ISOMORPH: A Supply Chain Digital Twin for Simulation, Dataset Generation, and Forecasting Benchmarks
Abstract
Open time-series forecasting (TSF) benchmarks cover retail, energy, weather, and traffic, but supply-chain logistics remains underserved. We introduce ISOMORPH, the first public digital twin of a multi-echelon logistics network with interpretable, user-configurable parameters and modular topology, demand, and control rules. The simulator advances a directed routing graph in discrete time: demand is served from inventory or recorded as backlog and triggers replenishment throughout the network. The state tracks inventory, outstanding orders, in-transit shipments, and a smoothed demand estimate, yielding Markovian dynamics on a tractable state space. The released data reproduces the bullwhip effect at empirically consistent magnitudes, while three conservation laws provide verification tools for simulator extensions. We release datasets at two catalogue scales (C=50 and C=200), with a 33-rollout scenario library at C=50. These datasets exhibit dynamics largely absent from fixed TSF benchmarks, including variance amplification, cascading bottlenecks, regime shifts, and cross-channel coupling through shared macro shocks. Zero-shot evaluation of three foundation models (Chronos, Moirai, TimesFM) against three in-domain-trained baselines (ARIMA, ETS, PatchTST) spans four targets: demand, backlog, fill rate, and edge utilization. Comparison with ETTh1, Electricity, and Weather shows that ISOMORPH introduces forecasting regimes that differ from standard real-world TSF benchmarks, positioning it as a complementary, regenerable logistics-domain benchmark. The same pairing produces forecast confidence bands across scenario configurations, providing forward UQ from parameter uncertainty and demonstrating foundation models as fast surrogates for digital-twin-based UQ. Code (MIT): https://github.com/tuhinsahai/ISOMORPH. Interactive demo: https://huggingface.co/spaces/HyeminGu/ISOMORPH-demo.
Related
- Just for FUNS: LLM-Guided Spatio-Temporal Graph Node Generation for Forecasting Unobserved Node States
- Active learning confidence measures for coupling strategies in digital twins integrating simulation and data-driven submodels
- Sparse-Observation Atmospheric Thermal Forecasting with Physics-Informed Neural Networks for Climate-Aware Digital Twins
- How Reusable Are Benchmarks with Richer Feedback?
- When Predictive Fit Misleads: Selecting Marketing Mix Models Using Experimental RoAS Benchmarks
BibTeX
@misc{zhang2026isomorph,
title = {{ISOMORPH: A Supply Chain Digital Twin for Simulation, Dataset Generation, and Forecasting Benchmarks}},
author = {Zhizhen Zhang and Hyemin Gu and Benjamin J. Zhang and Daniel Elenius and Michael Tyrrell and Theo J. Bourdais and Houman Owhadi and Markos A. Katsoulakis and Tuhin Sahai},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2605.12768},
eprint = {2605.12768},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2605.12768},
}
RIS
TY - UNPB
TI - ISOMORPH: A Supply Chain Digital Twin for Simulation, Dataset Generation, and Forecasting Benchmarks
AU - Zhizhen Zhang
AU - Hyemin Gu
AU - Benjamin J. Zhang
AU - Daniel Elenius
AU - Michael Tyrrell
AU - Theo J. Bourdais
AU - Houman Owhadi
AU - Markos A. Katsoulakis
AU - Tuhin Sahai
PY - 2026
DA - 2026/09/18
PB - arXiv
DO - 10.48550/arxiv.2605.12768
UR - https://arxiv.org/abs/2605.12768
AB - Open time-series forecasting (TSF) benchmarks cover retail, energy, weather, and traffic, but supply-chain logistics remains underserved. We introduce ISOMORPH, the first public digital twin of a multi-echelon logistics network with interpretable, user-configurable parameters and modular topology, demand, and control rules. The simulator advances a directed routing graph in discrete time: demand is served from inventory or recorded as backlog and triggers replenishment throughout the network. The state tracks inventory, outstanding orders, in-transit shipments, and a smoothed demand estimate, yielding Markovian dynamics on a tractable state space. The released data reproduces the bullwhip effect at empirically consistent magnitudes, while three conservation laws provide verification tools for simulator extensions. We release datasets at two catalogue scales (C=50 and C=200), with a 33-rollout scenario library at C=50. These datasets exhibit dynamics largely absent from fixed TSF benchmarks, including variance amplification, cascading bottlenecks, regime shifts, and cross-channel coupling through shared macro shocks. Zero-shot evaluation of three foundation models (Chronos, Moirai, TimesFM) against three in-domain-trained baselines (ARIMA, ETS, PatchTST) spans four targets: demand, backlog, fill rate, and edge utilization. Comparison with ETTh1, Electricity, and Weather shows that ISOMORPH introduces forecasting regimes that differ from standard real-world TSF benchmarks, positioning it as a complementary, regenerable logistics-domain benchmark. The same pairing produces forecast confidence bands across scenario configurations, providing forward UQ from parameter uncertainty and demonstrating foundation models as fast surrogates for digital-twin-based UQ. Code (MIT): https://github.com/tuhinsahai/ISOMORPH. Interactive demo: https://huggingface.co/spaces/HyeminGu/ISOMORPH-demo.
ER -