Machine Learning Approach to Calculate Electronic Couplings between Quasi-diabatic Molecular Orbitals: The Case of DNA

Two-Step Machine Learning Approach for Charge-Transfer Coupling with Structurally Diverse Data

Electronic coupling is important in determining charge-transfer rates and dynamics. Coupling strength is sensitive to both intermolecular, e.g., orientation or distance, and intramolecular degrees of freedom. Hence, it is challenging to build an accurate machine learning model to predict electronic coupling of molecular pairs, especially for those derived from the amorphous phase, for which intermolecular configurations are much more diverse than those derived from crystals. In this work, we devise a new prediction algorithm that employs two consecutive KRR models. The first model predicts molecular orbitals (MOs) from structural variation for each fragment, and coupling is further predicted by using the overlap integral included in a second model. With our two-step procedure, we achieved mean absolute errors of 0.27 meV for an ethylene dimer and 1.99 meV for a naphthalene pair, much improved accuracy amounting to 14-fold and 3-fold error reductions, respectively. In addition, MOs from the first model can also be the starting point to obtain other quantum chemical properties from atomistic structures. This approach is also compatible with a MO predictor with sufficient accuracy.

Machine learning based charge mobility prediction for organic semiconductors

Transfer integral is a crucial parameter that determines the charge mobility of organic semiconductors, and it is very sensitive to molecular packing motifs. The quantum chemical calculation of transfer integrals for all the molecular pairs in organic materials is usually an unaffordable task; fortunately, it can be accelerated by the data-driven machine learning method now. In this work, we develop machine learning models based on artificial neutral networks to predict transfer integrals accurately and efficiently for four typical organic semiconductor molecules: quadruple thiophene (QT), pentacene, rubrene, and dinaphtho[2,3-b:2',3'-f]thieno[3,2-b]thiophene (DNTT). We test various forms of features and labels and evaluate the accuracy of different models. With the implementation of a data augmentation scheme, we have achieved a very high accuracy with the determination coefficient of 0.97 and mean absolute error of 4.5 meV for QT, and similar accuracy for the other three molecules. We apply these models to studying charge transport in organic crystals with dynamic disorders at 300 K and obtain the charge mobility and anisotropy in perfect agreement with the brutal force quantum chemical calculation. If more molecular packings representing the amorphous phase of organic solids are supplemented to the dataset, the current models can be refined to study charge transport in organic thin films with polymorphs and static disorders.

Ag-Bi Charge Redistribution Creates Deep Traps in Defective Cs2AgBiBr6: Machine Learning Analysis of Density Functional Theory

Lead-free double perovskites hold promise for stable and environmentally benign solar cells; however, they exhibit low efficiencies because defects act as charge recombination centers. Identifying trap-assisted loss mechanisms and developing defect passivation strategies constitute an urgent goal. Applying unsupervised machine learning to density functional theory and nonadiabatic molecular dynamics, we demonstrate that negatively charged Br vacancies in Cs₂AgBiBr₆ create deep hole traps through charge redistribution between the adjacent Ag and Bi atoms. Vacancy electrons are first accepted by Bi and then shared with Ag, as the trap transforms from shallow to deep. Subsequent charge losses are promoted by Ag and Bi motions perpendicular to rather than along the Ag-Bi axis, as can be expected. In contrast, charge recombination in pristine Cs₂AgBiBr₆ correlates most with displacements of Cs atoms and Br-Br-Br angles. Doping with In to replace Ag at the vacancy maintains the electrons at Bi and keeps the trap shallow.

Diabatic States of Molecules

Quantitative simulations of electronically nonadiabatic molecular processes require both accurate dynamics algorithms and accurate electronic structure information. Direct semiclassical nonadiabatic dynamics is expensive due to the high cost of electronic structure calculations, and hence it is limited to small systems, limited ensemble averaging, ultrafast processes, and/or electronic structure methods that are only semiquantitatively accurate. The cost of dynamics calculations can be made manageable if analytic fits are made to the electronic structure data, and such fits are most conveniently carried out in a diabatic representation because the surfaces are smooth and the couplings between states are smooth scalar functions. Diabatic representations, unlike the adiabatic ones produced by most electronic structure methods, are not unique, and finding suitable diabatic representations often involves time-consuming nonsystematic diabatization steps. The biggest drawback of using diabatic bases is that it can require large amounts of effort to perform a globally consistent diabatization, and one of our goals has been to develop methods to do this efficiently and automatically. In this Feature Article, we introduce the mathematical framework of diabatic representations, and we discuss diabatization methods, including adiabatic-to-diabatic transformations and recent progress toward the goal of automatization.

All-Atom Nonadiabatic Dynamics Simulation of Hybrid Graphene Nanoribbons Based on Wannier Analysis and Machine Learning

Trajectory surface hopping combined with ab initio electronic structure calculations is a popular and powerful approach for on-the-fly nonadiabatic dynamics simulations. For large systems, however, this remains a significant challenge because of the unaffordable computational cost of large-scale electronic structure calculations. Here, we present an efficient divide-and-conquer approach to construct the system Hamiltonian based on Wannier analysis and machine learning. In detail, the large system under investigation is first decomposed into small building blocks, and then all possible segments formed by building blocks within a cutoff distance are found out. Ab initio molecular dynamics is carried out to generate a sequence of geometries for each equivalent segment with periodicity. The Hamiltonian matrices in the maximum localized Wannier function (MLWF) basis are obtained for all geometries and utilized to train artificial neural networks (ANNs) for the structure-dependent Hamiltonian elements. Taking advantage of the orthogonality and spatial locality of MLWFs, the one-electron Hamiltonian of a large system at arbitrary geometry can be directly constructed by the trained ANNs. As demonstrations, we study charge transport in a zigzag graphene nanoribbon (GNR), a coved GNR, and a series of hybrid GNRs with a state-of-the-art surface hopping method. The interplay between delocalized and localized states is found to determine the electron dynamics in hybrid GNRs. Our approach has successfully studied GNRs with >10 000 atoms, paving the way for efficient and reliable all-atom nonadiabatic dynamics simulation of general systems.

Interpolating Nonadiabatic Molecular Dynamics Hamiltonian with Inverse Fast Fourier Transform

Nonadiabatic (NA) molecular dynamics (MD) allows one to investigate far-from-equilibrium processes in nanoscale and molecular materials at the atomistic level and in the time domain, mimicking time-resolved spectroscopic experiments. Ab initio NAMD is limited to about 100 atoms and a few picoseconds, due to computational cost of excitation energies and NA couplings. We develop a straightforward methodology that can extend ab initio quality NAMD to nanoseconds and thousands of atoms. The ab initio NAMD Hamiltonian is sampled and interpolated along a trajectory using a Fourier transform, and then, it is used to perform NAMD with known algorithms. The methodology relies on the classical path approximation, which holds for many materials and processes. To achieve a complete ab initio quality description, the trajectory can be obtained using an ab initio trained machine learning force field. The method is demonstrated with charge carrier trapping and relaxation in hybrid organic-inorganic and all-inorganic metal halide perovskites that exhibit complex dynamics and are actively studied for optoelectronic applications.