Ilmu Komputer & AI editorial
Machine-learning-assisted material discovery of oxygen-rich highly porous carbon active materials for aqueous supercapacitors
The core problem
Innovation
The authors employed a machine-learning-derived activation strategy to guide the synthesis of highly porous carbons. Key methodological elements include:
- **Machine learning approach**: A data-driven analysis of previously reported research works was used to identify critical features for ideal carbon materials for supercapacitors. The ML model predicted specific capacitance values that guided experimental design.
- **Synthesis**: Sodium amide and cross-linked polymer precursors were used to synthesize highly porous carbons with specific surface areas exceeding 4000 m²/g. The pore size and oxygen content of the carbonaceous materials were tuned.
- **Electrode fabrication**: A highly porous carbon-based electrode with 0.7 mg/cm² of electrode mass loading was prepared.
- **Electrochemical characterization**: Specific capacitance was measured in 1 M H₂SO₄. The charge storage mechanism and electrolyte transport properties were investigated via step potential electrochemical spectroscopy (SPECS) and quasielastic neutron scattering (QENS) measurements.
The methodology integrates ML-guided material discovery with advanced experimental techniques to validate and understand the performance of the synthesized carbons.
Why it matters
Who should read this
Opening member content…