TianJi:An autonomous AI meteorologist for discovering physical mechanisms in atmospheric science

TL;DR

TianJi is an AI system that autonomously drives atmospheric models, conducts literature research, generates hypotheses, and verifies physical mechanisms with minimal human intervention, transforming Earth system science exploration.

Contribution

It introduces TianJi, the first AI meteorologist capable of autonomous scientific hypothesis testing and model verification in atmospheric science using a multi-agent architecture.

Findings

TianJi autonomously conducts experiments in atmospheric scenarios.

It completes complex research tasks within hours without human input.

TianJi provides detailed analysis and validation of physical hypotheses.

Abstract

Artificial intelligence (AI) has achieved breakthroughs comparable to traditional numerical models in data-driven weather forecasting, yet it remains essentially statistical fitting and struggles to uncover the physical causal mechanisms of the atmosphere. Physics-oriented mechanism research still heavily relies on domain knowledge and cumbersome engineering operations of human scientists, becoming a bottleneck restricting the efficiency of Earth system science exploration. Here, we propose TianJi - the first "AI meteorologist" system capable of autonomously driving complex numerical models to verify physical mechanisms. Powered by a large language model-driven multi-agent architecture, TianJi can autonomously conduct literature research and generate scientific hypotheses. We further decouple scientific research into cognitive planning and engineering execution: the meta-planner interprets hypotheses and devises experimental roadmaps, while a cohort of specialized worker agents collaboratively complete data preparation, model configuration, and multi-dimensional result analysis. In two classic atmospheric dynamic scenarios (squall-line cold pools and typhoon track deflections), TianJi accomplishes expert-level end-to-end experimental operations with zero human intervention, compressing the research cycle to a few hours. It also delivers detailed result analyses and autonomously judges and explains the validity of the hypotheses from outputs. TianJi reveals that the role of AI in Earth system science is transitioning from a "black-box predictor" to an "interpretable scientific collaborator", offering a new paradigm for high-throughput exploration of scientific mechanisms.