Data-Driven Prediction-Route Coupling Optimization for Cold Chain Logistics
International Journal of Information Systems and Supply Chain Management · 04.11.2026 · 19 (1) · 1-25
DOI: 10.4018/ijisscm.426647 ↗Kurz gefasst
Fachartikel in der Zeitschrift International Journal of Information Systems and Supply Chain Management, erschienen am 04.11.2026. Verfasst von Haipeng Mo und 2 weiteren Autor:innen. Die Arbeit nennt 37 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 3.0).
Abstract (Originalsprache)
Fresh-product cold-chain logistics suffers high commodity losses and poor cross-link dynamic coordination, since demand prediction and vehicle routing are often decoupled in practice. This study developed a data-driven prediction-route coupling optimization framework for proactive intelligent distribution scheduling. A convolutional neural network–long short-term memory–attention model captured spatiotemporal demand dependencies to boost prediction accuracy under nonlinear, volatile conditions. Using the Arrhenius equation for freshness decay, the study formulated a dynamic vehicle routing model to minimize generalized total cost, covering transportation, refrigeration, cargo-damage costs, and time-window penalties. Tested on real enterprise operational data, the experiments suggested that the hybrid prediction model reduced forecast errors. Under the stated experimental settings, the coupled framework cut operational cost and mitigated cargo loss. It improved distribution resilience against high-temperature disruptions and provided a feasible reference for information-driven cold-chain intelligent decision-support systems.
Zitieren
APA
Mo, H., Song, M., & Wang, X. (2026). Data-Driven Prediction-Route Coupling Optimization for Cold Chain Logistics. International Journal of Information Systems and Supply Chain Management, 19(1), 1-25. https://doi.org/10.4018/ijisscm.426647
Vancouver
Mo H, Song M, Wang X. Data-Driven Prediction-Route Coupling Optimization for Cold Chain Logistics. International Journal of Information Systems and Supply Chain Management. 2026;19(1):1-25. doi:10.4018/ijisscm.426647
BibTeX
@article{Mo2026,
author = {Mo, Haipeng and Song, Meijing and Wang, Xuping},
title = {Data-Driven Prediction-Route Coupling Optimization for Cold Chain Logistics},
journal = {International Journal of Information Systems and Supply Chain Management},
year = {2026},
volume = {19},
number = {1},
pages = {1--25},
doi = {10.4018/ijisscm.426647}
}
EUVIMED