgci.ac.cn –1– arXiv:2512.14429v1 [cs.AI] 16 Dec 2025 Abstract To address the steep learning curve and reliance on complex manual file editing and command- line operations in the traditional workflow of the mainstream open-source seismic wave simulation software SPECFEM, this paper proposes an intelligent, interactive workflow powered by Large Language Models (LLMs). We introduce the first Model Context Protocol (MCP) server suite for SPECFEM (supporting 2D, 3D Cartesian, and 3D Globe versions), which decomposes the entire simulation process into discrete, agent-executable tools spanning from parameter generation and mesh partitioning to solver execution and visualization. This approach enables a paradigm shift from file-driven to intent-driven conversational interactions. The framework supports both fully automated execution and human-in-the- loop collaboration, allowing researchers to guide simulation strategies in real time and retain scientific decision-making authority while significantly reducing tedious low-level operations. Validated through multiple case studies, the workflow operates seamlessly in both autonomous and interactive modes, yielding high-fidelity results consistent with standard baselines. As the first application of MCP technology to computational seismology, this study significantly lowers the entry barrier, enhances reproducibility, and offers a promising avenue for advancing computational geophysics toward AI-assisted and automated scientific research. The complete source code is available at https://github.com/RenYukun1563/specfem-mcp. Plain Language Summary Simulating how seismic waves travel through the Earth is important for understanding earthquakes, imaging underground structures, and studying the planet’s interior. SPECFEM is a widely used open-source software package for these simulations, but its workflow can be difficult for many researchers. It requires editing many detailed text files and running long sequences of command-line instructions, which can be time-consuming and easy to get wrong. In this work, we build a new way to use SPECFEM by connecting it to modern Artificial Intelligence (AI) systems. We create a set of Model Context Protocol (MCP) servers that allow human users to control SPECFEM with simple, conversational instructions, which are interpreted by a large language model that then operates SPECFEM on their behalf. Instead of manually setting up every file, researchers can tell the AI what they want to simulate, review intermediate results, and adjust the setup interactively. Researchers can freely choose between fully automated execution and interactive control for any simulation task. Through several case studies, we demonstrate how this framework can be used in practice. These examples suggest that the approach makes SPECFEM easier to use, reduces opportunities for human error, and provides a new pathway for AI-assisted and automated research in computational geophysics. 1 Introduction Numerical simulation of seismic wave propagation serves as a cornerstone of modern geophysics, providing an indispensable tool for understanding earthquake physics, assessing seismic hazards, and exploring subsurface resources (Aki & Richards, 2002; Fichtner, 2010). Against this backdrop, the open-source SPECFEM software suite (including SPECFEM2D, SPECFEM3D Cartesian, and SPECFEM3D Globe), developed based on the spectral-element method, has evolved over two decades of collaborative development and community building to become one of the most significant and powerful numerical simulation tools in the field today (Patera, 1984; Seriani & Priolo, 1994; Komatitsch & Vilotte, 1998; Komatitsch & Tromp, 1999, 2002b, 2002a; Tromp et al., 2008; SPECFEM Developers, 2025b). Its strength lies not only in the high precision, computational efficiency, and large-scale parallel capabilities of its core solver, but also in the mature ecosystem of auxiliary tools built around it (Carrington et al., 2008; Peter et al., 2011). This toolchain covers the entire scientific –2– lifecycle, from pre-processing (e.g., model building and meshing) to post-processing (e.g., data aggregation and visualization). Consequently, it has become the tool of choice for researchers and students worldwide for wave propagation modeling, underpinning countle

This content is AI-processed based on open access ArXiv data.