Input
EIS spectra
Output
SoC / SoH insights
Value
Interpretable ML
A compact, scalable framework for advanced battery diagnostics that connects measurable electrochemical behaviour with explainable machine-learning outputs.
What is Nevora
A smarter way to understand battery health in real time
NEVORA combines electrochemical impedance spectroscopy with interpretable machine learning to deliver scalable, physics-informed battery diagnostics for research and advanced battery management systems.
Diagnostic intelligence built on electrochemistry, data science, and interpretability
NEVORA (Network-based Evaluation for On-line Reliability Assessment of batteries) is a diagnostic software platform that combines electrochemical impedance spectroscopy (EIS) with machine learning to enable real-time, interpretable monitoring of battery performance and health. Traditional battery management systems rely mainly on voltage and current measurements, which often struggle to accurately determine state of charge (SoC) and state of health (SoH) under dynamic or aging conditions.
NEVORA addresses this limitation by transforming each impedance spectrum into a compact, physics-informed feature vector that captures frequency-dependent processes inside the battery, such as bulk transport, interfacial reactions, and degradation mechanisms. Using these feature vectors, the platform trains multi-output machine learning models capable of simultaneously predicting key battery metrics such as SoC and cycle number with very high accuracy.
Beyond prediction, NEVORA emphasizes interpretability. Feature-importance analysis links specific frequency ranges in the impedance spectrum to underlying physical and electrochemical processes, helping users understand why a prediction is made rather than treating the model as a black box.
Core capabilities
Built for scientific rigor and practical deployment
Physics-informed
Meaningful features
Each impedance spectrum is transformed into a compact representation linked to transport, interfacial, and degradation processes.
Multi-output ML
Real-time predictions
Simultaneous estimation of battery metrics such as state of charge and cycle-related health indicators with high accuracy.
Interpretability
Explainable diagnostics
Frequency-domain importance analysis helps explain why a prediction is made, making results more actionable for research and engineering teams.
Deployment-ready
Scalable integration
Designed for lightweight operation in next-generation battery management systems, including demanding environments such as solid-state battery platforms.
Why it matters
Better battery monitoring requires more than voltage and current alone
By combining impedance spectroscopy, machine learning, and physical insight into one workflow, NEVORA offers a more reliable path toward advanced monitoring and decision-making.
Designed for real-time operation and lightweight deployment, NEVORA is suitable for integration into next-generation battery management systems, particularly for advanced chemistries such as solid-state batteries where conventional methods fall short.
Its hybrid approach makes the platform valuable not only as a diagnostic tool, but also as a scientific framework for understanding the electrochemical origins of battery behaviour under realistic operating conditions.
This creates a bridge between raw electrochemical measurements and higher-level, explainable intelligence that can support both research workflows and industrial deployment.