Make gas-cost transmission into ammonia and urea visible while separating theoretical European cost, global market benchmarks and future forecasts.
3 · What it produces
Implied NH₃/urea cost, model-market spread, interval forecast and matured track record.
The images come from demonstration runs included in the attached repository and are shown without dates to illustrate workflow structure, method and evidence.
5 · Data, AI/ML/RPA and method
Data and features
TTF, World Bank Pink Sheet, ECB FX, lags/seasonality; explicit HHV/LHV
Calculation / inference
deterministic NH₃/urea chain + Ridge/Gradient Boosting M+1 forecast
Validation
walk-forward, persistence, seasonality, gas-only and physical baselines; MAE/RMSE/bias/coverage/skill
Stack
Python, pandas, scikit-learn, SQLite, Matplotlib
6 · Technical dossier
Operating conditions and declared limitations.
| Compute cadence | Mon–Fri 09:50 Europe/Rome; monthly maturation |
|---|---|
| Planned publication | IT Wed 11:30; EN Wed 20:30 |
| Possible applications | fertilizers, feedstocks, cost pressure and procurement intelligence |
| Research use | lags, elasticity and ML-vs-physical-model comparison |
| Required condition | global benchmark kept distinct from modelled European cost |
| Failure mode | mistaking a global benchmark for European cost or mixing nowcast and forecast |
Interpretation boundary
The global benchmark is not a European spot price, and implied cost does not include every plant, logistics, contract or margin-specific factor.
7 · Verification and further reading