\n<\/p>\n
Breaking oxygen out of a water molecule is a relatively simple process, at least chemically. Even so, it does require components, one of the most important of which is a catalyst. Catalysts enable reactions and are linearly scalable, so if you want more reactions quickly, you need a bigger catalyst. In space exploration, bigger means heavier, which translates into more expensive. So, when humanity is looking for a catalyst to split water into oxygen and hydrogen on Mars, creating one from local Martian materials would be worthwhile. That is precisely what a team from Hefei, China, did by using what they called an \u201cAI Chemist.\u201d<\/p>\n
<\/p>\n Unfortunately, the name \u201cAIChemist\u201d didn\u2019t stick, though that joke might vary depending on the font you read it in. Whatever its name, the team\u2019s work was some serious science. It specifically applied machine learning algorithms that have become all the rage lately to selecting an effective catalyst for an \u201coxygen evolution reaction\u201d by utilizing materials native to Mars.\u00a0<\/p>\n To say it only chose the catalyst isn\u2019t giving the system the full credit it\u2019s due, though. It accomplished a series of steps, including developing a catalyst formula, pretreating the ore to create the catalyst, synthesizing it, and testing it once it was complete. The authors estimate that the automated process saved over 2,000 years of human labor by completing all of these tasks and point to the exceptional results of the testing to prove it.<\/p>\n Before we get to that, though, let\u2019s start with the \u201cinitial conditions.\u201d The team developed an \u201call-in-one\u201d robotic AI chemist capable of performing all these tasks. It was initially based on work done by more limited AI chemists who could read synthetic chemistry literature and estimate the efficacy of different chemical compounds for different tasks. After they built the model, they needed to feed it with some data.<\/p>\n For that data, they selected five different common rocks from the surface of Mars. They estimated that there would be 3,764,376 possible combinations to come out of the elements present in those rocks, depending on how the combinations were manufactured. So, the first task of the AI Chemist was to select one that could act as a catalyst for splitting off oxygen. Part of that dataset was built with 30,000 other theoretical datasets and the results of 243 experiments. The result is a \u201cpolymetallic\u201d material composed of manganese, iron, nickel, magnesium, aluminum, and calcium.\u00a0<\/p>\n Next, a sample of the catalyst would be manufactured for testing. The AI is equipped with a robot arm that took physical samples of meteorites that had been dissolved in hydrochloric acid and attempted to synthesize the suggested catalyst out of those materials. This process involved pretty extreme processes like centrifuging the samples at 7,500g for 5 minutes to separate out the necessary materials and drying out the resultant material. Impressively, all of this was seemingly done without human intervention.<\/p>\n \n
Credit \u2013 Zhu et al.<\/figcaption><\/figure>\n