Causal Transformers Reveal Disruption Cascades in Critical Mineral Supply Networks
DOI:
https://doi.org/10.62051/ajmse.v1n2.06Keywords:
Critical Mineral Supply Chains, Causal Transformer, Disruption Cascades, Supply Network Resilience, Multi-Head Attention, Causal InferenceAbstract
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.
Downloads
References
[1] Kim, T. Y., Gould, T., Bennet, S., Briens, F., Dasgupta, A., Gonzales, P., ... & Lagelee, J. (2021). The role of critical minerals in clean energy transitions. International Energy Agency: Washington, DC, USA, 70-71.
[2] Hund, K., La Porta, D., Fabregas, T. P., Laing, T., & Drexhage, J. (2020). Minerals for climate action.
[3] Ivanov, D. (2021). Supply chain viability and the COVID-19 pandemic: a conceptual and formal generalisation of four major adaptation strategies. International journal of production research, 59(12), 3535-3552.
[4] Chen, T., & Ding, J. (2026). Cold Start Latency Optimization Strategies for Function as a Service Platforms. Computer Life, 14(1), 64-73.
[5] Liu, J., Wang, J., Chen, H., Guinness, J., Martin, R., & Kulkarni, C. S. (2019). Optimal Level Crossing Predictions for Electronic Prognostics. In AIAA Scitech 2019 Forum (p. 1962).
[6] Chen, J., Cui, Y., Zhang, X., Yang, J., & Zhou, M. (2024). Temporal convolutional network for carbon tax projection: A data-driven approach. Applied Sciences, 14(20), 9213.
[7] Wei, Z., Sun, T., & Zhou, M. (2024). LIRL: Latent Imagination-Based Reinforcement Learning for Efficient Coverage Path Planning. Symmetry, 16(11), 1537.
[8] Zhang, S., Qiu, L., & Zeng, Z. (2026). Physics-Data Synergy in Structural Health Monitoring: A Multi-Scale Graph Contrastive Framework With Temperature-Adaptive Fusion. IEEE Access.
[9] Zeng, Z., Lin, H., Zhang, S., & Wang, B. (2026). Adaptive Robust Watermarking for Large Language Models via Dynamic Token Embedding Perturbation. IEEE Access, 14, 9319-9339.
[10] Qiu, L. (2025). Multi-Agent Reinforcement Learning for Coordinated Smart Grid and Building Energy Management Across Urban Communities. Computer Life, 13(3), 8-15.
[11] Zhao, W., Chen, T., Yang, J. S., & Qiu, L. (2026). AutoML-Pipeline: A RAG-enhanced code generation framework with pre-validation for cloud-native machine learning workflows. IEEE Access.
[12] Yang, Y., & Yang, J. (2026). Synthetic Data Meets Finance: Generative Models for Privacy Preserving Analytics. Journal of Banking and Financial Dynamics, 10(4), 1-8.
[13] Wang, Z., Shen, Z., Wang, B., & Shang, W. (2025). Modernizing Enterprise Analytics through Low-Code Automation and Cloud-Native Data Architectures. Asian Business Research Journal, 10(12), 20-33.
[14] Zhao, X., Sun, T., Ren, S., Yang, J., & Liu, Y. (2025). RAG-Based AI Agents for Enterprise Software Development: Implementation Patterns and Production Deployment. Frontiers in Artificial Intelligence Research, 2(3), 501-520.
[15] Li, P., Liu, J., & Qiu, L. (2026). Deep Learning Methods for Demand Forecasting and Inventory Optimization in Modern Supply Chains. Asian Business Research Journal, 11(3), 21-29.
[16] Qiu, L. (2025). Reinforcement Learning Approaches for Intelligent Control of Smart Building Energy Systems with Real-Time Adaptation to Occupant Behavior and Weather Conditions. Journal of Computing and Electronic Information Management, 18(2), 32-37.
[17] Zhang, H. (2025). Reinforcement Learning Approaches for Layout Optimization in Electronic Design Automation with Electromagnetic Compatibility Constraints. Frontiers in Robotics and Automation, 2(2), 77-93.
[18] Shen, Z., Zhao, W., Wang, B., Wang, Z., & Shang, W. (2026). CAGR: A Cross-Accelerator Graph Optimization Framework for Efficient Recommender System Inference. IEEE Access.
[19] Sun, T., Wang, M., & Han, X. (2025). Deep Learning in Insurance Fraud Detection: Techniques, Datasets, and Emerging Trends. Journal of Banking and Financial Dynamics, 9(8), 1-11.
[20] Liu, J., Li, P., & Wang, Y. (2026). Graph Neural Networks for Modeling Complex Dependencies in Global Supply Chain Networks. Journal of Computing and Electronic Information Management, 20(3), 9-20.
[21] Zhang, F., & Wu, B. (2025). Large Language Models as General Purpose Intelligence Systems for Reasoning, Planning and Decision Making. American Journal of Artificial Intelligence and Neural Networks, 6(4), 45-72.
[22] Li, P., Ren, S., Zhang, Q., Wang, X., & Liu, Y. (2024). Think4SCND: Reinforcement learning with thinking model for dynamic supply chain network design. IEEE Access, 12, 195974-195985.
[23] Zhang, F., & Yang, J. S. (2025). Learning Driven Decision Intelligence for Autonomous Driving Through Multimodal Understanding World Modeling and Policy Optimization. Frontiers in Artificial Intelligence Research, 2(3), 616-634.
[24] Wang, B., Wang, Z., Zhao, W., & Liu, Y. (2025). Network Fabric Simulation and Validation for Data Center Routing Convergence Under Large-Scale Failure Scenarios. Computer Science Bulletin, 8(01), 310-326.
[25] Xue, R., Zhou, J., Wang, J., Wen, Q., & Zhang, H. (2025, October). Long-Term Forecasting of Atmospheric Water Vapor Using Transformer-Based Architectures and SHAP Explainability. In 2025 6th International Conference on Machine Learning and Computer Application (ICMLCA) (pp. 1181-1184). IEEE.
[26] Liu, Y., Wu, H., Wang, J., & Long, M. (2022). Non-stationary transformers: Exploring the stationarity in time series forecasting. Advances in neural information processing systems, 35, 9881-9893.
[27] Ding, J., Chen, T., & Qin, Y. (2026). Achieving Resource Isolation in Multi-Tenant Cloud Platforms Without Sacrificing Performance. Journal of Computing and Electronic Information Management, 21(1), 10-18.
[28] Ding, J., & Qin, Y. (2026). Raft and Beyond: Practical Consensus Mechanisms for Geo-Distributed Data Systems. Computer Life, 14(1), 54-63.
[29] Mineault, P. (2025). Is Attention All You Need?. In From Human Attention to Computational Attention: A Multidisciplinary Approach (pp. 297-314). Cham: Springer Nature Switzerland.
[30] Alaparthi, S., & Mishra, M. (2021). BERT: a sentiment analysis odyssey: S. Alaparthi, M. Mishra. Journal of Marketing Analytics, 9(2), 118-126.
[31] Wang, Q., Zhou, Q., Lin, J., Guo, S., She, Y., & Qu, S. (2024). Risk assessment of power outages to inter-regional supply chain networks in China. Applied Energy, 353, 122100.
[32] Dolgui, A., Ivanov, D., & Sokolov, B. (2020). Reconfigurable supply chain: the X-network. International journal of production research, 58(13), 4138-4163.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Academic Journal of Management Science and Engineering
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
