Toward causal artificial intelligence approach for PM2.5 interpretation: A discovery of structural causal models

Mallika Kliangkhlao, Apaporn Tipsavak, Thanathip Limna, Racha Dejchanchaiwong, Perapong Tekasakul, Kirttayoth Yeranee, Thanyabun Phutson, Bukhoree Sahoh

Abstract: Highlights•Novel causal AI framework advances beyond prediction to reveal underlying PM2.5 formation mechanisms.•Data-driven SCM approach achieves 80 % accuracy in mapping environmental cause-effect relationships•Interpretable results provide evidence-based insights for environmental policymaking and urban air quality management.