AlloyInter: Visualising Alloy Mixture Interpolations in t-SNE Representations
This work addresses visualization challenges for materials researchers, but it appears incremental as it builds on prior XAI and manifold learning methods.
The paper tackles the problem of exploring input mixtures and output parameters in materials science by proposing AlloyInter, a system that enables users to discover mixture ratios through iterative adjustments toward specified goals, using a learned model ensemble and XAI techniques.
This entry description proposes AlloyInter, a novel system to enable joint exploration of input mixtures and output parameters space in the context of the SciVis Contest 2025. We propose an interpolation approach, guided by eXplainable Artificial Intelligence (XAI) based on a learned model ensemble that allows users to discover input mixture ratios by specifying output parameter goals that can be iteratively adjusted and improved towards a goal. We strengthen the capabilities of our system by building upon prior research within the robustness of XAI, as well as combining well-established techniques like manifold learning with interpolation approaches.