Published October 23, 2026 | Version 1.0.0

Minimal numerical reproducibility package for "From Short-Window Battery Reserve Estimation to Operational Decisions: Accuracy, Uncertainty, and Reliability under Domain Shift"

  • 1. Ural Federal University named after the first President of Russia B. N. Yeltsin

Description

This package accompanies the manuscript “From Short-Window Battery Reserve Estimation to Operational Decisions: Accuracy, Uncertainty, and Reliability under Domain Shift.” It provides a minimal numerical reproducibility resource containing analysis code, configurations, source manifests, saved NASA-derived numerical inputs, and verification controls.

The documented numerical replay reconstructs the included NASA analyses without model training or uncertainty recalibration. Its scope includes capacity estimation, empirical uncertainty intervals, remaining backup-time estimation, operational decisions, robustness analyses, grouped feature ablation, chronological performance summaries, cutoff diagnostics, and numerical checks of selected discharge curves.

Original raw datasets, fitted model binaries, manuscript files, and figure-layout reproduction are excluded. Orbital-derived numerical materials and mixed NASA/Orbital history tables are withheld pending clarification of redistribution conditions; source identifiers, acquisition instructions, and analysis code are retained. The full workflow from raw data through model training was not rerun during package verification. README.md, REPRODUCIBILITY.md, and RESULTS_MAP.csv document the supported scope and limitations.

The original study software and its accompanying original documentation are licensed under the MIT License. This license does not cover the underlying third-party datasets or the included numerical materials.

NASA dataset attribution: B. Saha and K. Goebel (2007). Battery Data Set. NASA Prognostics Data Repository, NASA Ames Research Center, Moffett Field, CA.

Files

battery_reserve_reproducibility_v1.0.0.zip

Files (11.1 MB)

Name Size
md5:7303dae2ccd70227e2ba1fcb41d1a139
11.1 MB Preview Download

Additional details

Software

Programming language
Python