Rational design for
next-generation materials.
We are developing an AI-driven discovery engine to help battery cell makers and carbon precursor suppliers optimize hard carbon synthesis: predicting the exact pyrolysis temperature window, pore-opening activation, and edge functionalization to target reversible capacities exceeding 300 mAh/g and improve Initial Coulombic Efficiency (ICE > 85%), aiming to shorten traditional wet-lab trial cycles from 18 months down to 2 months.
Physical synthesis is slow.
Computational screening narrows the search space.
Traditional trial-and-error chemistry requires months of physically baking biomass in furnaces, testing structural properties, and measuring capacity. Each wet-lab iteration takes weeks, representing a costly bottleneck in developing commercial Sodium-Ion energy storage.
By digitizing precursor-to-performance modeling, IONCE aims to help researchers and precursor suppliers evaluate pyrolysis temperatures, pore-opening activation thresholds, and edge chemistry before spending furnace time and material resources.
Synthesis Screening
Stage 1 screening engine mapping precursor pyrolysis parameters to electrochemical performance with empirical prediction intervals.
Curated Materials Atlas
A research index of 141 published hard carbon structures compiled from open-access literature review tables.
Atomistic Physics Visualizer
Stage 2 visualizer exploring turbostratic carbon geometries, defect traps, and interlayer sodium binding.
Explainable Decisions
Transparent model outputs breaking down the exact thermodynamic and stoichiometric variables driving battery capacity.
Two-Stage Architecture
Coupling macroscopic synthesis screening with atomistic first-principles quantum calculations.
Access the Intelligence.
Explore computational screening tools to prioritize experimental synthesis candidates and reduce laboratory iterations.