Emission-GPT: A domain-specific language model agent for knowledge retrieval, emission inventory and data analysis

2025-09-28

AI Summary

Air pollution and climate change research are hindered by fragmented emission knowledge, inefficient data access, and barriers to domain understanding for non-experts. To address these challenges, we propose a knowledge-enhanced large language model (LLM) agent tailored for atmospheric emissions. The agent integrates a structured knowledge base comprising over 10,000 domain-specific publications, a curated emissions knowledge graph, modular prompt engineering, and question-completion techniques. It enables natural-language-driven emission data retrieval, inventory analysis, source contribution attribution, and scenario factor recommendation. Our architecture achieves end-to-end automation of emission analysis: in a Guangdong Province case study, it accurately identified point-source spatial distributions and sectoral trends while substantially improving data processing efficiency. The framework establishes a scalable, user-friendly paradigm for intelligent emission inventory compilation and policy-relevant scenario assessment.

Technology Category

• Data Mining & Knowledge Management: Linked Open Data, Knowledge Graphs & KB Completion
• Cognitive Modeling & Cognitive Systems: Agent Architectures
• Machine Learning: Large Multimodal Models (LMMs)

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Search and Retrieval-Augmented AI: Search Tool Learning with LLM: Teaching LLMs to invoke search and make use of retrieved information

Abstract

Improving air quality and addressing climate change relies on accurate understanding and analysis of air pollutant and greenhouse gas emissions. However, emission-related knowledge is often fragmented and highly specialized, while existing methods for accessing and compiling emissions data remain inefficient. These issues hinder the ability of non-experts to interpret emissions information, posing challenges to research and management. To address this, we present Emission-GPT, a knowledge-enhanced large language model agent tailored for the atmospheric emissions domain. Built on a curated knowledge base of over 10,000 documents (including standards, reports, guidebooks, and peer-reviewed literature), Emission-GPT integrates prompt engineering and question completion to support accurate domain-specific question answering. Emission-GPT also enables users to interactively analyze emissions data via natural language, such as querying and visualizing inventories, analyzing source contributions, and recommending emission factors for user-defined scenarios. A case study in Guangdong Province demonstrates that Emission-GPT can extract key insights--such as point source distributions and sectoral trends--directly from raw data with simple prompts. Its modular and extensible architecture facilitates automation of traditionally manual workflows, positioning Emission-GPT as a foundational tool for next-generation emission inventory development and scenario-based assessment.

Problem

• Addresses fragmented specialized emission knowledge access
• Enables interactive natural language emission data analysis
• Automates manual emission inventory workflows using AI

Innovation

• Domain-specific language model for emission knowledge retrieval
• Integrates prompt engineering with curated document knowledge base
• Enables interactive data analysis via natural language queries