AlloyLens: A Visual Analytics Tool for High-throughput Alloy Screening and Inverse Design

2025-11-03

AI Summary

In multi-functional alloy design, the high-dimensional composition–structure–property space is challenging to explore effectively, and existing methods lack robust support for sensitivity analysis and multi-objective trade-off reasoning. To address this, we propose an interactive visual analytics system that innovatively integrates gradient-based sensitivity curves with nearest-neighbor composition recommendations, augmented by coordinated scatterplot matrices (SPLOMs) and dynamic parameter sliders. This framework enables synergistic exploration of both local structural variations and global patterns in simulation data. It visually reveals how minute compositional perturbations affect multiple performance metrics, thereby facilitating inverse design and Pareto-optimal decision-making. Evaluated through expert-coordinated case studies on structural, thermal, and electrical alloys, the system significantly improves the efficiency of high-dimensional space exploration and enhances analysts’ capability to reason about multi-objective trade-offs.

Technology Category

• Search and Optimization: Sampling/Simulation-based Search
• Data Mining & Knowledge Management: Conversational Systems for Recommendation & Retrieval
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems

Application Category

• Graph Algorithms and Modeling for the Web: Algorithms and analysis for incomplete, noisy, or partially observed Web-related graphs
• User Modeling, Personalization and Recommendation: User modeling and simulation for interactive and conversational systems
• Web Mining and Content Analysis: Web data visualization

Abstract

Designing multi-functional alloys requires exploring high-dimensional composition-structure-property spaces, yet current tools are limited to low-dimensional projections and offer limited support for sensitivity or multi-objective tradeoff reasoning. We introduce AlloyLens, an interactive visual analytics system combining a coordinated scatterplot matrix (SPLOM), dynamic parameter sliders, gradient-based sensitivity curves, and nearest neighbor recommendations. This integrated approach reveals latent structure in simulation data, exposes the local impact of compositional changes, and highlights tradeoffs when exact matches are absent. We validate the system through case studies co-developed with domain experts spanning structural, thermal, and electrical alloy design.

Problem

• Explores high-dimensional composition-structure-property spaces in alloy design
• Overcomes limitations in sensitivity analysis and multi-objective tradeoff reasoning
• Enables inverse design through interactive visualization of simulation data

Innovation

• Combines coordinated SPLOM with dynamic parameter sliders
• Uses gradient-based sensitivity curves for local impact analysis
• Provides nearest neighbor recommendations for tradeoff exploration