When Does Better Scenario Modelling Improve Financeability? A Decision-Coupled Evaluation for Offshore Wind-to-Hydrogen

Investment decisions for offshore wind-to-hydrogen (W2H) projects are often framed as “better forecasts reduce uncertainty,” but it is less clear when higher-fidelity scenario modelling meaningfully changes a financing decision versus merely narrowing outcome ranges. We address this question using a decision-coupled evaluation that scores forecast skill on propagated economic distributions and links it directly to financeability metrics.

Using 61 years of ERA5 wind data at 150 m hub height, we generate 1000 synthetic 23-year hourly wind scenarios per method and propagate them through a techno-economic model of a 375 MW offshore W2H project (development in 2024, operation in 2026-2050, base hydrogen price €8/kg, discount rate 7%). We compare three probabilistic scenario generators: historical bootstrapping, parametric Weibull fitting, and a calibrated probabilistic long short-term memory (LSTM) sequence model (used as a benchmark rather than architectural novelty).

We evaluate (a) continuous ranked probability score (CRPS) of levelized cost of hydrogen (LCOH), net present value (NPV), and internal rate of return (IRR), (b) decision bandwidths W(Y) = P₉₅(Y) – P₅(Y), (c) threshold-crossing probabilities P_r(NPV>0) and P_r(IRR>10%), and (d) a local elasticity E(Y) = dW(Y)/dCRPS that maps marginal forecast skill to risk-band compression. Finally, we run a financing price sweep to identify the minimum hydrogen offtake price that achieves a 90% probability target for NPV > 0 and the joint target NPV > 0, IRR > 10%.

Results show that improved scenario modelling can substantially reduce economic distribution error and compress risk bands: the LSTM lowers CRPS by 30% for LCOH and NPV and by 25% for IRR versus the best bootstrap/Weibull configurations. However, under base assumptions the financeability thresholds are nearly invariant across methods: the 90%-target required hydrogen price is €7.76-7.78/kg for P_r(NPV>0) and €9.16-9.18/kg for P_r(NPV>0 and IRR>10%), with cross-method spread below €0.02/kg indicates a threshold-saturated regime where better modelling mainly narrows uncertainty rather than shifting the decision boundary. Sensitivity analysis indicates decision value is highest in moderate-margin regimes (roughly €5.5-8/kg) and diminishes at high profitability where models converge.

This work reframes “better scenarios” into an investment-relevant diagnostic: use elasticity and threshold behaviour to identify when modelling improvements will shift financeability versus only compress risk bands, supporting more defensible screening and policy design.