MXenes are two-dimensional (2D) transition metal carbides and nitrides, and are invariably metallic in pristine form. While spontaneous passivation of their reactive bare surfaces lends unprecedented functionalities, consequently a many-folds increase in number of possible functionalized MXene makes their characterization difficult.Here, we study the electronic properties of this vast class of materials by accurately estimating the band gaps using statistical learning. Using easily available properties of the MXene, namely, boiling and melting points, atomic radii, phases, bond lengths, etc., as input features, models were developed using kernel ridge (KRR), support vector (SVR), Gaussian process (GPR), and bootstrap aggregating regression algorithms. Among these, the GPR model predicts the band gap with lowest root-mean-squared error (rmse) of 0.14 eV, within seconds. Most importantly, these models do not involve the Perdew−Burke−Ernzerhof (PBE) band gap as a feature. Our results demonstrate that machine-learning models can bypass the band gap underestimation problem of local and semilocal functionals used in density functional theory (DFT) calculations, without subsequent correction using the time-consuming GW approach.

Summary Modern data-driven tools are transforming application-specific polymer development cycles. Surrogate models that can be trained to predict properties of polymers are becoming commonplace. Nevertheless, these models do not utilize the full breadth of the knowledge available in datasets, which are oftentimes sparse; inherent correlations between different property datasets are disregarded. Here, we demonstrate the potency of multi-task learning approaches that exploit such inherent correlations effectively. Data pertaining to 36 different properties of over 13,000 polymers are supplied to deep-learning multi-task architectures. Compared to conventional single-task learning models, the multi-task approach is accurate, efficient, scalable, and amenable to transfer learning as more data on the same or different properties become available. Moreover, these models are interpretable. Chemical rules, that explain how certain features control trends in property values, emerge from the present work, paving the way for the rational design of application specific polymers meeting desired property or performance objectives.

Laser-driven molecular spectroscopy of low spatial resolution is widely used, while electronic current-driven molecular spectroscopy of atomic scale resolution has been limited because currents provide only minimal information. However, electron transmission of a graphene nanoribbon on which a molecule is adsorbed shows molecular fingerprints of Fano resonances, i.e., characteristic features of frontier orbitals and conformations of physisorbed molecules. Utilizing these resonance profiles, here we demonstrate two-dimensional molecular electronics spectroscopy (2D MES). The differential conductance with respect to bias and gate voltages not only distinguishes different types of nucleobases for DNA sequencing but also recognizes methylated nucleobases which could be related to cancerous cell growth. This 2D MES could open an exciting field to recognize single molecule signatures at atomic resolution. The advantages of the 2D MES over the one-dimensional (1D) current analysis can be comparable to those of 2D NMR over 1D NMR analysis.

We analyze the transmission of narrow semiconducting nanoribbons designed from two-dimensional (2D) layered materials such as graphene, silicene, hexagonal boron nitride (hBN), and molybdenum disulfide (MoS 2 ). The Fano resonance driven dips in the transmission, when nucleobases stack with graphene nanoribbon, are known to be useful for DNA sequencing. For graphene and hBN nanoribbons the transmission dips are distinct for each nucleobase, but with a larger band gap for the latter case. For silicene nanoribbon the dips due to different nucleobases are somehow less clear. The transmission of the MoS 2 nanoribbon is unpromising for DNA sequencing as the dip in the transmission is not useful to identify any of the nucleobase. The dip positions in the transmission shift linearly with bias voltage. This shift depends on the nanoribbon used and the orientation of the DNA base. Hence, edge-modified hBN nanoribbons with a reduced band gap could be an alternative to graphene nanoribbon (GNR) for DNA sequencing and recognition of other adsorbents.

Functionalized MXene has emerged a promising class of two-dimensional materials having more than tens of thousands of compounds, whose uses may range from electronics to energy applications. Other than the band gap, these properties rely on the accurate position of the band edges. Hence, to synthesize MXenes for various applications, a prior knowledge of the accurate position of their band edges at an absolute scale is essential; computing these with conventional methods would take years for all the MXenes. Here, we develop a machine learning model for positioning the band edges with GW level of accuracy having a minimum root-mean-squared error of 0.12 eV. An intuitive model is proposed based on the combination of Perdew–Burke–Ernzerhof band edge and vacuum potential having a correlation of 0.93 with GW band edges. These models can be utilized to identify MXenes for a desired application in an accelerated manner.