Research
SimPoly: Simulation of polymers with machine learning force fields derived from first principles
Nature · By Gregor N. C. Simm ·
The Brief
- Researchers present SimPoly, a machine learning force field trained only on quantum-chemical data.
- The force field is reported to reproduce measured polymer properties such as densities and glass transition temperatures.
- The work was published in Nature Communications on 9 November 2026.
Why it matters
It offers a route to simulating polymer materials from first-principles-derived training data rather than empirically fitted parameters, which could help materials scientists predict polymer properties computationally.
Who’s affected
- polymer scientists and materials researchers
- computational chemists running molecular dynamics simulations
- #polymers
- #machine learning
- #force fields
- #molecular dynamics
- #materials science
Nature Communications, Published online: 09 November 2026; doi:10.1038/s41467-026-78736-x The authors develop a machine learning force field trained only on quantum-chemical data that can reproduce measured key polymer properties such as densities and glass transition…
Timeline
SimPoly study published online in Nature Communications
nature.com
SimPoly: Simulation of polymers with machine learning force fields derived from first principles