CONI-Net: Machine Learning of Separable Intermolecular Force Fields.

Noncovalent interactions (NCIs) play an essential role in soft matter and biomolecular simulations. The ab initio method symmetry-adapted perturbation theory allows a precise quantitative analysis of NCIs and offers an inherent energy decomposition, enabling a deeper understanding of the nature of intermolecular interactions. However, this method is limited to small systems, for instance, dimers of molecules. Here, we present a scale-bridging approach to systematically derive an intermolecular force field from ab initio data while preserving the energy decomposition of the underlying method. We apply the model in molecular dynamics simulations of several solvents and compare two predicted thermodynamic observables-mass density and enthalpy of vaporization-to experiments and established force fields. For a data set limited to hydrocarbons, we investigate the extrapolation capabilities to molecules absent from the training set. Overall, despite the affordable moderate quality of the reference ab initio data, we find promising results. With the straightforward data set generation procedure and the lack of target data in the fitting process, we have developed a method that enables the rapid development of predictive force fields with an extra dimension of insights into the balance of NCIs.

Fast Generation of Machine Learning-Based Force Fields for Adsorption Energies.

Adsorption and desorption of molecules are key processes in extraction and purification of biomolecules, engineering of drug carriers, and designing of surface-specific coatings. To understand the adsorption process on the atomic scale, state-of-the-art quantum mechanical and classical simulation methodologies are widely used. However, studying adsorption using a full quantum mechanical treatment is limited to picoseconds simulation timescales, while classical molecular dynamics simulations are limited by the accuracy of the existing force fields. To overcome these challenges, we propose a systematic way to generate flexible, application-specific highly accurate force fields by training artificial neural networks. As a proof of concept, we study the adsorption of the amino acid alanine on graphene and gold (111) surfaces and demonstrate the force field generation methodology in detail. We find that a molecule-specific force field with Lennard-Jones type two-body terms incorporating the 3rd and 7th power of the inverse distances between the atoms of the adsorbent and the surfaces yields optimal results, which is surprisingly different from typical Lennard-Jones potentials used in traditional force fields. Furthermore, we present an efficient and easy-to-train machine learning model that incorporates system-specific three-body (or higher order) interactions that are required, for example, for gold surfaces. Our final machine learning-based force field yields a mean absolute error of less than 4.2 kJ/mol at a speed-up of ∼105 times compared to quantum mechanical calculation, which will have a significant impact on the study of adsorption in different research areas.

Analyzing Dynamical Disorder for Charge Transport in Organic Semiconductors via Machine Learning.

Organic semiconductors are indispensable for today's display technologies in the form of organic light-emitting diodes (OLEDs) and further optoelectronic applications. However, organic materials do not reach the same charge carrier mobility as inorganic semiconductors, limiting the efficiency of devices. To find or even design new organic semiconductors with higher charge carrier mobility, computational approaches, in particular multiscale models, are becoming increasingly important. However, such models are computationally very costly, especially when large systems and long timescales are required, which is the case to compute static and dynamic energy disorder, i.e., the dominant factor to determine charge transport. Here, we overcome this drawback by integrating machine learning models into multiscale simulations. This allows us to obtain unprecedented insight into relevant microscopic materials properties, in particular static and dynamic disorder contributions for a series of application-relevant molecules. We find that static disorder and thus the distribution of shallow traps are highly asymmetrical for many materials, impacting widely considered Gaussian disorder models. We furthermore analyze characteristic energy level fluctuation times and compare them to typical hopping rates to evaluate the importance of dynamic disorder for charge transport. We hope that our findings will significantly improve the accuracy of computational methods used to predict application-relevant materials properties of organic semiconductors and thus make these methods applicable for virtual materials design.

Toward Design of Novel Materials for Organic Electronics.

Materials for organic electronics are presently used in prominent applications, such as displays in mobile devices, while being intensely researched for other purposes, such as organic photovoltaics, large-area devices, and thin-film transistors. Many of the challenges to improve and optimize these applications are material related and there is a nearly infinite chemical space that needs to be explored to identify the most suitable material candidates. Established experimental approaches struggle with the size and complexity of this chemical space. Herein, the development of simulation methods is addressed, with a particular emphasis on predictive multiscale protocols, to complement experimental research in the identification of novel materials and illustrate the potential of these methods with a few prominent recent applications. Finally, the potential of machine learning and methods based on artificial intelligence is discussed to further accelerate the search for new materials.

Nanocrystalline graphene at high temperatures: insight into nanoscale processes.

During high temperature pyrolysis of polymer thin films, nanocrystalline graphene with a high defect density, active edges and various nanostructures is formed. The catalyst-free synthesis is based on the temperature assisted transformation of a polymer precursor. The processing conditions have a strong influence on the final thin film properties. However, the precise elemental processes that govern the polymer pyrolysis at high temperatures are unknown. By means of time resolved in situ transmission electron microscopy investigations we reveal that the reactivity of defects and unsaturated edges plays an integral role in the structural dynamics. Both mobile and stationary structures with varying size, shape and dynamics have been observed. During high temperature experiments, small graphene fragments (nanoflakes) are highly unstable and tend to lose atoms or small groups of atoms, while adjacent larger domains grow by addition of atoms, indicating an Ostwald-like ripening in these 2D materials, besides the mechanism of lateral merging of nanoflakes with edges. These processes are also observed in low-dose experiments with negligible electron beam influence. Based on energy barrier calculations, we propose several inherent temperature-driven mechanisms of atom rearrangement, partially involving catalyzing unsaturated sites. Our results show that the fundamentally different high temperature behavior and stability of nanocrystalline graphene in contrast to pristine graphene is caused by its reactive nature. The detailed analysis of the observed dynamics provides a pioneering overview of the relevant processes during ncg heating.

Machine learning of correlated dihedral potentials for atomistic molecular force fields.

Computer simulation increasingly complements experimental efforts to describe nanoscale structure formation. Molecular mechanics simulations and related computational methods fundamentally rely on the accuracy of classical atomistic force fields for the evaluation of inter- and intramolecular energies. One indispensable component of such force fields, in particular for large organic molecules, is the accuracy of molecule-specific dihedral potentials which are the key determinants of molecular flexibility. We show in this work that non-local correlations of dihedral potentials play a decisive role in the description of the total molecular energy-an effect which is neglected in most state-of-the-art dihedral force fields. We furthermore present an efficient machine learning approach to compute intramolecular conformational energies. We demonstrate with the example of α-NPD, a molecule frequently used in organic electronics, that this approach outperforms traditional force fields by decreasing the mean absolute deviations by one order of magnitude to values smaller than 0.37 kcal/mol (16.0 meV) per dihedral angle.