Machine learning prediction of bismuth recovery from literature data: publication-grouped validation, anchored calibration and chemical interpretation
- 1Centre for Materials for Electronics Technology (C-MET
- 2Ministry of Electronics and Information Technology (MeitY
Abstract
Machine learning models trained on published leaching data often report high accuracy from random splits that place runs of one study in both training and test sets. This study tested whether reported operating conditions can predict bismuth recovery for a study that the model has not seen. A data set of 485 runs from 82 sources was compiled across six unit operations; runs designed to retain bismuth, plate part of a bath or recover another metal were set aside, leaving 375 recovery runs from 72 studies. Thirteen models, including a mean baseline, were compared under random, publication-grouped and feedstock-grouped validation, and six of them under temporal validation. Random splits gave R2 up to 0.57, whereas publication-grouped validation gave at most 0.09 (95% interval −0.22 to 0.28); about half of the residual variance lay between publications. Three measured runs from a new study raised R2 for its remaining runs from about zero to 0.48, and Gaussian-process predictions were positively rank-correlated with measured recovery in 83% of studies. Within studies, recovery rose with acid concentration and temperature, although the temperature trend tended to reverse across studies. Literature data can therefore rank conditions for a new feed, but absolute prediction needs a few local measurements; an offline browser tool that applies this approach to leaching is provided.
Related
- Publication-block calibration reveals wide uncertainty in PLGA release endpoint prediction
- Literature-Scale Mössbauer Data Enable Prediction, Electronic-State Interpretation, and Chemical Insight in Molecular Iron Chemistry
- 3DRISM Solvation for Accurate and Large-Scale Protein Hydration Prediction and Mechanistic Interpretation
- Hierarchical Multimodal Large Language Model-Based Interpretation and Aggregation of PDP and ICE Explanations for Battery State-of-Charge Prediction in Electric Vehicles
- Bridging the Literature-to-Laboratory Gap with Language Models and Active Learning for Reaction Feasibility Prediction and Autonomous Exploration
BibTeX
@misc{rapaka2026machine,
title = {{Machine learning prediction of bismuth recovery from literature data: publication-grouped validation, anchored calibration and chemical interpretation}},
author = {Subash Chandra Bose Rapaka},
howpublished = {ChemRxiv},
year = {2026},
month = oct,
doi = {10.26434/chemrxiv.15010302/v1},
url = {https://chemrxiv.org/doi/full/10.26434/chemrxiv.15010302/v1},
note = {CC BY-NC-ND},
}
RIS
TY - UNPB
TI - Machine learning prediction of bismuth recovery from literature data: publication-grouped validation, anchored calibration and chemical interpretation
AU - Subash Chandra Bose Rapaka
PY - 2026
DA - 2026/10/12
PB - ChemRxiv
DO - 10.26434/chemrxiv.15010302/v1
UR - https://chemrxiv.org/doi/full/10.26434/chemrxiv.15010302/v1
AB - Machine learning models trained on published leaching data often report high accuracy from random splits that place runs of one study in both training and test sets. This study tested whether reported operating conditions can predict bismuth recovery for a study that the model has not seen. A data set of 485 runs from 82 sources was compiled across six unit operations; runs designed to retain bismuth, plate part of a bath or recover another metal were set aside, leaving 375 recovery runs from 72 studies. Thirteen models, including a mean baseline, were compared under random, publication-grouped and feedstock-grouped validation, and six of them under temporal validation. Random splits gave R2 up to 0.57, whereas publication-grouped validation gave at most 0.09 (95% interval −0.22 to 0.28); about half of the residual variance lay between publications. Three measured runs from a new study raised R2 for its remaining runs from about zero to 0.48, and Gaussian-process predictions were positively rank-correlated with measured recovery in 83% of studies. Within studies, recovery rose with acid concentration and temperature, although the temperature trend tended to reverse across studies. Literature data can therefore rank conditions for a new feed, but absolute prediction needs a few local measurements; an offline browser tool that applies this approach to leaching is provided.
ER -