Newfound Materials provides a physics‑driven AI platform that converts a target inorganic material specification into a lab‑ready synthesis plan within minutes. By combining thermodynamic modeling with curated experimental data, the system evaluates synthetic accessibility, generates and ranks thousands of retrosynthetic routes, and runs virtual experiments to optimize yield and selectivity, reducing costly trial‑and‑error in material discovery.
Funding
Funding not disclosed
Founders
Product
Problem
Developing new inorganic materials often stalls because most candidate compounds fail during experimental synthesis, despite promising computational predictions. Researchers lack efficient tools to assess synthesis feasibility, plan viable experiments, and optimize processing conditions, leading to costly trial‑and‑error cycles.
Solution
Newfound Materials offers a physics‑driven AI platform that transforms a target material specification into a lab‑ready synthesis plan within minutes. By integrating thermodynamic modeling with curated experimental data, the system evaluates synthetic accessibility, generates thousands of retrosynthetic routes, and ranks them based on stability, selectivity, safety, precursor availability, and practical constraints. Virtual experiments simulate reaction outcomes, and optimization algorithms iteratively refine processing parameters to maximize yield and selectivity. The platform thus reduces the need for extensive wet‑lab screening, accelerates discovery, and enables more reliable translation from computational design to physical production.
Target Audience
Primary users are materials scientists, chemists, and R&D teams in industrial and academic settings who need to accelerate inorganic material discovery and scale up synthesis processes.
Features
- Thermodynamic modeling combined with experimental datasets to assess material stability and competing phases
- Retrosynthesis engine that generates and scores thousands of synthesis recipes per target material
- Multi‑criteria evaluation of routes, including selectivity, safety, precursor availability, and practical feasibility
- Virtual experiment simulation to predict yields and selectivity before lab execution
- Adaptive optimization algorithms that learn from data and suggest processing condition adjustments
- Rapid generation of lab‑ready synthesis plans, reducing planning time from weeks to minutes