DSL Masters / NRF Sprint
Research discussion feedback note
This note is a thinking guide from your research discussion. It is not a proposal draft, not a decision, and not something to paste into an AI tool. Use it to think before you rewrite.
How To Use This
Read it once, close the page, and answer the questions in rough bullets. The goal is to make your own reasoning clearer before the next version of your NRF application.
What you are trying to do
You are exploring whether an expensive biomedical simulation workflow can be made more useful by running the simulation work across multiple computing nodes and then using the results to support a faster surrogate model. The practical context is wound-healing simulation, but the deeper research direction is about computational speed, fidelity, and what can be learned from a carefully bounded simulation workflow.
What is strong
You are already thinking beyond simply building a tool. The useful part of your direction is that it can ask whether a multi-node workflow changes what researchers can test, how quickly they can test it, and how much accuracy is retained when a faster model is introduced. That gives the project a real evidence path.
Main issue
The project must not become a clinical, biological, high-performance-computing, and AI project all at once. The main knot is choosing the intellectual centre. Is the contribution the parallel simulation workflow, the surrogate-model fidelity, or the biomedical insight? Choose one centre and keep the others as context.
Three thinking questions
- What exact wound-healing process, simulator, input variables, and output variables will you use as the smallest useful test case?
- What simple baseline will show whether the multi-node or surrogate route adds value beyond a standard simulation workflow?
- What result can you defend using simulation evidence without claiming that the work proves clinical effectiveness?
What to do next
Write rough bullets that define the simulator, the compute route, the baseline, the accuracy or runtime checks, and the claim you are not going to make. Keep it as a boundary note before you rewrite the NRF text.