# Machine learning pipeline for battery state of health estimation

arXiv: https://arxiv.org/abs/2102.00837 · HTML: https://mlsanity.com/paper/2102.00837/

## Key facts

- Cited by 29 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 90 references that are in the map.
- First posted on arXiv 1 Feb 2021.

## Builds on (most cited first, 9 of 9)

- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles](https://mlsanity.com/paper/1612.01474/) (2016)
- [Accurate Uncertainties for Deep Learning Using Calibrated Regression](https://mlsanity.com/paper/1807.00263/) (2018)
- [Manipulating Machine Learning: Poisoning Attacks and Countermeasures for Regression Learning](https://mlsanity.com/paper/1804.00308/) (2018)
- [EAD: Elastic-Net Attacks to Deep Neural Networks via Adversarial Examples](https://mlsanity.com/paper/1709.04114/) (2017)
- [Confidence Intervals for Random Forests: The Jackknife and the Infinitesimal Jackknife](https://mlsanity.com/paper/1311.4555/) (2013)
- [Correlation and variable importance in random forests](https://mlsanity.com/paper/1310.5726/) (2013)
- [Attacking the Madry Defense Model with L1-based Adversarial Examples](https://mlsanity.com/paper/1710.10733/) (2017)
- [Why walking the dog takes time: Frechet distance has no strongly subquadratic algorithms unless SETH fails](https://mlsanity.com/paper/1404.1448/) (2014)

## Built on by (most cited first, 29 of 29)

- [Uncertainty Quantification in Machine Learning for Engineering Design and Health Prognostics: A Tutorial](https://mlsanity.com/paper/2305.04933/) (2023)
- [Distribution-free risk assessment of regression-based machine learning algorithms](https://mlsanity.com/paper/2310.03545/) (2023)
- [Dynaformer: A Deep Learning Model for Ageing-aware Battery Discharge Prediction](https://mlsanity.com/paper/2206.02555/) (2022)
- [PulseBat: A field-accessible dataset for second-life battery diagnostics from realistic histories using multidimensional rapid pulse test](https://mlsanity.com/paper/2502.16848/) (2025)
- [BatteryLife: A Comprehensive Dataset and Benchmark for Battery Life Prediction](https://mlsanity.com/paper/2502.18807/) (2025)
- [Evaluating feasibility of batteries for second-life applications using machine learning](https://mlsanity.com/paper/2203.04249/) (2022)
- [Adapting Amidst Degradation: Cross Domain Li-ion Battery Health Estimation via Physics-Guided Test-Time Training](https://mlsanity.com/paper/2402.00068/) (2024)
- [Health Index Estimation Through Integration of General Knowledge with Unsupervised Learning](https://mlsanity.com/paper/2405.04990/) (2024)
- [From paper to benchmark: agentic, framework-based reproduction of under-specified methods in machine health intelligence](https://mlsanity.com/paper/2605.28371/) (2026)
- [Lithium-ion Battery Online Knee Onset Detection by Matrix Profile](https://mlsanity.com/paper/2304.00691/) (2023)
- [A Self-attention Knowledge Domain Adaptation Network for Commercial Lithium-ion Batteries State-of-health Estimation under Shallow Cycles](https://mlsanity.com/paper/2304.05084/) (2023)
- [Accurate battery lifetime prediction across diverse aging conditions with deep learning](https://mlsanity.com/paper/2310.05052/) (2023)
- [Diagnostic-free onboard battery health assessment](https://mlsanity.com/paper/2503.07383/) (2025)
- [Fast and Generalizable parameter-embedded Neural Operators for Lithium-Ion Battery Simulation](https://mlsanity.com/paper/2508.08087/) (2025)
- [Multivariate Prediction Intervals for Random Forests](https://mlsanity.com/paper/2205.02260/) (2022)
- [Random Search Hyper-Parameter Tuning: Expected Improvement Estimation and the Corresponding Lower Bound](https://mlsanity.com/paper/2208.08170/) (2022)
- [Toward High-Performance Energy and Power Battery Cells with Machine Learning-based Optimization of Electrode Manufacturing](https://mlsanity.com/paper/2307.05521/) (2023)
- [Depth analysis of battery performance based on a data-driven approach](https://mlsanity.com/paper/2308.15833/) (2023)
- [Health diagnosis and recuperation of aged Li-ion batteries with data analytics and equivalent circuit modeling](https://mlsanity.com/paper/2310.03750/) (2023)
- [Machine Learning based prediction of Vanadium Redox Flow Battery temperature rise under different charge-discharge conditions](https://mlsanity.com/paper/2404.17284/) (2024)
- [Coupling Machine Learning with Ontology for Robotics Applications](https://mlsanity.com/paper/2407.02500/) (2024)
- [Chemistry-aware battery degradation prediction under simulated real-world cyclic protocols](https://mlsanity.com/paper/2504.03701/) (2025)
- [Learning to fuse: dynamic integration of multi-source data for accurate battery lifespan prediction](https://mlsanity.com/paper/2504.18230/) (2025)
- [A Hybrid Physics-Based and Reinforcement Learning Framework for Electric Vehicle Charging Time Prediction](https://mlsanity.com/paper/2512.06287/) (2025)
- [Multiscale Dual-path Feature Aggregation Network for Remaining Useful Life Prediction of Lithium-Ion Batteries](https://mlsanity.com/paper/2512.19719/) (2025)
- [Excluding the Target Domain Improves Extrapolation: Deconfounded Hierarchical Physics Constraints](https://mlsanity.com/paper/2605.07485/) (2026)
- [Charging Phase Health Indicators for Battery State-of-Health Estimation: A Systematic Comparison of CC, CV, and Combined Approaches under Cross-Battery Validation](https://mlsanity.com/paper/2607.23482/) (2026)
- [PiDDM: Physics-Informed Differentiable Degradation Modeling for Lithium-Ion Battery State-of-Health Prediction](https://mlsanity.com/paper/2607.29095/) (2026)
- [Early Cycle Charge Trajectory Generative Prediction and Full Life Cycle Health Management of Iron-Chromium Flow Batteries Based on FlowBD-E1](https://mlsanity.com/paper/2608.14637/) (2026)

## Abstract (arXiv)

Lithium-ion batteries are ubiquitous in modern day applications ranging from portable electronics to electric vehicles. Irrespective of the application, reliable real-time estimation of battery state of health (SOH) by on-board computers is crucial to the safe operation of the battery, ultimately safeguarding asset integrity. In this paper, we design and evaluate a machine learning pipeline for estimation of battery capacity fade - a metric of battery health - on 179 cells cycled under various conditions. The pipeline estimates battery SOH with an associated confidence interval by using two parametric and two non-parametric algorithms. Using segments of charge voltage and current curves, the pipeline engineers 30 features, performs automatic feature selection and calibrates the algorithms. When deployed on cells operated under the fast-charging protocol, the best model achieves a root mean squared percent error of 0.45%. This work provides insights into the design of scalable data-driven models for battery SOH estimation, emphasising the value of confidence bounds around the prediction. The pipeline methodology combines experimental data with machine learning modelling and can be generalized to other critical components that require real-time estimation of SOH.