In order to survive trips to Mars, humans need oxygen. Now, a team of scientists has designed a robot that could extract oxygen from water on the Red Planet.

The robot, which is called “AI chemist”, used a machine learning model to find a compound that could ignite an oxygen-producing chemical reaction on Mars. The compound, known as a catalyst (催化剂), is made entirely from elements found in Martian meteorites (陨石)   — which means, if such a system could work reliably, space travelers would not need to bring oxygen or even the catalyst needed to produce it.

Mars’ atmosphere contains only trace amounts of oxygen. But scientists have detected evidence of liquid water beneath the planet’s southern ice cap. To create the breathable gas, researchers wanted to find a way to break down this water into its hydrogen and oxygen molecules using materials found on Mars.

Their robot analyzed five meteorites that either came from Mars or had a composition similar to that of the Martian surface. Using a laser, it identified significant amounts of iron, nickel, calcium, magnesium, aluminum and manganese in the samples. From these six elements, the robot’s algorithm (算法) determined it could produce more than 3.7 million possible molecules to break down water and form oxygen on Mars. According to the researchers, finding the best one from this extensive list would take roughly 2,000 years of human labor, but for the AI chemist, it took only weeks.

“On Earth, we don’t use these six elements,” Yi Luo, a co-author of the study says. “They are not the best choices for catalysts, but it’s only what you’ve got on Mars.”

With its chosen catalyst, the system could produce oxygen from the Martian materials at around -37℃, demonstrating the chemical reaction could be possible on the cold Martian surface.

Notably, the robot was able to carry out the entire process — analyzing the rock samples, identifying the best possible catalyst and producing it without human intervention.

Network-based technologies have become increasingly widespread, and they are now being used by countless individuals, professionals, and businesses worldwide. Despite their advantages, most network-based systems are highly at risk of malicious (恶意的) attacks.

The consequences of a malicious attack on network-based systems can be extremely harmful. For instance, an attack on a power plant network could leave millions of individuals and offices without electricity, while attacks on social media networks can lead to exposure of user information.

To overcome the weaknesses of network-based systems, computer scientists worldwide have been trying to develop advanced intrusion detection systems (IDSs) (入侵检测系统) that could help to identify malicious attacks, increasing a network’s safety. In recent years, machine learning (ML) algorithms (机器学习算法) have been found to be particularly promising for automatically detecting attacks and intrusions on a network’s functioning.

An important step in the development and training of ML-based IDSs is the selection of data features that a model can rely or focus on when making predictions. Ideally, by analyzing large datasets, researchers should be able to identify the most suitable features for solving a given task using ML tools, and this can also be applied to intrusion detection.

Researchers at Canadian University Dubai in the UAE have recently developed a new feature selection method that could enable the development of more effective ML-based IDSs. This method was found to perform remarkably well when compared with other commonly employed feature selection techniques. Using the features they identified as most important for intrusion detection, the researchers created a highly efficient ML-based detection system. This system was found to be capable of distinguishing between DDoS attacks and harmless network signals with 99% accuracy.

In the future, the feature selection method developed by the researchers and their findings could help the development of new, highly effective IDSs. In addition, the system they created using the features they identified could be applied in real-world settings to detect malicious attacks on real networks.

Do you like the woolly mammoths from the movie Ice Age? Too bad they're extinct? Thanks to recent developments in biotechnology, the stuff of science fiction may soon become a reality through an attractive process called "de-extinction", which aims to bring the extinct species back. The resurrected species are functionally equal to the original extinct species, but they are not exact copies.

There are three primary techniques of de-extinction. One of them is that scientists deliberately select existing species with similar characters to the extinct species to produce later generation. This is a natural method. Another is cloning. A cloned animal is created by obtaining the DNA of the extinct animal. The later generation will be an identical copy of the extinct species. This is only applied to animals that are either endangered or have recently gone extinct, as it requires well-preserved eggs. The third is the newest technique, genetic engineering. It uses gene-editing tools to place selected genes from extinct animals in place of those present in its closest living relative.

If we refer to Jurassic Park , resurrecting extinct animals is a terrible idea. Thankfully, we don't have to worry about dinosaurs running wildly, as their DNA has disintegrated over the 65 million years since their extinction. DNA can survive for several million years at best under certain rare conditions, but does that mean we should do that?

De-extinction is more for ecology than for tourism. Ecologist Ben Novak said, “All animals perform critical roles in their ecosystem. Woolly mammoths, for example, were excellent gardeners. Their disappearance was followed by a loss in diversity and the Arctic grassland became a cold, ice field. If a resurrected animal is always going to be a zoo animal then it shouldn't be brought back.”