Predicting Rare Earth Elements Concentration in Coal Ashes with Multi-Task Neural Networks
Preprint
- 24 October 2022
- preprint
- Published by Springer Nature in Research Square
Abstract
The increasing demand for rare earth elements (REEs) makes them a scarce strategic resource for technical developments. In that regard, harvesting REEs from coal ashes—a waste byproduct from coal power plants—offers an alternative solution to conventional ore-based extraction. However, this approach is bottlenecked by our ability to screen coal ashes bearing large concentrations of REEs from feedstocks—since measuring the REE content in ashes is a time-consuming and costly task requiring advanced analytical tools. Here, we propose a machine learning approach to predict the REE contents based on the bulk composition of coal ashes (which is easily measurable under the current testing protocol). We introduce a multi-task neural network that simultaneously predicts the contents of different REEs and, importantly, exhibits notably improved accuracy than the single-task models. Further model analyses reveal key data patterns for screening coal ashes with high REE concentrations.Teaser: With machine learning, high-throughput screening of REE-bearing coal ashes can be fulfilled based on a simple measurement.Keywords
All Related Versions
- Version 1, 2022-10-24, Research Square
- Published version: Materials Horizons, 11 (6), 1448.
This publication has 48 references indexed in Scilit:
- On-the-fly machine-learning for high-throughput experiments: search for rare-earth-free permanent magnetsScientific Reports, 2014
- Rare Earth Elements Supply Restrictions: Market Failures, Not Scarcity, Hamper Their Current Use in High-Tech ApplicationsEnvironmental Science & Technology, 2014
- An investigation into six coal fly ashes from the United Kingdom and Poland to evaluate rare earth element contentFuel, 2014
- Can a dysprosium shortage threaten green energy technologies?Energy, 2013
- Coal deposits as potential alternative sources for lanthanides and yttriumInternational Journal of Coal Geology, 2012
- Evaluating Rare Earth Element Availability: A Case with Revolutionary Demand from Clean TechnologiesEnvironmental Science & Technology, 2012
- Heavy Metal Pollution Index of Ground Water of an Abandoned Open Cast Mine Filled with Fly Ash: a Case StudyMine Water and the Environment, 2008
- Predicting coal ash fusion temperature based on its chemical composition using ACO-BP neural networkThermochimica Acta, 2007
- Recursive feature elimination with random forest for PTR-MS analysis of agroindustrial productsChemometrics and Intelligent Laboratory Systems, 2006
- Review and comparison of methods to study the contribution of variables in artificial neural network modelsEcological Modelling, 2003