Deep learning methods for the prediction of molecular excitation spectra are presented. For the example of the electronic density of states of 132k organic molecules, three different neural network architectures: multilayer perceptron (MLP), convolutional neural network (CNN), and deep tensor neural network (DTNN) are trained and assessed. The inputs for the neural networks are the coordinates and charges of the constituent atoms of each molecule. Already, the MLP is able to learn spectra, but the root mean square error (RMSE) is still as high as 0.3 eV. The learning quality improves significantly for the CNN (RMSE = 0.23 eV) and reaches its best performance for the DTNN (RMSE = 0.19 eV). Both CNN and DTNN capture even small nuances in the spectral shape. In a showcase application of this method, the structures of 10k previously unseen organic molecules are scanned and instant spectra predictions are obtained to identify molecules for potential applications.

Tailoring the functional properties of advanced organic/inorganic heterogeneous devices to their intended technological applications requires knowledge and control of the microscopic structure inside the device. Atomistic quantum mechanical simulation methods deliver accurate energies and properties for individual configurations, however, finding the most favourable configurations remains computationally prohibitive. We propose a 'building block'-based Bayesian Optimization Structure Search (BOSS) approach for addressing extended organic/inorganic interface problems and demonstrate its feasibility in a molecular surface adsorption study. In BOSS, a Bayesian model identifies material energy landscapes in an accelerated fashion from atomistic configurations sampled during active learning. This allowed us to identify several most favorable molecular adsorption configurations for C60 on the (101) surface of TiO2 anatase and clarify the key molecule-surface interactions governing structural assembly. Inferred structures were in good agreement with detailed experimental images of this surface adsorbate, demonstrating good predictive power of BOSS and opening the route towards large-scale surface adsorption studies of molecular aggregates and films.

Instant machine learning predictions of molecular properties are desirable for materials design, but the predictive power of the methodology is mainly tested on well-known benchmark datasets. Here, we investigate the performance of machine learning with kernel ridge regression (KRR) for the prediction of molecular orbital energies on three large datasets: the standard QM9 small organic molecules set, amino acid and dipeptide conformers, and organic crystal-forming molecules extracted from the Cambridge Structural Database. We focus on prediction of highest occupied molecular orbital (HOMO) energies, computed at density-functional level of theory. Two different representations that encode molecular structure are compared: the Coulomb matrix (CM) and the many-body tensor representation (MBTR). We find that KRR performance depends significantly on the chemistry of the underlying dataset and that the MBTR is superior to the CM, predicting HOMO energies with a mean absolute error as low as 0.09 eV. To demonstrate the power of our machine learning method, we apply our model to structures of 10k previously unseen molecules. We gain instant energy predictions that allow us to identify interesting molecules for future applications.

Data science and machine learning in materials science require large datasets of technologically relevant molecules or materials. Currently, publicly available molecular datasets with realistic molecular geometries and spectral properties are rare. We here supply a diverse benchmark spectroscopy dataset of 61,489 molecules extracted from organic crystals in the Cambridge Structural Database (CSD), denoted OE62. Molecular equilibrium geometries are reported at the Perdew-Burke-Ernzerhof (PBE) level of density functional theory (DFT) including van der Waals corrections for all 62k molecules. For these geometries, OE62 supplies total energies and orbital eigenvalues at the PBE and the PBE hybrid (PBE0) functional level of DFT for all 62k molecules in vacuum as well as at the PBE0 level for a subset of 30,876 molecules in (implicit) water. For 5,239 molecules in vacuum, the dataset provides quasiparticle energies computed with many-body perturbation theory in the G0W0 approximation with a PBE0 starting point (denoted GW5000 in analogy to the GW100 benchmark set (M. van Setten et al. J. Chem. Theory Comput. 12, 5076 (2016))).

In scanning probe microscopy, the imaging characteristics in the various interaction channels crucially depend on the chemical termination of the probe tip. Here we analyze the contrast signatures of an oxygen-terminated copper tip with a tetrahedral configuration of the covalently bound terminal O atom. Supported by first-principles calculations we show how this tip termination can be identified by contrast analysis in noncontact atomic force and scanning tunneling microscopy (NC-AFM, STM) on a partially oxidized Cu(110) surface. After controlled tip functionalization by soft indentations of only a few angstroms in an oxide nanodomain, we demonstrate that this tip allows imaging an organic molecule adsorbed on Cu(110) by constant-height NC-AFM in the repulsive force regime, revealing its internal bond structure. In established tip functionalization approaches where, for example, CO or Xe is deliberately picked up from a surface, these probe particles are only weakly bound to the metallic tip, leading to lateral deflections during scanning. Therefore, the contrast mechanism is subject to image distortions, artifacts, and related controversies. In contrast, our simulations for the O-terminated Cu tip show that lateral deflections of the terminating O atom are negligible. This allows a detailed discussion of the fundamental imaging mechanisms in high-resolution NC-AFM experiments. With its structural rigidity, its chemically passivated state, and a high electron density at the apex, we identify the main characteristics of the O-terminated Cu tip, making it a highly attractive complementary probe for the characterization of organic nanostructures on surfaces.