TianJi-Environ: An Autonomous AI Scientist for Atmospheric Environmental Research

2026-06-05

AI Summary

This study addresses the long-standing reliance on expert intuition in validating atmospheric chemical mechanisms, which has lacked automated, structured, and auditable methodologies. To overcome this limitation, the authors introduce a novel multi-agent framework built upon WRF-Chem that automatically translates mechanistic hypotheses into executable experimental configurations, testing protocols, and evidentiary criteria, thereby enabling explicit, structured, and reproducible mechanism validation. Integrating multi-agent collaboration, automated experiment orchestration, and evidence-based reasoning, the system demonstrates its analytical capability in complex processes such as aerosol–radiation–boundary layer coupling and NOx response. Its effectiveness is validated through case studies of ozone formation over the North China Plain and PM2.5 dynamics in the Guanzhong Basin, where it successfully identifies critical gaps in mechanistic evidence.

Abstract

As atmospheric environmental prediction continues to improve, interpretable validation of pollution mechanisms and feedback processes has become a main challenge in atmospheric chemistry. Yet mechanism validation based on complex numerical models still relies heavily on expert knowledge: mechanistic hypotheses must be operationalized into executable experiments, and model outputs must be organized into traceable evidence. We present TianJi-Environ, an auditable AI Scientist for atmospheric-chemistry mechanism validation. TianJi-Environ establishes the first WRF-Chem-based multi-agent framework that autonomously drives complex atmospheric-chemistry simulations, converting mechanistic hypotheses into executable configurations, testing experiments, and evidence criteria. Using ozone response and particulate-matter feedback as two representative examples, we demonstrate TianJi-Environ's capability for mechanism validation. In a summertime ozone case over the North China Plain, the system detects directionally consistent aerosol-radiation-interaction signals in shortwave radiation and boundary-layer height, but judges the evidence for ozone response to NOx control to be incomplete. In a wintertime PM2.5 case over the Guanzhong Basin, it localizes the unsupported link to insufficient propagation from black-carbon perturbation to particulate response and missing diagnostics of vertical absorptive heating. These results show that TianJi-Environ makes expert-driven mechanism validation explicit, structured, and auditable, offering a reproducible paradigm for multi-agent systems coupled with complex atmospheric-chemistry models.

Problem

• mechanism validation
• atmospheric chemistry
• interpretable validation
• pollution feedback
• numerical modeling

Innovation

• multi-agent system
• WRF-Chem
• mechanism validation
• interpretable AI
• atmospheric chemistry