Accelerating the discovery of high-performance nonlinear optical materials using active learning and high-throughput screening
arXiv:2504.01526 · doi:10.1039/D5TC01335F
Abstract
Due to their abundant use in all-solid-state lasers, nonlinear optical (NLO) crystals are needed for many applications across diverse fields such as medicine and communication. However, because of conflicting requirements, the design of suitable inorganic crystals with strong second-harmonic generation (SHG) has proven to be challenging to both experimentalists and computational scientists. In this work, we leverage a data-driven approach to accelerate the search for high-performance NLO materials. We construct an extensive pool of candidates using databases within the OPTIMADE federation and employ an active learning strategy to gather optimal data while iteratively improving a machine learning model. The result is a publicly accessible dataset of 2,200 computed SHG tensors using density-functional perturbation theory. We further assess the performance of machine learning models on SHG prediction and introduce a multi-fidelity correction-learning scheme to refine data accuracy. This study represents a significant step towards data-driven materials discovery in the NLO field and demonstrates how new materials can be screened in an automated fashion.
References in corpus (17)
- The PseudoDojo: Training and grading a 85 element optimized norm-conserving pseudopotential table
- Graph Networks as a Universal Machine Learning Framework for Molecules and Crystals
- Materials Cloud, a platform for open computational science
- An invertible crystallographic representation for general inverse design of inorganic crystals with targeted properties
- Third-order nonlinear optical response of 2D materials in the telecom band
- Nonlinear optics from an ab-initio approach by means of the dynamical Berry phase: Application to second- and third-harmonic generation in semiconductors
- MODNet -- accurate and interpretable property predictions for limited materials datasets by feature selection and joint-learning
- OPTIMADE, an API for exchanging materials data
- Ab Initio Second-Order Nonlinear Optics in Solids: Second-Harmonic Generation Spectroscopy from Time-Dependent Density-Functional Theory
- MatterGen: a generative model for inorganic materials design
- Developments and applications of the OPTIMADE API for materials discovery, design, and data exchange
- An equivariant graph neural network for the elasticity tensors of all seven crystal systems
- Robust model benchmarking and bias-imbalance in data-driven materials science: a case study on MODNet
- A Community Contribution Framework for Sharing Materials Data with Materials Project
- TensorNet: Cartesian Tensor Representations for Efficient Learning of Molecular Potentials
- Optical materials discovery and design with federated databases and machine learning
- DARWIN 1.5: Large Language Models as Materials Science Adapted Learners