Causal Transformers Reveal Disruption Cascades in Critical Mineral Supply Networks
Academic Journal of Management Science and Engineering · 2026
DOI: 10.62051/ajmse.v1n2.06 ↗Kurz gefasst
Fachartikel in der Zeitschrift Academic Journal of Management Science and Engineering, 2026. Verfasst von Zhongkai Xie. Die Arbeit nennt 32 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0).
Abstract (Originalsprache)
Critical mineral supply chains—encompassing lithium, cobalt, and rare earth elements (REE)—underpin the global clean energy transition yet remain acutely vulnerable to multi-tier disruption cascades. Existing forecasting frameworks based on recurrent architectures or static Bayesian networks capture sequential dependencies but fail to distinguish genuine causal pathways from spurious temporal correlations, limiting their capacity to identify which network nodes amplify shocks across tiers. This paper introduces a causal Transformer (CT) architecture that integrates multi-head attention with a structural causal model (SCM) layer constrained by a directed acyclic graph (DAG) encoding domain knowledge. Applied to a four-tier network spanning extraction, processing, intermediate manufacturing, and end-use assembly for lithium-ion battery and permanent-magnet supply chains, the CT achieves F1 scores of 0.823–0.891 for cascade onset detection and a mean absolute error (MAE) of 0.97–1.31 tiers for propagation depth, outperforming long short-term memory (LSTM), gated recurrent unit (GRU), standard Transformer, and static Bayesian network baselines. Causal attribution identifies processing-tier geographic concentration as the dominant cascade amplifier, with Democratic Republic of Congo cobalt refining and Chinese REE separation collectively responsible for 63% of detected cascade events. Results carry direct policy implications, arguing for strategic stockpiling calibrated to processing-tier inventory compression cycles rather than extraction-tier geological events.
Zitieren
APA
Xie, Z. (2026). Causal Transformers Reveal Disruption Cascades in Critical Mineral Supply Networks. Academic Journal of Management Science and Engineering. https://doi.org/10.62051/ajmse.v1n2.06
Vancouver
Xie Z. Causal Transformers Reveal Disruption Cascades in Critical Mineral Supply Networks. Academic Journal of Management Science and Engineering. 2026. doi:10.62051/ajmse.v1n2.06
BibTeX
@article{Xie2026,
author = {Xie, Zhongkai},
title = {Causal Transformers Reveal Disruption Cascades in Critical Mineral Supply Networks},
journal = {Academic Journal of Management Science and Engineering},
year = {2026},
doi = {10.62051/ajmse.v1n2.06}
}
EUVIMED