Scientists say they have developed a system that uses machine learning to predict when and where lightning will strike. Researchers report the system is able to predict lightning strikes up to 30 minutes before they happen within a 30-kilometre radius.

Lightning is a strong burst of electricity in the atmosphere. Since it carries extremely powerful electric charge, it can be destructive and deadly. European researchers have estimated that between 6, 000 and 24, 000 people are killed by lightning worldwide each year. For this reason, climate scientists have long sought to develop methods of predicting lightning.

The system tested in the experiments used a combination of data from weather stations and machine learning methods. The researchers developed a prediction model that was trained to recognise weather conditions that were likely to cause lightning.

The model was created with the data collected over a 12-year period from 12 Swiss weather stations in cities and mountain areas. The data, related to four main surface conditions: air pressure, air temperature, relative humidity and wind speed, was placed into a unique machine learning algorithm (算法) , which compared it to the records of lightning strikes. Researchers say the algorithm was then able to learn the conditions under which lightning would happen.

The researchers tested the system several times. They found that the system made predictions that proved correct almost 80 percent of the time. “It can now be used anywhere,” the Swiss Federal Institute of Technology said in a statement.

The researchers plan to keep developing the technology in partnership with a European effort that aims to create a lightning protection programme. The effort is called the European Laser Lightning Rod project. Scientists working on the project are experimenting with the laser technology that could someday control lightning activity, transferring lightning charge from clouds to the ground. They hope that such technology can one day be used as protection against lightning strikes. Possible uses could be at stations, airports or places where crowds of people gather.

To tackle the problem of tiny plastics polluting waterways, chemists in the Czech Republic are thinking small. Their brainchild is a new microrobot which is no bigger than the tip of a sharpened pencil. When sunlight hits them, they produce chemical reactions that push them through water in a specific direction. When they find a piece of plastic, they stick to it and start to break it down.

Chemist Martin Pumera at the Czech University led the project. A decade ago, he chose to focus on the problem posed by microplastics. They’re everywhere—from the bottom of the ocean to air blowing onto ice atop mountains. They’ve turned up in drinking water. Some studies estimate that billions of pieces of plastic end up in the world’s waters. The plastic has many sources, from shopping bags to washing and cleaning wipes.

In lab experiments, the star-shaped swimmers stuck onto each of four different types of plastic. And after a week exposed to light, the robots had reduced the weight of the plastics. It wasn’t much—only by percent. But that was an indication that they were breaking the plastic down. They also caused the surface of the plastic to change from smooth to rough. That’s another sign that the robots were degrading (分解) it. The new study is a proof of concept type. That means it shows something can be done successfully.

In fact, Pumera says they still have a long way to go. There are many types of plastics. And even these microrobots are unlikely to succeed in degrading them all. The researchers also have not yet shown how safe this system is for the environment, although Pumera says that’s their next goal. The first real-world test will be in a wastewater-treatment plant. “Indeed,” says one researcher. “We’ll need a lot of testing to show that they’re safe in open waterways, such as at sea.”

The smart clothes industry is targeting specific health conditions. Diabetic (糖尿病的) foot is a major health issue today. The loss of mobility and independence that some with diabetes face, as well as health care—associated costs, is alarming.

Now, Siren Care, a medical device company, has developed an injury-monitoring sock that could help people with diabetes prevent loss of feet. Early discovery is critical in this process. Since skin inflammation (炎症) is accompanied by a rise in temperature, studies show that home monitoring of foot skin temperature could make a big difference.

What is so special about Siren's product is that the sensors are incorporated into the fabric of the socks. The sensor is connected to a PCB battery. whose lifetime is two months if used daily. The socks are only on when users wear them; they go into sleep mode when off. All data from the socks is sent to the Siren app, so the user can monitor the condition of his or her feet in real—time. The application gives foot health scores and, when necessary, reminds the user to adjust activity and/or see a health care professional.

Ran Ma, the company's CEO, says. “Equipped with the novel technology, users can adjust their activity by self-monitoring their skin temperature. But the sock is not a device for illness diagnosis. The user still needs to see a doctor, who can then say exactly what the illness is or the cause of the problem.”

The socks are machine washable and don't need to be charged. Every six months, the user gets a new box with seven pairs of socks to replace the used ones. For customers, the cost is $ 30 per month. This might signal that this technology is becoming more accessible when compared to the price of similar smart clothing. Siren presented their product at this year's CES event in Las Vegas and announced that they were planning to start shipping their socks this summer. And the company is already planning future applications that will go beyond diabetes care.