Propelled partly by the Materials Genome Initiative, and partly by the algorithmic developments and the resounding successes of data-driven efforts in other domains, informatics strategies are beginning to take shape within materials science. These approaches lead to surrogate machine learning models that enable rapid predictions based purely on past data rather than by direct experimentation or by computations/simulations in which fundamental equations are explicitly solved. Data-centric informatics methods are becoming useful to determine material properties that are hard to measure or compute using traditional methods-due to the cost, time or effort involved-but for which reliable data either already exists or can be generated for at least a subset of the critical cases. Predictions are typically interpolative, involving fingerprinting a material numerically first, and then following a mapping (established via a learning algorithm) between the fingerprint and the property of interest. Fingerprints may be of many types and scales, as dictated by the application domain and needs. Predictions may also be extrapolative-extending into new materials spaces-provided prediction uncertainties are properly taken into account. This article attempts to provide an overview of some of the recent successful data-driven "materials informatics" strategies undertaken in the last decade, and identifies some challenges the community is facing and those that should be overcome in the near future.

The question of whether one can systematically identify (previously unknown) ferroelectric phases of a given material is addressed, taking hafnia (HfO2) as an example. Low free energy phases at various pressures and temperatures are identified using a first-principles based structure search algorithm. Ferroelectric phases are then recognized by exploiting group theoretical principles for the symmetry-allowed displacive transitions between non-polar and polar phases. Two orthorhombic polar phases occurring in space groups P ca21 and P mn21 are singled out as the most viable ferroelectric phases of hafnia, as they display low free energies (relative to known non-polar phases), and substantial switchable spontaneous electric polarization. These results provide an explanation for the recently observed surprising ferroelectric behavior of hafnia, and reveal pathways for stabilizing ferroelectric phases of hafnia as well as other compounds.Commonly known structural phases of hafnia (HfO 2 ) are centrosymmetric, and thus, non-polar. Hence, recent observations of ferroelectric behavior of hafnia thin films (when doped with Si, Zr, Y, Al or Gd) [1][2][3][4][5][6][7] are rather surprising as ferroelectricity requires the presence of switchable spontaneous electrical polarization. The emergence of non-polar hafnia-as a linear high dielectric constant (or high-κ) successor to SiO 2 -for use in modern electronic devices (e.g., field-effect transistors) is now well-established [8,9]. If the origins of its unexpected ferroelectricity can be understood and appropriately harnessed, hafnia-based materials may find applications in nonvolatile memories and ferroelectric field effect transistors as well.A broader question that arises within this context, and also the one that will be addressed directly in this contribution, is whether one can systematically identify ferroelectric phases of a given material system. We show that this can indeed be accomplished and ascertained, for the example of hafnia, in two steps. First, a computationbased structure search method, e.g., the minima-hopping method [10][11][12], is used to identify low-energy phases at various pressures and temperatures. Then, ferroelectric phases are singled out by applying the group theoretical symmetry reduction principles, established by Shuvalov for ferroelectricity [13]. These principles allow for the systematic identification of all possible lower symmetry proper ferroelectric phases that can result from highersymmetry non-polar prototype (parent) phases.Using this approach, we find two ferroelectric phases of hafnia, belonging to the P ca2 1 and P mn2 1 orthorhombic space groups, which are close in free energy with the known non-polar equilibrium phases of hafnia over a wide temperature and pressure range. Figure 1(a) displays the computed equilibrium phase diagram of hafnia indicating the regimes at which the known non-polar phases are stable. This includes the low-temperature lowpressure P 2 1 /c monoclinic phase, high-pressure P bca and P nma orthorhombic p...

Force fields developed with machine learning methods in tandem with quantum mechanics are beginning to find merit, given their (i) low cost, (ii) accuracy, and (iii) versatility. Recently, we proposed one such approach, wherein, the vectorial force on an atom is computed directly from its environment. Here, we discuss the multi-step workflow required for their construction, which begins with generating diverse reference atomic environments and force data, choosing a numerical representation for the atomic environments, down selecting a representative training set, and lastly the learning method itself, for the case of Al. The constructed force field is then validated by simulating complex materials phenomena such as surface melting and stressstrain behavior -that truly go beyond the realm of ab initio methods both in length and time scales. To make such force fields truly versatile an attempt to estimate the uncertainty in force predictions is put forth, allowing one to identify areas of poor performance and paving the way for their continual improvement.

Quantum mechanics-based ab initio molecular dynamics (MD) simulation schemes offer an accurate and direct means to monitor the time evolution of materials. Nevertheless, the expensive and repetitive energy and force computations required in such simulations lead to significant bottlenecks. Here, we lay the foundations for an accelerated ab initio MD approach integrated with a machine learning framework. The proposed algorithm learns from previously visited configurations in a continuous and adaptive manner on-the-fly, and predicts (with chemical accuracy) the energies and atomic forces of a new configuration at a minuscule fraction of the time taken by conventional ab initio methods. Key elements of this new accelerated ab initio MD paradigm include representa-tions of atomic configurations by numerical fingerprints, a learning algorithm to map the fingerprints to the properties, a decision engine that guides the choice of the prediction scheme, and requisite amount of ab initio data. The performance of each aspect of the proposed scheme is critically evaluated for Al in several different chemical environments. This work has enormous implications beyond ab initio MD acceleration. It can also lead to accelerated structure and property prediction schemes, and accurate force fields.

The ability to efficiently design new and advanced dielectric polymers is hampered by the lack of sufficient, reliable data on wide polymer chemical spaces, and the difficulty of generating such data given time and computational/experimental constraints. Here, we address the issue of accelerating polymer dielectrics design by extracting learning models from data generated by accurate state-of-the-art first principles computations for polymers occupying an important part of the chemical subspace. The polymers are ‘fingerprinted’ as simple, easily attainable numerical representations, which are mapped to the properties of interest using a machine learning algorithm to develop an on-demand property prediction model. Further, a genetic algorithm is utilised to optimise polymer constituent blocks in an evolutionary manner, thus directly leading to the design of polymers with given target properties. While this philosophy of learning to make instant predictions and design is demonstrated here for the example of polymer dielectrics, it is equally applicable to other classes of materials as well.