IonSense-QKG ranks battery datasets for quantum-ready machine learning
New framework scores lithium-ion battery datasets on quantum feasibility for hybrid ML.
Public lithium-ion battery datasets are critical for state-of-health estimation, remaining-useful-life prediction, and safety research, but they vary widely in chemistry, modality, scale, and preprocessing complexity. This heterogeneity makes it difficult to determine which datasets are suitable for emerging hybrid quantum-classical machine learning workflows. IonSense-QKG addresses this by building on the EV-Battery-IonSense index and enriching metadata with quantum-specific fields: task type, sensing modality, chemistry, label availability, sequence type, preprocessing requirements, candidate quantum encodings, estimated qubit range, and NISQ feasibility. A novel Quantum Readiness Score provides a transparent heuristic—not a claim of quantum advantage—to rank datasets for near-term quantum battery benchmarks.
IonSense-QKG also enables query-based discovery over the enriched metadata, allowing researchers to find datasets suitable for compact quantum feature maps, quantum time-series analysis, and limited-label anomaly detection. The released artifact includes metadata tables, scoring scripts, robustness checks, link-checking utilities, and SQL-style query examples. By framing dataset selection as a data-management problem, IonSense-QKG offers a reproducible foundation for data-centric quantum battery analytics, helping the community rapidly identify viable resources for future hybrid quantum-classical experiments.
- Metadata enriched with task type, chemistry, qubit range, and NISQ feasibility.
- Quantum Readiness Score acts as a heuristic to select datasets for hybrid benchmarks.
- Released artifact includes scoring scripts, robustness checks, and SQL queries.
Why It Matters
Helps researchers quickly identify suitable battery datasets for near-term quantum machine learning experiments.