Active meta-learning for predicting and selecting perovskite crystallization experiments

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 expensiv...

Full description

Saved in:
Bibliographic Details
Published in:The Journal of chemical physics 2022-02, Vol.156 (6), p.064108-064108
Main Authors: Shekar, Venkateswaran, Nicholas, Gareth, Najeeb, Mansoor Ani, Zeile, Margaret, Yu, Vincent, Wang, Xiaorong, Slack, Dylan, Li, Zhi, Nega, Philip W., Chan, Emory M., Norquist, Alexander J., Schrier, Joshua, Friedler, Sorelle A.
Format: Article
Language:English
Subjects:
Active learning
Algorithms
Crystallization
Data acquisition
Decision trees
Experimentation
Experiments
Laboratory tests
Machine learning
Perovskites
Physics
Uncertainty
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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.
ISSN:0021-9606
1089-7690
DOI:10.1063/5.0076636