Modeling REE interactions by Explainable AIs

Research question
How can interaction within the chemical composition of a REE mineral be assessed linearly, nonlinearly, and multivariable?

As a fundamental-applied project, this study aims to develop a new explainable artificial intelligence (XAI) model and machine learning (ML) algorithm to integrate REE characterization data of different ores into a digitalized platform, which can potentially be used to predict the REE content and their chemical interactions with other elements within the raw material structures. The main goal of this study is to generate and develop a new XAI and a predictive ML model to enhance a robust platform for understanding the magnitude and significance of complex intercorrelations, educating lab operators, reducing potential environmental issues, and assisting sustainable critical raw material production. Such an AI platform can be used for various applications. In other words, as a systematical study, this project will be tightly linked to the field of materials for green development and sustainable and efficient metal recovery in a circular economy.

The project will also be relevant to the different aims of WASP. This structure would help to address the strengths of soft computing models as enabling technologies for the advancement of systems acting in collaboration with humans, adapting control and maintenance systems through sensors, information, and knowledge, and generating intelligent systems for systems to advance Swedish mines into an internationally recognized and leading position not only in the areas of AI, autonomous systems and software but also in the areas of mining, processing and other similar industries such as cement production. All these will engage tightly with various WASP aims.

Sustainability apects
The complexity of ores (the main natural sources of critical raw materials) becomes the basis of several unknown interactions in the ore processing plants. Thus, significant and emerging modeling of elemental interactions within the structure of raw materials would be essential for sustainable development.