Migration to Mars and life on Mars have long been described in science fiction. But before this dream can become a reality, humans must overcome an obstacle: the planet’s lack of chemicals, such as oxygen, that are needed for long-term survival. However, the recent discovery of water activity on Mars is promising.

Scientists are currently investigating the possibility of splitting water to produce oxygen through electrochemical oxidation of water under the influence of solar energy using oxygen evolution reaction (OER) catalysts. The challenge is to find a way to synthesize these catalysts in situ using materials from Mars, rather than transporting them from Earth, which is expensive.

To solve this problem, a team led by Professor Luo Yi, Professor Jiang Jun and Professor Shang Weiwei from the University of Science and Technology of China (USTC) of the Chinese Academy of Sciences (CAS) recently made it possible to synthesize and optimize OER. They automatically retrieve catalysts from meteorites on Mars using robotic artificial intelligence (AI) chemists.

“Chemist innovatively synthesized artificial intelligence[d] It is an OER catalyst using Martian material based on interdisciplinary collaboration,” said Professor Luo Yi, the group’s principal investigator. In each experiment cycle, an AI chemist first analyzes the elemental composition of Martian ores using laser beam diffraction spectroscopy (LIBS).

A series of ore pretreatments are then performed, including weighing in the solid dosing workstation, preparing stock solutions in the liquid dosing workstation, performing liquid separation in the centrifuge workstation, and achieving solidification in the dryer workstation.

The resulting metal hydroxides are treated with Nafion adhesive to prepare the working electrode for OER testing in an electrochemical workstation. Test data is sent in real time to the AI ​​chemist’s computational “brain” for machine learning (ML) processing.

The AI ​​chemist’s “brain” uses quantum chemistry and molecular dynamics simulations for 30,000 high-entropy hydroxides with different element ratios and calculates their OER catalytic activity using density functional theory. Simulation data is used to train a neural network model to quickly predict the activity of catalysts with different elemental compositions.

Finally, using Bayesian optimization, the brain predicts the combination of available Martian ores required to synthesize the optimal OER catalyst.

Meanwhile, a chemist with artificial intelligence has created a wonderful catalyst using five types of Martian meteorites in an unmanned environment. This catalyst can operate stably for more than 550,000 seconds at a current density of 10 mA cm.^-2 and overvoltage 445.1 mV. Further tests at -37 °C, the temperature on Mars, confirmed that the catalyst could stably produce oxygen without any apparent degradation.

An AI chemist completed in two months a complex catalyst optimization that would have taken a human chemist 2000 years. The team is working to develop AI Chemist into a general experimental platform for various chemical syntheses without human intervention. The paper reviewer noted: “Such research is of broad interest and is rapidly developing in the field of synthesis and discovery of organic/inorganic materials.”

“In the future, people will be able to create an oxygen plant on Mars with the help of artificial intelligence chemists,” Jiang said. Only 15 hours of solar radiation is required to obtain sufficient oxygen concentration necessary for human survival. “This revolutionary technology brings us one step closer to realizing our dream of living on Mars,” he said. Source