Metal halide perovskites are a promising class of materials for next-generation photovoltaic and optoelectronic devices. The discovery and full characterization of new perovskite-derived materials are limited by the difficulty of growing high quality crystals needed for single-crystal Xray diffraction studies. We present the first automated, high-throughput approach for metal halide perovskite single crystal discovery based on inverse temperature crystallization (ITC) as a means to rapidly identify and optimize synthesis conditions for the formation of high quality single crystals. Using this automated approach, a total of 1928 metal halide perovskite synthesis reactions were conducted using six organic ammonium cations (methylammonium, ethylammonium, nbutylammonium, formamidinium, guanidinium, and acetamidinium), increasing the number of metal halide perovskite materials accessible by ITC syntheses by three and resulting in the formation of a new phase, [C2H7N2][PbI3]. This comprehensive dataset allows for a statistical quantification of the total experimental space and of the likelihood of large single crystal formation. Moreover, this dataset enables the construction and evaluation of machine learning models for predicting crystal formation conditions. This work is a proof-of-concept that combining high throughput experimentation and machine learning accelerates and enhances the study of metal halide perovskite crystallization. This approach is designed to be generalizable to different synthetic routes for the acceleration of materials discovery.

Autonomous experimentation systems use algorithms and data from prior experiments to select and perform new experiments in order to meet a specified objective. In most experimental chemistry situations, there is a limited set of prior historical data available, and acquiring new data may be expensive and time consuming, which places constraints on machine learning methods. Active learning methods prioritize new experiment selection by using machine learning model uncertainty and predicted outcomes. Meta-learning methods attempt to construct models that can learn quickly with a limited set of data for a new task. In this paper, we applied the model-agnostic meta-learning (MAML) model and the Probabilistic LATent model for Incorporating Priors and Uncertainty in few-Shot learning (PLATIPUS) approach, which extends MAML to active learning, to the problem of halide perovskite growth by inverse temperature crystallization. Using a dataset of 1870 reactions conducted using 19 different organoammonium lead iodide systems, we determined the optimal strategies for incorporating historical data into active and meta-learning models to predict reaction compositions that result in crystals. We then evaluated the best three algorithms (PLATIPUS and active-learning k-nearest neighbor and decision tree algorithms) with four new chemical systems in experimental laboratory tests. With a fixed budget of 20 experiments, PLATIPUS makes superior predictions of reaction outcomes compared to other active-learning algorithms and a random baseline.

Machine learning is a useful tool for accelerating materials discovery, however it is a challenge to develop accurate methods that successfully transfer between domains while also broadening the scope of reaction conditions considered. In this paper, we consider how active- and transfer-learning methods can be used as building blocks for predicting reaction outcomes of metal halide perovskite synthesis. We then introduce a serendipity-based recommendation system that guides these methods to balance novelty and accuracy. The model-agnostic recommendation system is tested across active- and transfer-learning algorithms, using laboratory experiments for training and testing and a time-separated hold out that includes four different chemical systems. The serendipity recommendation system achieves high accuracy while increasing the scope of the synthesis conditions explored.

Abstract-The trend towards ever more powerful and faster processors has led to an enormous increase in power consump tion. This paper focuses on scheduling tasks in a heterogeneous environment with DVS enabled processors to minimize both execution time and energy consumed. The proposed algorithm, called Energy-Dynamic Level Scheduling (EDLS), favors low energy consuming processors by introducing a cost factor that affects scheduling decisions. Our scheme allows for trade offs between energy consumption and the desired performance.Our simulation results exhibit significant power savings at a reasonable increase in overall execution time. Moreover, our results demonstrates a high degree of correlation between the energy saving and the increase in the heterogeneity of processors.

Machine learning is a useful tool for accelerating materials discovery, however it is a challenge to develop accurate methods that successfully transfer between domains while also broadening the scope of reaction conditions considered. In this paper, we consider how active- and transfer-learning methods can be used as building blocks for predicting reaction outcomes of metal halide perovskite synthesis. We then introduce a serendipity-based recommendation system that guides these methods to balance novelty and accuracy. The model-agnostic recommendation system is tested across active- and transfer-learning algorithms, using laboratory experiments for training and testing and a time-separated hold out that includes four different chemical systems. The serendipity recommendation system achieves high accuracy while increasing the scope of the synthesis conditions explored.

No abstract

A spatiotemporal experimental route is reported for the antisolvent vapor diffusion crystal growth of metal halide perovskitoids. A computational analysis combining automated image capture and diffusion modeling enables the determination of the critical concentrations required for nucleation and crystal growth from a single experiment. Five different solvent systems and ten distinct organic ammonium iodide salts were investigated with lead iodide, from which nine previously unreported compounds were discovered. Automated image capture of the mother liquor and antisolvent vials was used to determine changes in solution meniscus positions and detect the nucleation event location. Matching the observations to a numerical solution of Fick’s second law diffusion model enables the calculation of reactant, solvent, and antisolvent concentrations at both the time and position of the first stable nucleation and crystal growth. A machine learning model was trained on the resulting data, and it reveals solvent- and amine-specific crystallization tendencies. Solvent systems that interact more weakly with dissolved lead species promote crystallization, while those with stronger interactions can prevent crystallization through increased solubilities. Organic amines that interact more strongly with inorganic components and exhibit greater rigidity are more likely to be incorporated into crystalline products.

Transportation networks are one of several critical infrastructures on which first responders rely in order to deliver emergency services. However, there is no guarantee that a transportation network will be fully operational following a regional event, such as a hurricane or earthquake. Emergency planning and response tools should explicitly integrate this possibility to ensure the completeness of the risk assessment process. This paper considers the elevated vulnerability to which a community is exposed when disruptions in a transportation network slow emergency response. An average weighted vulnerability metric is defined to favor a network restoration strategy that quickly reduces emergency response times to their nominal levels. This metric is incorporated into an algorithm to prioritize network restoration, so that individuals who might require assistance are not exposed to prolonged periods of lengthy response times. The formulation considers a number of types of emergency response facilities and different types of hazard; the hazards can require a response from more than one type of facility. The utility of the approach is illustrated through a series of examples. Our results demonstrate that the approach can offer systematic guidance to reduce emergency response times after a partial or complete outage of a transportation network.