Assessing static glass leaching predictions from large datasets using machine learning

Lillington, Joseph N.P. and Goût, Thomas L. and Harrison, Mike T. and Farnan, Ian (2020) Assessing static glass leaching predictions from large datasets using machine learning. Journal of Non-Crystalline Solids, 546. p. 120276. ISSN 00223093 DOI

[img] Text
Assessing+static+glass+leaching+predictions+JL+14th_August_2020.pdf - Accepted Version

Download (385kB)
[img] Text
Supplementary+Data+14th+August+2020.pdf - Supplemental Material

Download (93kB)
Official URL:


Radioactive waste vitrified within glass is planned to be ultimately disposed of within a geological disposal facility. This study has applied machine learning to predict static glass leaching using an international experimental database of approximately 450 glasses to train/test various algorithms. Machine learning can accurately predict B, Li, Na, and Si releases for this complex database with Tree-based algorithms (notably ‘BaggingRegressor’ and ‘RandomForestRegressor’ in Python). This is provided that leaching experiment results, including elemental releases, are incorporated within the algorithm training variables, given that this study finds inaccurate prediction solely using initial test parameters as features. The trained algorithms underwent additional testing using an external database with prediction showing worse performance, likely due to substantial MgO and Na2O pristine glass oxide compositional variations across databases, with B releases generally being overestimated and Na underestimated. The use of molar oxide content performed significantly better than weight-fraction oxide for learning.

Item Type: Article
Uncontrolled Keywords: 2020AREP; IA76
Subjects: 03 - Mineral Sciences
Divisions: 03 - Mineral Sciences
08 - Green Open Access
12 - PhD
Journal or Publication Title: Journal of Non-Crystalline Solids
Volume: 546
Page Range: p. 120276
Identification Number:
Depositing User: Sarah Humbert
Date Deposited: 25 Aug 2020 16:24
Last Modified: 08 Jul 2021 00:01

Actions (login required)

View Item View Item

About cookies