No abstract

The Open Quantum Materials Database (OQMD) is a high-throughput database currently consisting of nearly 300,000 density functional theory (DFT) total energy calculations of compounds from the Inorganic Crystal Structure Database (ICSD) and decorations of commonly occurring crystal structures. To maximise the impact of these data, the entire database is being made available, without restrictions, at www.oqmd.org/download. In this paper, we outline the structure and contents of the database, and then use it to evaluate the accuracy of the calculations therein by comparing DFT predictions with experimental measurements for the stability of all elemental ground-state structures and 1,670 experimental formation energies of compounds. This represents the largest comparison between DFT and experimental formation energies to date. The apparent mean absolute error between experimental measurements and our calculations is 0.096 eV/atom. In order to estimate how much error to attribute to the DFT calculations, we also examine deviation between different experimental measurements themselves where multiple sources are available, and find a surprisingly large mean absolute error of 0.082 eV/atom. Hence, we suggest that a significant fraction of the error between DFT and experimental formation energies may be attributed to experimental uncertainties. Finally, we evaluate the stability of compounds in the OQMD (including compounds obtained from the ICSD as well as hypothetical structures), which allows us to predict the existence of~3,200 new compounds that have not been experimentally characterised and uncover trends in material discovery, based on historical data available within the ICSD.

Accurately predicting lifetime of complex systems like lithium-ion batteries is crucial for accelerating technology development. However, diverse aging 1 mechanisms, significant device variability, and varied operating conditions have remained major challenges. To study this problem, we generated a dataset consisting of 124 commercial lithium-iron-phosphate/graphite cells cycled under fast charging conditions. The cells exhibited widely varied cycle lives spanning from 150 to 2,300 cycles, with end-of-life defined as 20% degradation from nominal capacity. Using discharge voltage curves from early cycles yet to exhibit capacity degradation, we apply machine learning tools to predict cycle life with less than 15% error on average, which is improved to ~8% error by incorporating additional data. Our work represents a significant improvement over previous predictions that generally required data corresponding to >5% capacity degradation, without needing specialized diagnostics. Additionally, it highlights the promise of combining data generation with data-driven modeling to predict the behavior of complex and variable systems. Main Lithium-ion batteries are deployed in a wide range of applications due to their low and falling costs, high energy densities, and long cycle lives. 1-3 However, as is the case with many chemical, mechanical, and electronics systems, long battery cycle life implies delayed feedback of performance during development and manufacture, often many months to years. Accurately predicting cycle life using early-cycle data would accelerate this feedback loop as well as enable estimation of battery life expectancy for use in consumer electronics, electric vehicles, and second-life applications. 4-6

| The discovery and development of novel materials in the field of energy are essential to accelerate the transition to a low-carbon economy. Bringing recent technological innovations in automation, robotics and computer science together with current approaches in chemistry , materials synthesis and characterization will act as a catalyst for revolutionizing traditional research and development in both industry and academia. This Perspective provides a vision for an integrated artificial intelligence approach towards autonomous materials discovery , which, in our opinion, will emerge within the next 5 to 10 years. The approach we discuss requires the integration of the following tools, which have already seen substantial development to date: high-throughput virtual screening, automated synthesis planning, automated laboratories and machine learning algorithms. In addition to reducing the time to deployment of new materials by an order of magnitude, this integrated approach is expected to lower the cost associated with the initial discovery. Thus, the price of the final products (for example, solar panels, batteries and electric vehicles) will also decrease. This in turn will enable industries and governments to meet more ambitious targets in terms of reducing greenhouse gas emissions at a faster pace. volume 3 | mAY 2018 | 5 PERSPECTIVES

Extended Data Fig. 5 | Mean and standard deviation of the CLO-estimated predicted distribution over cycle lives after round 4. In this two-dimensional representation, mean estimated cycle life (colour scale) and standard deviation of cycle life (marker size) after round 4 are presented as a function of CC1, CC2 and CC3 (the x axis, y axis and panels a-f, respectively). Panels a-f represent CC3 = 3.6C, 4.0C, 4.4C, 4.8C, 5.2C, 5.6C and 6.0C, respectively. CC4 is represented by the contour lines. Note that the protocols with the highest cycle lives generally have the smallest standard deviations, since these protocols have been tested repeatedly.