AI Driven Discovery of Bio Ecological Mediation in Cascading Heatwave Risks
Yiquan Wang, Tin-Yeh Huang, Qingyun Gao, Yuhan Chang, Jialin Zhang
TL;DR
This work tackles the challenge of mapping cascading heatwave risks across climate, ecological, and socioeconomic systems amid fragmented disciplinary knowledge. It introduces HeDA, a multi-agent AI framework that constructs a high-fidelity knowledge graph from 8,111 publications, yielding 70,297 evidence nodes to enable multi-layer risk propagation analysis. Key findings show a bio-ecological mediation effect where biological systems amplify thermal stress into economic losses, and identify latent cross-sector couplings and grey rhino transmission vectors that traditional sectoral models miss. The study provides empirical support for shifting climate adaptation from static, sectoral defenses to dynamic, cross-system resilience, underpinned by an interpretable, data-driven topology of risk and explicit formulas such as $NoveltyScore(P) = \alpha \cdot LF(P) + \beta \cdot CLC(P) + \gamma \cdot IP(P)$ and $L: E -> {Physical, Biological, Social, Economic, CrossLayer}$ to guide risk discovery.
Abstract
Compound heatwaves increasingly trigger complex cascading failures that propagate through interconnected physical and human systems, yet the fragmentation of disciplinary knowledge hinders the comprehensive mapping of these systemic risk topologies. This study introduces the Heatwave Discovery Agent HeDA as an autonomous scientific synthesis framework designed to bridge cognitive gaps by constructing a high fidelity knowledge graph from 8,111 academic publications. By structuring 70,297 evidence nodes, the system exhibits enhanced inferential fidelity in capturing long tail risk mechanisms and achieves a significant accuracy margin compared to standard foundation models including GPT 5.2 and Claude Sonnet 4.5 in complex reasoning tasks. The resulting topological analysis reveals a critical bio ecological mediation effect where biological systems function as the primary non linear amplifiers of thermal stress that transform physical meteorological hazards into systemic socioeconomic losses. We further identify latent functional couplings between theoretically distinct sectors such as the heat induced synchronization of power grid failures and emergency medical capacity saturation. These findings elucidate the dynamics of compound climate risks and provide an empirical basis for shifting adaptation strategies from static sectoral defense to dynamic cross system resilience.
