README.md

metadata

title: ISOMORPH Supply Chain Digital Twin
emoji: 🏭
colorFrom: blue
colorTo: indigo
sdk: gradio
sdk_version: 5.7.1
app_file: app.py
pinned: false
python_version: '3.11'

ISOMORPH Supply Chain Digital Twin

Interactive simulation environment for stress-testing supply chains under demand shocks, disruptions, and cascading transport congestion.

ISOMORPH is a stochastic digital twin of a 13-node multi-echelon US logistics network. Configure parameters, run the simulation, and observe how local operational decisions propagate through the network over time.

What you can explore

• 🗺️ Network Map — animated shipment propagation across the US network; nodes colored by backlog stress, moving dots colored by SKU. Export as an animated GIF.
• 📊 Node Detail — per-node time series of inventory, backlog, inflow, outflow, and demand with disruption event markers.
• 📈 Bullwhip — tier-level amplification chart (B = Var(inflow) / Var(outflow)); shows how demand variability grows upstream through the network.
• 🔥 Edge Util — heatmap of daily shipping-lane utilization; highlights congestion and disruption events.
• ⬇️ Download — full CSV export of all state variables for every node, item, and day.

Preset scenarios

Preset	What it demonstrates
🟢 Baseline	Mild bullwhip emerging internally from (s, S) ordering and lead-time delays alone
⚡ Demand Shock	Correlated macro shocks and per-item bursts amplify variability upstream
🔴 Disruption	A lane is randomly blocked; goods reroute and a catch-up wave propagates on recovery
📦 Low Capacity	Cascading transport congestion from the last-mile inward; systemic stockouts and extreme bullwhip

Use the preset buttons to instantly load a scenario, then tune individual parameters with the left-panel sliders and click ▶ Run Simulation to re-run.

Paper

ISOMORPH: A Supply Chain Digital Twin for Simulation, Dataset Generation, and Forecasting Benchmarks Zhang et al., 2026 — arXiv:2605.12768

Full simulator and datasets: github.com/tuhinsahai/ISOMORPH

Acknowledgements

This material is based upon work supported by the Defense Advanced Research Projects Agency (DARPA) under Agreement No. HR00112590112. Approved for public release; distribution is unlimited.

Citation

@misc{zhang2026isomorphsupplychaindigital,
      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},
      year={2026},
      eprint={2605.12768},
      archivePrefix={arXiv},
      primaryClass={stat.ML},
      url={https://arxiv.org/abs/2605.12768},
}