Enhanced Performance of Protonic Ceramic Electrolysis Cells with ML-Designed Anode

A dataset from a 2026 study presents experimental results for enhancing protonic ceramic electrolysis cells (PCECs). It was created by Xuan Li and shared on figshare under a CC-BY-NC-4.0 license. The data likely contains performance metrics for cells with a machine-learning-screened anode material and an optimized fabrication process.

Use Cases

• Benchmarking electrochemical performance based on anode material composition mentioned in the description
• Training models to predict cell performance based on fabrication parameters like sintering temperature
• Analyzing the relationship between material properties (e.g., proton concentration, oxygen vacancies) and cell output metrics
• Validating machine-learning-assisted material discovery workflows for energy devices

Strengths

• Includes specific performance metrics, such as a current density of 1.74 A cm–2 at 1.3 V and an area-specific resistance of 0.04 Ω cm–2
• Describes a closed-loop machine-learning/experimental strategy, suggesting a structured methodological approach
• The dataset is small (51.7 KB), facilitating quick download and initial exploration

Limitations

• Column-level documentation is absent; field semantics must be inferred after download
• Row count is unknown, which may limit suitability assessment
• The dataset's scope is limited to the specific materials and processes described in the single study

Provenance

Source

figshare

Collection Method

Experimental results from a scientific study on protonic ceramic electrolysis cells.

Freshness

Last updated 2026-05-07 11:37:59; freshness should be verified