An official website of the United States government
Abstract Optical properties in solids, such as refractive index and absorption, hold vast applications ranging from solar panels to sensors, photodetectors, and transparent displays. However, first‐principles computation of optical properties from crystal structures is a complex task due to the high convergence criteria and computational cost. Recent progress in machine learning shows promise in predicting material properties, yet predicting optical properties from crystal structures remains challenging due to the lack of efficient atomic embeddings. Here, Graph Neural Network for Optical spectra prediction (GNNOpt) is introduced, an equivariant graph‐neural‐network architecture featuring universal embedding with automatic optimization. This enables high‐quality optical predictions with a dataset of only 944 materials. GNNOpt predicts all optical properties based on the Kramers‐Krönig relations, including absorption coefficient, complex dielectric function, complex refractive index, and reflectance. The trained model is applied to screen photovoltaic materials based on spectroscopic limited maximum efficiency and search for quantum materials based on quantum weight. First‐principles calculations validate the efficacy of the GNNOpt model, demonstrating excellent agreement in predicting the optical spectra of unseen materials. The discovery of new quantum materials with high predicted quantum weight, such as SiOs, which host exotic quasiparticles with multifold nontrivial topology, demonstrates the potential of GNNOpt in predicting optical properties across a broad range of materials and applications.
more »
« less
A neural network protocol for electronic excitations of N -methylacetamide
UV absorption is widely used for characterizing proteins structures. The mapping of UV spectra to atomic structure of proteins relies on expensive theoretical simulations, circumventing the heavy computational cost which involves repeated quantum-mechanical simulations of excited-state properties of many fluctuating protein geometries, which has been a long-time challenge. Here we show that a neural network machine-learning technique can predict electronic absorption spectra of N -methylacetamide (NMA), which is a widely used model system for the peptide bond. Using ground-state geometric parameters and charge information as descriptors, we employed a neural network to predict transition energies, ground-state, and transition dipole moments of many molecular-dynamics conformations at different temperatures, in agreement with time-dependent density-functional theory calculations. The neural network simulations are nearly 3,000× faster than comparable quantum calculations. Machine learning should provide a cost-effective tool for simulating optical properties of proteins.
more »
« less
- Award ID(s):
- 1663822
- PAR ID:
- 10174857
- Date Published:
- Journal Name:
- Proceedings of the National Academy of Sciences
- ISSN:
- 0027-8424
- Page Range / eLocation ID:
- 201821044
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Abstract Monte Carlo simulations for photon transport are commonly used to predict the spectral response, including reflectance, absorptance, and transmittance in nanoparticle laden media, while the computational cost could be high. In this study, we demonstrate a general purpose fully connected neural network approach, trained with Monte Carlo simulations, to accurately predict the spectral response while dramatically accelerating the computational speed. Monte Carlo simulations are first used to generate a training set with a wide range of optical properties covering dielectrics, semiconductors, and metals. Each input is normalized, with the scattering and absorption coefficients normalized on a logarithmic scale to accelerate the training process and reduce error. A deep neural network with ReLU activation is trained on this dataset with the optical properties and medium thickness as the inputs, and diffuse reflectance, absorptance, and transmittance as the outputs. The neural network is validated on a validation set with randomized optical properties, as well as nanoparticle medium examples including barium sulfate, aluminum, and silicon. The error in the spectral response predictions is within 1% which is sufficient for many applications, while the speedup is 1–3 orders of magnitude. This machine learning accelerated approach can allow for high throughput screening, optimization, or real-time monitoring of nanoparticle media's spectral response.more » « less
-
Organic chromophores initiate much of daytime aqueous phase chemistry in the environment. Thus, studying the absorption spectra of commonly used organic photosensitizers is paramount to fully understand their relevance in environmental processes. In this work, we combined UV-Vis spectroscopy, 1 H-NMR spectroscopy, quantum chemical calculations, and molecular dynamics simulations to investigate the absorption spectra of 4-benzoyl benzoic acid (4BBA), a widely used photosensitizer and a common proxy of environmentally relevant chromophores. Solutions of 4BBA at different pH values show that protonated and deprotonated species have an effect on its absorbance spectra. Theoretical calculations of these species in water clusters provide physical and chemical insights into the spectra. Quantum chemical calculations were conducted to analyze the UV-Vis absorbance spectra of 4BBA species using various cluster sizes, such as C 6 H 5 COC 6 H 4 COOH·(H 2 O) n , where n = 8 for relatively small clusters and n = 30 for larger clusters. While relatively small clusters have been successfully used for smaller chromophores, our results indicate that simulations of protonated species of 4BBA require relatively larger clusters of n = 30. A comparison between the experimental and theoretical results shows good agreement in the pH-dependent spectral shift between the hydrated cluster model and the experimental data. Overall, the theoretical and empirical results indicate that the experimental optical spectra of aqueous phase 4BBA can be represented by the acid–base equilibrium of the keto-forms, with a spectroscopically measured p K a of 3.41 ± 0.04. The results summarized here contribute to a molecular-level understanding of solvated organic molecules through calculations restricted to cluster models, and thereby, broader insight into environmentally relevant chromophores.more » « less
-
The recently discovered Neorhodopsin (NeoR) exhibits absorption and emission maxima in the near-infrared spectral region, which together with the high fluorescence quantum yield makes it an attractive retinal protein for optogenetic applications. The unique optical properties can be rationalized by a theoretical model that predicts a high charge transfer character in the electronic ground state (S0) which is otherwise typical of the excited state S1 in canonical retinal proteins. The present study sets out to assess the electronic structure of the NeoR chromophore by resonance Raman (RR) spectroscopy since frequencies and relative intensities of RR bands are controlled by the ground and excited state’s properties. The RR spectra of NeoR differ dramatically from those of canonical rhodopsins but can be reliably reproduced by the calculations carried out within two different structural models. The remarkable agreement between the experimental and calculated spectra confirms the consistency and robustness of the theoretical approach.more » « less
-
null (Ed.)Photochemical reactions are widely used by academic and industrial researchers to construct complex molecular architectures via mechanisms that often require harsh reaction conditions. Photodynamics simulations provide time-resolved snapshots of molecular excited-state structures required to understand and predict reactivities and chemoselectivities. Molecular excited-states are often nearly degenerate and require computationally intensive multiconfigurational quantum mechanical methods, especially at conical intersections. Non-adiabatic molecular dynamics require thousands of these computations per trajectory, which limits simulations to ∼1 picosecond for most organic photochemical reactions. Westermayr et al. recently introduced a neural-network-based method to accelerate the predictions of electronic properties and pushed the simulation limit to 1 ns for the model system, methylenimmonium cation (CH 2 NH 2 + ). We have adapted this methodology to develop the Python-based, Python Rapid Artificial Intelligence Ab Initio Molecular Dynamics (PyRAI 2 MD) software for the cis – trans isomerization of trans -hexafluoro-2-butene and the 4π-electrocyclic ring-closing of a norbornyl hexacyclodiene. We performed a 10 ns simulation for trans -hexafluoro-2-butene in just 2 days. The same simulation would take approximately 58 years with traditional multiconfigurational photodynamics simulations. We generated training data by combining Wigner sampling, geometrical interpolations, and short-time quantum chemical trajectories to adaptively sample sparse data regions along reaction coordinates. The final data set of the cis – trans isomerization and the 4π-electrocyclic ring-closing model has 6207 and 6267 data points, respectively. The training errors in energy using feedforward neural networks achieved chemical accuracy (0.023–0.032 eV). The neural network photodynamics simulations of trans -hexafluoro-2-butene agree with the quantum chemical calculations showing the formation of the cis -product and reactive carbene intermediate. The neural network trajectories of the norbornyl cyclohexadiene corroborate the low-yielding syn -product, which was absent in the quantum chemical trajectories, and revealed subsequent thermal reactions in 1 ns.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Journal Article:
- https://doi.org/10.1073/pnas.1821044116
