Methodology

Validation approach

Use cases are dynamic environments that simultaneously validate the AI and feed it new data across three project phases.

Phase 1

M1–18

Data role

UC partners curate experimental and simulation datasets for SciFM V0 prototyping.

Validation role

Architecture sanity checks — are V0 predictions physically plausible?

Phase 2

M19–36

Data role

Generative engine proposes thousands of candidates; simulation pipeline creates massive new datasets fed back to the KG.

Validation role

Large-scale in-silico screening — millions of virtual candidates across all six use cases.

Phase 3

M37–48

Data role

Lab synthesis results — highest-quality experimental data — close the loop into SciFM V2.

Validation role

Definitive proof — predicted vs measured properties on real physical samples (TRL 4).

Project updates subscription

Get milestones, publications, events, consortium news and other SimuLingua project information — straight to your inbox.

Project coordination

Get in touch with the SimuLingua project.

FLOWPHYS AS coordinates the Horizon Europe action. Reach out for scientific, consortium or press enquiries across our nine partners.

Project enquiries

HORIZON-RIA · GenAI4EU

1 June 2026May 2030

HORIZON-CL4-INDUSTRY-2025-01-DIGITAL-61

Follow the project on our social networks