From The DOE’s Brookhaven National Laboratory: “Machine Learning Framework IDs Targets for Improving Catalysts”
From The DOE’s Brookhaven National Laboratory
May 10, 2022
Karen McNulty Walsh
kmcnulty@bnl.gov
(631) 344-8350
Peter Genzer
genzer@bnl.gov
(631) 344-3174
Method provides details on reaction kinetics and zeros in on steps where tweaks could improve production of desired products.
Brookhaven Lab chemist Ping Liu and Wenjie Liao, a graduate student at Stony Brook University, developed a machine learning framework to identify which chemical reaction steps could be targeted to improve reaction productivity.
Chemists at the U.S. Department of Energy’s Brookhaven National Laboratory have developed a new machine-learning (ML) framework that can zero in on which steps of a multistep chemical conversion should be tweaked to improve productivity. The approach could help guide the design of catalysts—chemical “dealmakers” that speed up reactions.
The team developed the method to analyze the conversion of carbon monoxide (CO) to methanol using a copper-based catalyst. The reaction consists of seven fairly straightforward elementary steps.
“Our goal was to identify which elementary step in the reaction network or which subset of steps controls the catalytic activity,” said Wenjie Liao, the first author on a paper describing the method just published in the journal Catalysis Science & Technology. Liao is a graduate student at Stony Brook University – SUNY who has been working with scientists in the Catalysis Reactivity and Structure (CRS) group in Brookhaven Lab’s Chemistry Division.
Ping Liu, the CRS chemist who led the work, said, “We used this reaction as an example of our ML framework method, but you can put any reaction into this framework in general.”
Targeting activation energies
Picture a multistep chemical reaction as a rollercoaster with hills of different heights. The height of each hill represents the energy needed to get from one step to the next. Catalysts lower these “activation barriers” by making it easier for reactants to come together or allowing them to do so at lower temperatures or pressures. To speed up the overall reaction, a catalyst must target the step or steps that have the biggest impact.
Traditionally, scientists seeking to improve such a reaction would calculate how changing each activation barrier one at a time might affect the overall production rate. This type of analysis could identify which step was “rate-limiting” and which steps determine reaction selectivity—that is, whether the reactants proceed to the desired product or down an alternate pathway to an unwanted byproduct.
This graphic shows the seven-step reaction pathway of CO hydrogenation to methanol over copper-based catalysts, including the reactants at each step, schematic atomic arrangements of the intermediates, and the energy activation barriers required to get from step to step. The Brookhaven Lab team demonstrated a machine learning framework that successfully identified which steps/combinations of steps to tweak to improve methanol production. Their work could help guide the design of new catalysts to achieve that goal and the framework can be applied to optimize other reactions.
But, according to Liu, “These estimations end up being very rough with a lot of errors for some groups of catalysts. That has really hurt for catalyst design and screening, which is what we are trying to do,” she said.
The new machine learning framework is designed to improve these estimations so scientists can better predict how catalysts will affect reaction mechanisms and chemical output.
“Now, instead of moving one barrier at a time we are moving all the barriers simultaneously. And we use machine learning to interpret that dataset,” said Liao.
This approach, the team said, gives much more reliable results, including about how steps in a reaction work together.
“Under reaction conditions, these steps are not isolated or separated from each other; they are all connected,” said Liu. “If you just do one step at a time, you miss a lot of information—the interactions among the elementary steps. That’s what’s been captured in this development,” she said.
Building the model
The scientists started by building a data set to train their machine learning model. The data set was based on “density functional theory” (DFT) calculations of the activation energy required to transform one arrangement of atoms to the next through the seven steps of the reaction. Then the scientists ran computer-based simulations to explore what would happen if they changed all seven activation barriers simultaneously—some going up, some going down, some individually, and some in pairs.
“The range of data we included was based on previous experience with these reactions and this catalytic system, within the interesting range of variation that is likely to give you better performance,” Liu said.
By simulating variations in 28 “descriptors”—including the activation energies for the seven steps plus pairs of steps changing two at a time—the team produced a comprehensive dataset of 500 data points. This dataset predicted how all those individual tweaks and pairs of tweaks would affect methanol production. The model then scored the 28 descriptors according to their importance in driving methanol output.
“Our model ‘learned’ from the data and identified six key descriptors that it predicts would have the most impact on production,” Liao said.
After the important descriptors were identified, the scientists retrained the ML model using just those six “active” descriptors. This improved ML model was able to predict catalytic activity based purely on DFT calculations for those six parameters.
“Rather than you having to calculate the whole 28 descriptors, now you can calculate with only the six descriptors and get the methanol conversion rates you are interested in,” said Liu.
The team says they can also use the model to screen catalysts. If they can design a catalyst that improves the value of the six active descriptors, the model predicts a maximal methanol production rate.
Understanding mechanisms
When the team compared the predictions of their model with the experimental performance of their catalyst—and the performance of alloys of various metals with copper—the predictions matched up with the experimental findings. Comparisons of the ML approach with the previous method used to predict alloys’ performance showed the ML method to be far superior.
The data also revealed a lot of detail about how changes in energy barriers could affect the reaction mechanism. Of particular interest—and importance—was how different steps of the reaction work together. For example, the data showed that in some cases, lowering the energy barrier in the rate-limiting step alone would not by itself improve methanol production. But tweaking the energy barrier of a step earlier in the reaction network, while keeping the activation energy of the rate-limiting step within an ideal range, would increase methanol output.
“Our method gives us detailed information we might be able to use to design a catalyst that coordinates the interaction between these two steps well,” Liu said.
But Liu is most excited about the potential for applying such data-driven ML frameworks to more complicated reactions.
“We used the methanol reaction to demonstrate our method. But the way that it generates the database and how we train the ML model and how we interpolate the role of each descriptor’s function to determine the overall weight in terms of their importance—that can be applied to other reactions easily,” she said.
The research was supported by the DOE Office of Science (BES). The DFT calculations were performed using computational resources at the Center for Functional Nanomaterials (CFN), which is a DOE Office of Science User Facility at Brookhaven Lab, and at the National Energy Research Scientific Computing Center (NERSC), DOE Office of Science User Facility at The DOE’s Lawrence Berkeley National Laboratory.
See the full article here .
five-ways-keep-your-child-safe-school-shootings
Please help promote STEM in your local schools.
Stem Education Coalition
One of ten national laboratories overseen and primarily funded by the The DOE Office of Science, The DOE’s Brookhaven National Laboratory conducts research in the physical, biomedical, and environmental sciences, as well as in energy technologies and national security. Brookhaven Lab also builds and operates major scientific facilities available to university, industry and government researchers. The Laboratory’s almost 3,000 scientists, engineers, and support staff are joined each year by more than 5,000 visiting researchers from around the world. Brookhaven is operated and managed for DOE’s Office of Science by Brookhaven Science Associates, a limited-liability company founded by Stony Brook University the largest academic user of Laboratory facilities, and Battelle, a nonprofit, applied science and technology organization.
Research at BNL specializes in nuclear and high energy physics, energy science and technology, environmental and bioscience, nanoscience and national security. The 5,300 acre campus contains several large research facilities, including the Relativistic Heavy Ion Collider [below] and National Synchrotron Light Source II [below]. Seven Nobel prizes have been awarded for work conducted at Brookhaven lab.
BNL is staffed by approximately 2,750 scientists, engineers, technicians, and support personnel, and hosts 4,000 guest investigators every year. The laboratory has its own police station, fire department, and ZIP code (11973). In total, the lab spans a 5,265-acre (21 km^2) area that is mostly coterminous with the hamlet of Upton, New York. BNL is served by a rail spur operated as-needed by the New York and Atlantic Railway. Co-located with the laboratory is the Upton, New York, forecast office of the National Weather Service.
Major programs
Although originally conceived as a nuclear research facility, Brookhaven Lab’s mission has greatly expanded. Its foci are now:
Nuclear and high-energy physics
Physics and chemistry of materials
Environmental and climate research
Nanomaterials
Energy research
Nonproliferation
Structural biology
Accelerator physics
Operation
Brookhaven National Lab was originally owned by the Atomic Energy Commission(US) and is now owned by that agency’s successor, the United States Department of Energy (DOE). DOE subcontracts the research and operation to universities and research organizations. It is currently operated by Brookhaven Science Associates LLC, which is an equal partnership of Stony Brook University and Battelle Memorial Institute. From 1947 to 1998, it was operated by Associated Universities, Inc.(AUI), but AUI lost its contract in the wake of two incidents: a 1994 fire at the facility’s high-beam flux reactor that exposed several workers to radiation and reports in 1997 of a tritium leak into the groundwater of the Long Island Central Pine Barrens on which the facility sits.
Foundations
Following World War II, the US Atomic Energy Commission was created to support government-sponsored peacetime research on atomic energy. The effort to build a nuclear reactor in the American northeast was fostered largely by physicists Isidor Isaac Rabi and Norman Foster Ramsey Jr., who during the war witnessed many of their colleagues at Columbia University leave for new remote research sites following the departure of the Manhattan Project from its campus. Their effort to house this reactor near New York City was rivalled by a similar effort at the Massachusetts Institute of Technology to have a facility near Boston, Massachusetts. Involvement was quickly solicited from representatives of northeastern universities to the south and west of New York City such that this city would be at their geographic center. In March 1946 a nonprofit corporation was established that consisted of representatives from nine major research universities — Columbia University, Cornell University, Harvard University, Johns Hopkins University, Massachusetts Institute of Technology, Princeton University, University of Pennsylvania, University of Rochester, and Yale University.
Out of 17 considered sites in the Boston-Washington corridor, Camp Upton on Long Island was eventually chosen as the most suitable in consideration of space, transportation, and availability. The camp had been a training center from the US Army during both World War I and World War II. After the latter war, Camp Upton was deemed no longer necessary and became available for reuse. A plan was conceived to convert the military camp into a research facility.
On March 21, 1947, the Camp Upton site was officially transferred from the U.S. War Department to the new U.S. Atomic Energy Commission (AEC), predecessor to the U.S. Department of Energy (DOE).
Research and facilities
Reactor history
In 1947 construction began on the first nuclear reactor at Brookhaven, the Brookhaven Graphite Research Reactor. This reactor, which opened in 1950, was the first reactor to be constructed in the United States after World War II. The High Flux Beam Reactor operated from 1965 to 1999. In 1959 Brookhaven built the first US reactor specifically tailored to medical research, the Brookhaven Medical Research Reactor, which operated until 2000.
Accelerator history
In 1952 Brookhaven began using its first particle accelerator, the Cosmotron. At the time the Cosmotron was the world’s highest energy accelerator, being the first to impart more than 1 GeV of energy to a particle.
The Cosmotron was retired in 1966, after it was superseded in 1960 by the new Alternating Gradient Synchrotron (AGS).
BNL Alternating Gradient Synchrotron (AGS).
The AGS was used in research that resulted in 3 Nobel prizes, including the discovery of the muon neutrino, the charm quark, and CP violation.
In 1970 in BNL started the ISABELLE project to develop and build two proton intersecting storage rings.
The groundbreaking for the project was in October 1978. In 1981, with the tunnel for the accelerator already excavated, problems with the superconducting magnets needed for the ISABELLE accelerator brought the project to a halt, and the project was eventually cancelled in 1983.
The National Synchrotron Light Source operated from 1982 to 2014 and was involved with two Nobel Prize-winning discoveries. It has since been replaced by the National Synchrotron Light Source II. [below].
BNL National Synchrotron Light Source.
After ISABELLE’S cancellation, physicist at BNL proposed that the excavated tunnel and parts of the magnet assembly be used in another accelerator. In 1984 the first proposal for the accelerator now known as the Relativistic Heavy Ion Collider (RHIC)[below] was put forward. The construction got funded in 1991 and RHIC has been operational since 2000. One of the world’s only two operating heavy-ion colliders, RHIC is as of 2010 the second-highest-energy collider after the Large Hadron Collider(CH). RHIC is housed in a tunnel 2.4 miles (3.9 km) long and is visible from space.
On January 9, 2020, It was announced by Paul Dabbar, undersecretary of the US Department of Energy Office of Science, that the BNL eRHIC design has been selected over the conceptual design put forward by DOE’s Thomas Jefferson National Accelerator Facility [Jlab] (US) as the future Electron–ion collider (EIC) in the United States.
Brookhaven Lab Electron-Ion Collider (EIC) to be built inside the tunnel that currently houses the RHIC.
In addition to the site selection, it was announced that the BNL EIC had acquired CD-0 from the Department of Energy. BNL’s eRHIC design proposes upgrading the existing Relativistic Heavy Ion Collider, which collides beams light to heavy ions including polarized protons, with a polarized electron facility, to be housed in the same tunnel.
Other discoveries
In 1958, Brookhaven scientists created one of the world’s first video games, Tennis for Two. In 1968 Brookhaven scientists patented Maglev, a transportation technology that utilizes magnetic levitation.
Major facilities
Relativistic Heavy Ion Collider (RHIC), which was designed to research quark–gluon plasma and the sources of proton spin. Until 2009 it was the world’s most powerful heavy ion collider. It is the only collider of spin-polarized protons.
Center for Functional Nanomaterials (CFN), used for the study of nanoscale materials.
BNL National Synchrotron Light Source II, Brookhaven’s newest user facility, opened in 2015 to replace the National Synchrotron Light Source (NSLS), which had operated for 30 years. NSLS was involved in the work that won the 2003 and 2009 Nobel Prize in Chemistry.
Alternating Gradient Synchrotron, a particle accelerator that was used in three of the lab’s Nobel prizes.
Accelerator Test Facility, generates, accelerates and monitors particle beams.
Tandem Van de Graaff, once the world’s largest electrostatic accelerator.
Computational Science resources, including access to a massively parallel Blue Gene series supercomputer that is among the fastest in the world for scientific research, run jointly by Brookhaven National Laboratory and Stony Brook University-SUNY.
Interdisciplinary Science Building, with unique laboratories for studying high-temperature superconductors and other materials important for addressing energy challenges.
NASA Space Radiation Laboratory, where scientists use beams of ions to simulate cosmic rays and assess the risks of space radiation to human space travelers and equipment.
Off-site contributions
It is a contributing partner to the ATLAS experiment, one of the four detectors located at the The European Organization for Nuclear Research [La Organización Europea para la Investigación Nuclear][Organisation européenne pour la recherche nucléaire] [Europäische Organisation für Kernforschung](CH)[CERN] Large Hadron Collider(LHC).
The European Organization for Nuclear Research [La Organización Europea para la Investigación Nuclear][Organisation européenne pour la recherche nucléaire] [Europäische Organisation für Kernforschung](CH)[CERN] map.
Iconic view of the European Organization for Nuclear Research [La Organización Europea para la Investigación Nuclear] [Organisation européenne pour la recherche nucléaire] [Europäische Organisation für Kernforschung](CH) [CERN] ATLAS detector.
It is currently operating at The European Organization for Nuclear Research [La Organización Europea para la Investigación Nuclear][Organisation européenne pour la recherche nucléaire] [Europäische Organisation für Kernforschung](CH) [CERN] near Geneva, Switzerland.
Brookhaven was also responsible for the design of the Spallation Neutron Source at DOE’s Oak Ridge National Laboratory, Tennessee.
DOE’s Oak Ridge National Laboratory Spallation Neutron Source annotated.
Brookhaven plays a role in a range of neutrino research projects around the world, including the Daya Bay Neutrino Experiment (CN) nuclear power plant, approximately 52 kilometers northeast of Hong Kong and 45 kilometers east of Shenzhen, China.
Daya Bay Neutrino Experiment (CN) nuclear power plant, approximately 52 kilometers northeast of Hong Kong and 45 kilometers east of Shenzhen, China .

DOE’s Fermi National Accelerator Laboratory DUNE LBNF from FNAL to Sanford Underground Research Facility, Lead, South Dakota, USA.

BNL National Synchrotron Light Source II.
Reply