Efficient, Interpretable Graph Neural Network Representation for Angle-dependent Properties and its Application to Optical Spectroscopy
This work addresses the challenge of modeling disordered atomic systems for materials science applications, though it is incremental as it builds on an existing method.
The authors tackled the problem of predicting angle-dependent properties in atomic structures by extending the ALIGNN graph neural network encoding to include dihedral angles (ALIGNN-d), resulting in a memory-efficient representation that captures complete geometry and successfully predicts the infrared optical response of Cu(II) aqua complexes, with bond and dihedral angles identified as critical contributors to absorption fine structure.
Graph neural networks are attractive for learning properties of atomic structures thanks to their intuitive graph encoding of atoms and bonds. However, conventional encoding does not include angular information, which is critical for describing atomic arrangements in disordered systems. In this work, we extend the recently proposed ALIGNN encoding, which incorporates bond angles, to also include dihedral angles (ALIGNN-d). This simple extension leads to a memory-efficient graph representation that captures the complete geometry of atomic structures. ALIGNN-d is applied to predict the infrared optical response of dynamically disordered Cu(II) aqua complexes, leveraging the intrinsic interpretability to elucidate the relative contributions of individual structural components. Bond and dihedral angles are found to be critical contributors to the fine structure of the absorption response, with distortions representing transitions between more common geometries exhibiting the strongest absorption intensity. Future directions for further development of ALIGNN-d are discussed.