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.

This study is motivated by the desire to disseminate a low-cost, high-precision, high-throughput environmental chamber to test materials and devices under elevated humidity, temperature, and light. This paper documents the...

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.

This study is motivated by the desire to disseminate a low-cost, high-precision, high-throughput environmental chamber to test materials and devices under elevated humidity, temperature, and light. This paper documents the creation of an open-source tool with a bill of materials as low as US$2,000, and the subsequent evolution of three second-generation tools installed at three different universities spanning thin films, bulk crystals, and thin-film solar-cell devices. We introduce an optical proxy measurement to detect real-time phase changes in materials. We present correlations between this optical proxy and standard X-ray diffraction measurements, describe some edge cases where the proxy measurement fails, and report key learnings from the technology-translation process. By sharing lessons learned, we hope that future open-hardware development and translation efforts can proceed with reduced friction. Throughout the paper, we provide examples of scientific impact, wherein participating laboratories used their environmental chambers to study and improve the stabilities of halide-perovskite materials. All generations of hardware bills of materials, assembly instructions, and operating codes are available in open-source repositories.

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.