Interpretation of Crystal Energy Landscapes with Kolmogorov-Arnold Networks

Abstract

Characterizing crystalline energy landscapes is essential to predicting thermodynamic stability, electronic structure, and functional behavior. While machine learning (ML) enables rapid property predictions, the "black-box" nature of most models limits their utility for generating new scientific insights. Here, we introduce Kolmogorov-Arnold Networks (KANs) as an interpretable framework to bridge this gap. Unlike conventional neural networks with fixed activation functions, KANs employ learnable functions that reveal underlying physical relationships. We developed the Element-Weighted KAN, a composition-only model that achieves state-of-the-art accuracy in predicting formation energy, band gap, and work function across large-scale datasets. Crucially, without any explicit physical constraints, KANs uncover interpretable chemical trends aligned with the periodic table and quantum mechanical principles through embedding analysis, correlation studies, and principal component analysis. These results demonstrate that KANs provide a powerful framework with high predictive performance and scientific interpretability, establishing a new paradigm for transparent, chemistry-based materials informatics.

References in corpus (10)

• A General-Purpose Machine Learning Framework for Predicting Properties of Inorganic Materials
• A Universal Graph Deep Learning Interatomic Potential for the Periodic Table
• The Joint Automated Repository for Various Integrated Simulations (JARVIS) for data-driven materials design
• High-Specific-Power Flexible Transition Metal Dichalcogenide Solar Cells
• Ultra-fast interpretable machine-learning potentials
• Deep learning generative model for crystal structure prediction
• Transfer learning relaxation, electronic structure and continuum model for twisted bilayer MoTe${}_2$
• Discovery of stable surfaces with extreme work functions by high-throughput density functional theory and machine learning
• Topogivity: A Machine-Learned Chemical Rule for Discovering Topological Materials
• Large-scale DFT methods for calculations of materials with complex structures