An Agentic Interface for End-to-End Probabilistic Seismic Hazard and Risk Analysis
physics.geo-ph, cs.AI
Submitted: 2026-06-27
Updated: 2026-06-27
Comments: 24 pages, 8 figures
DOI: 10.1038/s44304-026-00262-z
Code: https://github.com/gem/oq-engine
License: http://creativecommons.org/licenses/by-nc-nd/4.0/
The gist: Probabilistic seismic hazard and risk analyses are backbone to building codes, insurance pricing, and disaster management.
Terminology
Abstract
Probabilistic seismic hazard and risk analyses are backbone to building codes, insurance pricing, and disaster management. Yet their open-engine pipelines remain accessible primarily to experts. We present the first agentic interface to the end-to-end probabilistic seismic hazard and risk chain via an open-source server, addressable through the Model Context Protocol (MCP). MCP wraps the OpenQuake engine and the 2020 European Seismic Hazard and Risk Models using twenty-four typed endpoints. Here, an agent is defined as a large language model (LLM) with tools. LLM is confined to the role of an orchestrator so it plans, translates, and explains, while the OpenQuake engine and custom codes compute hazard values, damage probability, and loss. Each response carries source-model, ground-motion model (GMM), and certified data provenance for transparency. Results are benchmarked against ESHM20 at seventy-three cities, the replicated 475-year spectral accelerations match official values within a median of 5 %, and a full hazard-to-loss estimate runs in minutes. The interface additionally accepts a user-supplied empirical or machine-learning GMM on any tectonic region type of the published tree, and adds additional features that existing web services omit: conditional spectra, deterministic scenarios, surface hazard, per-building loss, retrofit comparison, and record selection with waveform retrieval. The proposed design layers transfer to other regional models, and to other hazards.
Sources
- From Research Question to Scientific Workflow: Leveraging Agentic AI for Science Automation
- An LLM Agent for Automatic Geospatial Data Analysis
- Securing the Model Context Protocol (MCP): Risks, Controls, and Governance
- A Lightweight Large Language Model-Based Multi-Agent System for 2D Frame Structural Analysis
- Agentic AI for Scientific Discovery: A Survey of Progress, Challenges, and Future Directions
- Model Context Protocol (MCP) Tool Descriptions Are Smelly! Towards Improving AI Agent Efficiency with Augmented MCP Tool Descriptions
- Model Context Protocol (MCP): Landscape, Security Threats, and Future Research Directions
- CLIMATEAGENT: Multi-Agent Orchestration for Complex Climate Data Science Workflows
- LLMs as World Models: Data-Driven and Human-Centered Pre-Event Simulation for Disaster Impact Assessment
- Mitigating Hallucination in Large Language Models: A Capability-Oriented Survey on RAG, Reasoning, and Agentic Systems
- Automating Structural Engineering Workflows with Large Language Model Agents
- LLM-based Agents Suffer from Hallucinations: A Survey of Taxonomy, Methods, and Directions
- Experiences with Model Context Protocol Servers for Science and High Performance Computing
- BioinfoMCP: A Unified Platform Enabling MCP Interfaces in Agentic Bioinformatics
- AQUAH: Automatic Quantification and Unified Agent in Hydrology
Related papers
- Physically-based dimensionless features for pluvial flood mapping with machine learning
- Correlative Microstructural Analysis of a Weathered Nantan Meteorite Fragment
- A General-Purpose Diversified 2D Seismic Image Dataset from NAMSS
- Physics-informed extreme learning machine for Terzaghi consolidation problems and interpretation of coefficient of consolidation based on CPTu data