Active meta-learning for predicting and selecting perovskite crystallization experiments

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.

doi:10.1063/5.0076636

Title: Active meta-learning for predicting and selecting perovskite crystallization experiments

Journal Article · 13 February 2022 · Journal of Chemical Physics

DOI: https://doi.org/10.1063/5.0076636 · OSTI ID:1963435

^[1]; Nicholas, Gareth ^[1];

^[1];

^[1]; Yu, Vincent ^[1]; Wang, Xiaorong ^[1]; Slack, Dylan ^[1]; Li, Zhi ^[2]; Nega, Philip W. ^[2];

^[2];

^[1];

^[3];

^[1]

Haverford College, PA (United States)
Lawrence Berkeley National Laboratory (LBNL), Berkeley, CA (United States). Molecular Foundry
Fordham University, The Bronx, NY (United States)

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. Here 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.

View Accepted Manuscript (DOE)

Cite

Export

Save

Research Organization:: Lawrence Berkeley National Laboratory (LBNL), Berkeley, CA (United States)

Sponsoring Organization:: Defense Advanced Research Projects Agency (DARPA); Henry Dreyfus Teacher-Scholar; USDOE; USDOE Office of Science (SC), Basic Energy Sciences (BES). Materials Sciences & Engineering Division

Contributing Organization:: MERCURY Consortium

Grant/Contract Number:: AC02-05CH11231

OSTI ID:: 1963435

Journal Information:: Journal of Chemical Physics, Journal Name: Journal of Chemical Physics Journal Issue: 6 Vol. 156; ISSN 0021-9606

Publisher:: American Institute of Physics (AIP)Copyright Statement

Country of Publication:: United States

Language:: English

References (57)

Artificial Chemist: An Autonomous Quantum Dot Synthesis Bot Epps, Robert W.; Bowen, Michael S.; Volk, Amanda A. Advanced Materials, Vol. 32, Issue 30 https://doi.org/10.1002/adma.202001626	journal	June 2020
Exploring the Stability of Novel Wide Bandgap Perovskites by a Robot Based High Throughput Approach Chen, Shi; Hou, Yi; Chen, Haiwei Advanced Energy Materials, Vol. 8, Issue 6 https://doi.org/10.1002/aenm.201701543	journal	October 2017
Human versus Robots in the Discovery and Crystallization of Gigantic Polyoxometalates Duros, Vasilios; Grizou, Jonathan; Xuan, Weimin Angewandte Chemie, Vol. 129, Issue 36 https://doi.org/10.1002/ange.201705721	journal	August 2017
Meta-Learning Vanschoren, Joaquin Automated Machine Learning https://doi.org/10.1007/978-3-030-05318-5_2	book	January 2019
Meta-QSAR: a large-scale application of meta-learning to drug design and discovery Olier, Ivan; Sadawi, Noureddin; Bickerton, G. Richard Machine Learning, Vol. 107, Issue 1 https://doi.org/10.1007/s10994-017-5685-x	journal	December 2017
Materials Acceleration Platforms: On the way to autonomous experimentation Flores-Leonar, Martha M.; Mejía-Mendoza, Luis M.; Aguilar-Granda, Andrés Current Opinion in Green and Sustainable Chemistry, Vol. 25 https://doi.org/10.1016/j.cogsc.2020.100370	journal	October 2020
A meta-learning framework using representation learning to predict drug-drug interaction Deepika, S. S.; Geetha, T. V. Journal of Biomedical Informatics, Vol. 84 https://doi.org/10.1016/j.jbi.2018.06.015	journal	August 2018
Machine learning for high-throughput experimental exploration of metal halide perovskites Ahmadi, Mahshid; Ziatdinov, Maxim; Zhou, Yuanyuan Joule, Vol. 5, Issue 11 https://doi.org/10.1016/j.joule.2021.10.001	journal	November 2021
Machine-Learning-Accelerated Perovskite Crystallization Kirman, Jeffrey; Johnston, Andrew; Kuntz, Douglas A. Matter, Vol. 2, Issue 4 https://doi.org/10.1016/j.matt.2020.02.012	journal	April 2020
A data fusion approach to optimize compositional stability of halide perovskites Sun, Shijing; Tiihonen, Armi; Oviedo, Felipe Matter, Vol. 4, Issue 4 https://doi.org/10.1016/j.matt.2021.01.008	journal	April 2021
Autonomous experimentation systems for materials development: A community perspective Stach, Eric; DeCost, Brian; Kusne, A. Gilad Matter, Vol. 4, Issue 9 https://doi.org/10.1016/j.matt.2021.06.036	journal	September 2021
Next-Generation Experimentation with Self-Driving Laboratories Häse, Florian; Roch, Loïc M.; Aspuru-Guzik, Alán Trends in Chemistry, Vol. 1, Issue 3 https://doi.org/10.1016/j.trechm.2019.02.007	journal	June 2019
Autonomous flow reactors for discovery and invention Volk, Amanda A.; Abolhasani, Milad Trends in Chemistry, Vol. 3, Issue 7 https://doi.org/10.1016/j.trechm.2021.04.001	journal	July 2021
Autonomous Discovery of Battery Electrolytes with Robotic Experimentation and Machine Learning Dave, Adarsh; Mitchell, Jared; Kandasamy, Kirthevasan Cell Reports Physical Science, Vol. 1, Issue 12 https://doi.org/10.1016/j.xcrp.2020.100264	journal	December 2020
MS/MS Spectrum Prediction for Modified Peptides Using pDeep2 Trained by Transfer Learning Zeng, Wen-Feng; Zhou, Xie-Xuan; Zhou, Wen-Jing Analytical Chemistry, Vol. 91, Issue 15 https://doi.org/10.1021/acs.analchem.9b01262	journal	June 2019
Robot-Accelerated Perovskite Investigation and Discovery Li, Zhi; Najeeb, Mansoor Ani; Alves, Liana Chemistry of Materials, Vol. 32, Issue 13 https://doi.org/10.1021/acs.chemmater.0c01153	journal	June 2020
Dimensional Control over Metal Halide Perovskite Crystallization Guided by Active Learning Li, Zhi; Nega, Philip W.; Nellikkal, Mansoor Ani Najeeb Chemistry of Materials, Vol. 34, Issue 2 https://doi.org/10.1021/acs.chemmater.1c03564	journal	January 2022
Halide Perovskite Photovoltaics: Background, Status, and Future Prospects Jena, Ajay Kumar; Kulkarni, Ashish; Miyasaka, Tsutomu Chemical Reviews, Vol. 119, Issue 5 https://doi.org/10.1021/acs.chemrev.8b00539	journal	March 2019
Solution Mixing Calculations as a Geometry, Linear Algebra, and Convex Analysis Problem Schrier, Joshua Journal of Chemical Education, Vol. 98, Issue 5 https://doi.org/10.1021/acs.jchemed.0c01456	journal	March 2021
Investigating Active Learning and Meta-Learning for Iterative Peptide Design Barrett, Rainier; White, Andrew D. Journal of Chemical Information and Modeling, Vol. 61, Issue 1 https://doi.org/10.1021/acs.jcim.0c00946	journal	December 2020
Improving Data and Prediction Quality of High-Throughput Perovskite Synthesis with Model Fusion Tang, Yuanqing; Li, Zhi; Nellikkal, Mansoor Ani Najeeb Journal of Chemical Information and Modeling, Vol. 61, Issue 4 https://doi.org/10.1021/acs.jcim.0c01307	journal	April 2021
Meta Learning for Low-Resource Molecular Optimization Wang, Jiahao; Zheng, Shuangjia; Chen, Jianwen Journal of Chemical Information and Modeling, Vol. 61, Issue 4 https://doi.org/10.1021/acs.jcim.0c01416	journal	March 2021
Intuition-Enabled Machine Learning Beats the Competition When Joint Human-Robot Teams Perform Inorganic Chemical Experiments Duros, Vasilios; Grizou, Jonathan; Sharma, Abhishek Journal of Chemical Information and Modeling, Vol. 59, Issue 6 https://doi.org/10.1021/acs.jcim.9b00304	journal	April 2019
Transfer Learning for Drug Discovery Cai, Chenjing; Wang, Shiwei; Xu, Youjun Journal of Medicinal Chemistry, Vol. 63, Issue 16 https://doi.org/10.1021/acs.jmedchem.9b02147	journal	July 2020
Transfer Learning from Markov Models Leads to Efficient Sampling of Related Systems Sultan, Mohammad M.; Pande, Vijay S. The Journal of Physical Chemistry B, Vol. 122, Issue 21 https://doi.org/10.1021/acs.jpcb.7b06896	journal	September 2017
Efficient Phase Diagram Sampling by Active Learning Dai, Chengyu; Glotzer, Sharon C. The Journal of Physical Chemistry B, Vol. 124, Issue 7 https://doi.org/10.1021/acs.jpcb.9b09202	journal	January 2020
Can Machines “Learn” Halide Perovskite Crystal Formation without Accurate Physicochemical Features? Pendleton, Ian M.; Caucci, Mary K.; Tynes, Michael The Journal of Physical Chemistry C, Vol. 124, Issue 25 https://doi.org/10.1021/acs.jpcc.0c01726	journal	May 2020
Putting Density Functional Theory to the Test in Machine-Learning-Accelerated Materials Discovery Duan, Chenru; Liu, Fang; Nandy, Aditya The Journal of Physical Chemistry Letters, Vol. 12, Issue 19 https://doi.org/10.1021/acs.jpclett.1c00631	journal	May 2021
Transfer Learning-Based Artificial Intelligence-Integrated Physical Modeling to Enable Failure Analysis for 3 Nanometer and Smaller Silicon-Based CMOS Transistors Pan, Jieming; Low, Kain Lu; Ghosh, Joydeep ACS Applied Nano Materials, Vol. 4, Issue 7 https://doi.org/10.1021/acsanm.1c00960	journal	June 2021
Optimizing Chemical Reactions with Deep Reinforcement Learning Zhou, Zhenpeng; Li, Xiaocheng; Zare, Richard N. ACS Central Science, Vol. 3, Issue 12 https://doi.org/10.1021/acscentsci.7b00492	journal	November 2017
Chemical Robotics Enabled Exploration of Stability in Multicomponent Lead Halide Perovskites via Machine Learning Higgins, Kate; Valleti, Sai Mani; Ziatdinov, Maxim ACS Energy Letters, Vol. 5, Issue 11 https://doi.org/10.1021/acsenergylett.0c01749	journal	October 2020
Elucidating the Weakly Reversible Cs–Pb–Br Perovskite Nanocrystal Reaction Network with High-Throughput Maps and Transformations Dahl, Jakob C.; Wang, Xingzhi; Huang, Xiao Journal of the American Chemical Society, Vol. 142, Issue 27 https://doi.org/10.1021/jacs.0c04997	journal	June 2020
The Earth Mover's Distance as a Metric for Image Retrieval Rubner, Yossi International Journal of Computer Vision, Vol. 40, Issue 2, p. 99-121 https://doi.org/10.1023/a:1026543900054	journal	November 2000
Machine-learning-assisted materials discovery using failed experiments Raccuglia, Paul; Elbert, Katherine C.; Adler, Philip D. F. Nature, Vol. 533, Issue 7601 https://doi.org/10.1038/nature17439	journal	May 2016
Autonomy in materials research: a case study in carbon nanotube growth Nikolaev, Pavel; Hooper, Daylond; Webber, Frederick npj Computational Materials, Vol. 2, Issue 1 https://doi.org/10.1038/npjcompumats.2016.31	journal	October 2016
Autonomous discovery of optically active chiral inorganic perovskite nanocrystals through an intelligent cloud lab Li, Jiagen; Li, Junzi; Liu, Rulin Nature Communications, Vol. 11, Issue 1 https://doi.org/10.1038/s41467-020-15728-5	journal	April 2020
On-the-fly closed-loop materials discovery via Bayesian active learning Kusne, A. Gilad; Yu, Heshan; Wu, Changming Nature Communications, Vol. 11, Issue 1 https://doi.org/10.1038/s41467-020-19597-w	journal	November 2020
Discovery of temperature-induced stability reversal in perovskites using high-throughput robotic learning Zhao, Yicheng; Zhang, Jiyun; Xu, Zhengwei Nature Communications, Vol. 12, Issue 1 https://doi.org/10.1038/s41467-021-22472-x	journal	April 2021
Anthropogenic biases in chemical reaction data hinder exploratory inorganic synthesis Jia, Xiwen; Lynch, Allyson; Huang, Yuheng Nature, Vol. 573, Issue 7773 https://doi.org/10.1038/s41586-019-1540-5	journal	September 2019
A mobile robotic chemist Burger, Benjamin; Maffettone, Phillip M.; Gusev, Vladimir V. Nature, Vol. 583, Issue 7815 https://doi.org/10.1038/s41586-020-2442-2	journal	July 2020
Efficient Closed-loop Maximization of Carbon Nanotube Growth Rate using Bayesian Optimization Chang, Jorge; Nikolaev, Pavel; Carpena-Núñez, Jennifer Scientific Reports, Vol. 10, Issue 1 https://doi.org/10.1038/s41598-020-64397-3	journal	June 2020
Benchmarking the acceleration of materials discovery by sequential learning Rohr, Brian; Stein, Helge S.; Guevarra, Dan Chemical Science, Vol. 11, Issue 10 https://doi.org/10.1039/c9sc05999g	journal	January 2020
Toward autonomous design and synthesis of novel inorganic materials Szymanski, Nathan J.; Zeng, Yan; Huo, Haoyan Materials Horizons, Vol. 8, Issue 8 https://doi.org/10.1039/d1mh00495f	journal	January 2021
Less is more: Sampling chemical space with active learning Smith, Justin S.; Nebgen, Ben; Lubbers, Nicholas The Journal of Chemical Physics, Vol. 148, Issue 24 https://doi.org/10.1063/1.5023802	journal	June 2018
Utilization of machine learning to accelerate colloidal synthesis and discovery Fong, Anthony Y.; Pellouchoud, Lenson; Davidson, Malcolm The Journal of Chemical Physics, Vol. 154, Issue 22 https://doi.org/10.1063/5.0047385	journal	June 2021
Building process design rules for microstructure control in wide-bandgap mixed halide perovskite solar cells by a high-throughput approach Akhundova, Fatima; Lüer, Larry; Osvet, Andres Applied Physics Letters, Vol. 118, Issue 24 https://doi.org/10.1063/5.0049010	journal	June 2021
Using automated serendipity to discover how trace water promotes and inhibits lead halide perovskite crystal formation Nega, Philip W.; Li, Zhi; Ghosh, Victor Applied Physics Letters, Vol. 119, Issue 4 https://doi.org/10.1063/5.0059767	journal	July 2021
On-the-fly autonomous control of neutron diffraction via physics-informed Bayesian active learning McDannald, Austin; Frontzek, Matthias; Savici, Andrei T. Applied Physics Reviews, Vol. 9, Issue 2 https://doi.org/10.1063/5.0082956	journal	June 2022
Efficient estimation of material property curves and surfaces via active learning Tian, Yuan; Xue, Dezhen; Yuan, Ruihao Physical Review Materials, Vol. 5, Issue 1 https://doi.org/10.1103/physrevmaterials.5.013802	journal	January 2021
Ensemble Meta-Learning for Few-Shot Soot Density Recognition Gu, Ke; Zhang, Yonghui; Qiao, Junfei IEEE Transactions on Industrial Informatics, Vol. 17, Issue 3 https://doi.org/10.1109/tii.2020.2991208	journal	March 2021
A Bayesian experimental autonomous researcher for mechanical design Gongora, Aldair E.; Xu, Bowen; Perry, Wyatt Science Advances, Vol. 6, Issue 15 https://doi.org/10.1126/sciadv.aaz1708	journal	April 2020
Self-driving laboratory for accelerated discovery of thin-film materials MacLeod, B. P.; Parlane, F. G. L.; Morrissey, T. D. Science Advances, Vol. 6, Issue 20 https://doi.org/10.1126/sciadv.aaz8867	journal	May 2020
Fingerprinting diverse nanoporous materials for optimal hydrogen storage conditions using meta-learning Sun, Yangzesheng; DeJaco, Robert F.; Li, Zhao Science Advances, Vol. 7, Issue 30 https://doi.org/10.1126/sciadv.abg3983	journal	July 2021
The Diversity of Layered Halide Perovskites Smith, Matthew D.; Crace, Ethan J.; Jaffe, Adam Annual Review of Materials Research, Vol. 48, Issue 1 https://doi.org/10.1146/annurev-matsci-070317-124406	journal	July 2018
Machine Learning in Materials Discovery: Confirmed Predictions and Their Underlying Approaches Saal, James E.; Oliynyk, Anton O.; Meredig, Bryce Annual Review of Materials Research, Vol. 50, Issue 1 https://doi.org/10.1146/annurev-matsci-090319-010954	journal	July 2020
Materials science in the artificial intelligence age: high-throughput library generation, machine learning, and a pathway from correlations to the underpinning physics Vasudevan, Rama K.; Choudhary, Kamal; Mehta, Apurva MRS Communications, Vol. 9, Issue 3 https://doi.org/10.1557/mrc.2019.95	journal	July 2019
On the Likelihood that One Unknown Probability Exceeds Another in View of the Evidence of Two Samples Thompson, William R. Biometrika, Vol. 25, Issue 3/4 https://doi.org/10.2307/2332286	journal	December 1933

Similar Records

Learning together: Towards foundation models for machine learning interatomic potentials with meta-learning

Journal Article · 2024 · npj Computational Materials · OSTI ID:2403610

Allen, Alice Elisabeth Anastasia; Lubbers, Nicholas; Matin, Sakib Edward; +4 more

Learning functional priors and posteriors from data and physics

Journal Article · 2022 · Journal of Computational Physics · OSTI ID:1897198

Meng, Xuhui; Yang, Liu; Mao, Zhiping; +2 more

Learning object-level and meta-level knowledge in expert systems

Thesis/Dissertation · 1984 · OSTI ID:5424026

Fu, L M

Related Subjects

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CHEMISTRY
crystallization
decision theory
machine learning
materials
optimization algorithms
perovskites
robotics

Title: Active meta-learning for predicting and selecting perovskite crystallization experiments

Citation Formats

References (57)

Similar Records

Related Subjects