TOPICS:DOEEnergyMachine LearningMaterials ScienceOak Ridge National LaboratoryPerovskite Solar CellRobotics
By OAK RIDGE NATIONAL LABORATORY MARCH 23, 2021
Chemical Robotics and Machine Learning to hurry the look for Stable Perovskites
Researchers at ORNL and therefore the University of Tennessee developed an automatic workflow that mixes chemical robotics and machine learning to hurry the look for stable perovskites. Credit: Jaimee Janiga/ORNL, U.S. Dept of Energy
Researchers at the Department of Energy’s Oak Ridge National Laboratory and therefore the University of Tennessee are automating the look for new materials to advance solar power technologies.
A novel workflow published in ACS Energy Letters combines robotics and machine learning to review metal halide perovskites, or MHPs — thin, lightweight, flexible materials with outstanding properties for harnessing light which will be wont to make solar cells, energy-efficient lighting and sensors.
“Our approach speeds exploration of perovskite materials, making it exponentially faster to synthesize and characterize many material compositions directly and identify areas of interest,” said ORNL’s Sergei Kalinin.
The study, a part of an ORNL-UT Science Alliance collaboration, aims to spot the foremost stable MHP materials for device integration.
“Automated experimentation can help us carve an efficient path forward in exploring what’s an immense pool of potential material compositions,” said UT’s Mahshid Ahmadi.
Although MHPs are attractive for his or her high efficiency and low fabrication costs, their sensitivity to the environment limits operational use. Real-world examples tend to degrade too quickly in ambient conditions, like light, humidity or heat, to be practical.
The enormous potential for perovskites presents an inherent obstacle for materials discovery. Scientists face a huge design space in their efforts to develop more robust models. quite thousand MHPs are predicted, and every of those are often chemically modified to get a near limitless library of possible compositions.
“It is difficult to beat this challenge with conventional methods of synthesizing and characterizing samples one at a time,” said Ahmadi. “Our approach allows us to screen up to 96 samples at a time to accelerate materials discovery and optimization.”
The team selected four model MHP systems — yielding 380 compositions total — to demonstrate the new workflow for solution-processable materials, compositions that begin as wet mixtures but dry to solid forms.
The synthesis step employed a programmable pipetting robot designed to figure with standard 96-well microplates. The machine saves time over manually dispensing many various compositions; and it minimizes error in replicating a tedious process that must be performed in just an equivalent ambient conditions, a variable that’s difficult to regulate over extended periods.
Next, researchers exposed samples to air and measured their photoluminescent properties employing a standard optical plate reader.
“It’s an easy measurement but is that the de facto standard for characterizing stability in MHPs,” said Kalinin. “The key’s that conventional approaches would be labor intensive, whereas we were ready to measure the photoluminescent properties of 96 samples in about five minutes.”
Repeating the method over several hours captured complex phase diagrams during which wavelengths of sunshine vary across compositions and evolve over time.
The team developed a machine-learning algorithm to research the info and residential in on regions with high stability.
“Machine learning enables us to urge more information out of sparse data by predicting properties between measured points,” said ORNL’s Maxim Ziatdinov, who led development of the algorithm. “The results guide materials characterization by showing us where to seem next.”
While the study focuses on materials discovery to spot the foremost stable compositions, the workflow could even be wont to optimize material properties for specific optoelectronic applications.
The automated process are often applied to any solution-processable material for time and price savings over traditional synthesis methods.
Reference: “Chemical Robotics Enabled Exploration of Stability in Multicomponent Lead Halide Perovskites via Machine Learning” by Kate Higgins, Sai Mani Valleti, Maxim Ziatdinov, Sergei V. Kalinin and Mahshid Ahmadi, 15 October 2020, ACS Energy Letters.
The research was supported by the Science Alliance, a Tennessee Center of Excellence, and therefore the Center for Nanophase Materials Sciences, a DOE Office of Science User Facility.