# Prediction of the electron density of states for crystalline compounds with Atomistic Line Graph Neural Networks (ALIGNN)

arXiv: https://arxiv.org/abs/2201.08348 · HTML: https://mlsanity.com/paper/2201.08348/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 2 of its 33 references that are in the map.
- First posted on arXiv 20 Jan 2022.

## Builds on (most cited first, 2 of 2)

- [By-passing the Kohn-Sham equations with machine learning](https://mlsanity.com/paper/1609.02815/) (2016)
- [Machine Learning Prediction of Accurate Atomization Energies of Organic Molecules from Low-Fidelity Quantum Chemical Calculations](https://mlsanity.com/paper/1906.03233/) (2019)

## Built on by (most cited first, 6 of 6)

- [Equivariant Neural Operator Learning with Graphon Convolution](https://mlsanity.com/paper/2311.10908/) (2023)
- [Artificial Intelligence in Material Engineering: A review on applications of AI in Material Engineering](https://mlsanity.com/paper/2209.11234/) (2022)
- [Contrastive Learning of English Language and Crystal Graphs for Multimodal Representation of Materials Knowledge](https://mlsanity.com/paper/2502.16451/) (2025)
- [Edge Direction-invariant Graph Neural Networks for Molecular Dipole Moments Prediction](https://mlsanity.com/paper/2206.12867/) (2022)
- [Element2Vec: Build Chemical Element Representation from Text for Property Prediction](https://mlsanity.com/paper/2510.13916/) (2025)
- [LEGO-MOF: Equivariant Latent Manipulation for Editable, Generative, and Optimizable MOF Design](https://mlsanity.com/paper/2604.13520/) (2026)

## Abstract (arXiv)

Machine learning (ML) based models have greatly enhanced the traditional materials discovery and design pipeline. Specifically, in recent years, surrogate ML models for material property prediction have demonstrated success in predicting discrete scalar-valued target properties to within reasonable accuracy of their DFT-computed values. However, accurate prediction of spectral targets such as the electron Density of States (DOS) poses a much more challenging problem due to the complexity of the target, and the limited amount of available training data. In this study, we present an extension of the recently developed Atomistic Line Graph Neural Network (ALIGNN) to accurately predict DOS of a large set of material unit cell structures, trained to the publicly available JARVIS-DFT dataset. Furthermore, we evaluate two methods of representation of the target quantity - a direct discretized spectrum, and a compressed low-dimensional representation obtained using an autoencoder. Through this work, we demonstrate the utility of graph-based featurization and modeling methods in the prediction of complex targets that depend on both chemistry and directional characteristics of material structures.