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

2026-03-29

AI Summary

Traditional AI-based weather forecasting largely relies on statistical fitting, which struggles to uncover the underlying physical causal mechanisms of atmospheric processes; meanwhile, existing mechanistic studies depend heavily on expert intuition, resulting in low efficiency. This work proposes TianJi, the first autonomous “AI meteorologist” system, built upon a large language model–driven multi-agent architecture that decouples cognitive planning from engineering execution. TianJi autonomously conducts the full scientific workflow—from literature review and hypothesis generation to experimental design, numerical simulation, and result analysis. For the first time, it enables AI to independently validate physical mechanisms using complex numerical models, achieving expert-level mechanistic verification within hours—without human intervention—in case studies involving squall-line cold pools and typhoon track deflection. By generating interpretable reports, TianJi transforms AI from a “black-box predictor” into an “explainable scientific collaborator,” establishing a new paradigm for high-throughput exploration of atmospheric mechanisms.

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.

Problem

• physical mechanisms
• atmospheric science
• AI meteorologist
• scientific discovery
• Earth system science

Innovation

• AI meteorologist
• multi-agent architecture
• autonomous scientific discovery
• physical mechanism verification
• large language model