British researchers say they have created an artificial intelligence (AI) model that is highly effective at predicting rainfall within the next 90 minutes.

The model was built by scientists at Google-owned research company DeepMind in London. The company partnered with researchers at the University of Exeter in Britain and the Met Office, the British government’s national weather service. The team says tests of the system showed it produced more accurate predictions, or forecasts, for short-term rainfall than other existing systems.

Accurate nowcasting can be a very important tool for preparing for possible weather emergencies. It can be used by officials in the areas of water management, agriculture, air and ground traffic control and outdoor event planning. “We were especially interested in the ability of these models to make predictions on medium to heavy-rain events, which are the events that most impact people and the economy,” the team said. The scientists said their model aims to create predictive “movies” of immediate weather patterns. They said that, unlike other systems, theirs can accurately capture large-scale events, as well as several different rain possibilities. This combination permits “rainfall uncertainties” to be deeply explored.

During the testing process, the team said the model showed “statistically significant” improvements in these areas compared to competing methods. In addition, the researchers reported that a group of more than 50 weather experts from the Met Office rated the AI model to be more accurate and useful in 89 percent of cases than existing forecasting systems.

Despite the study results, researchers admitted that the model still has limitations. They said “more work is needed to improve the accuracy of long-term predictions and the accuracy on rare and intense events.” The team said it will now center on developing new methods to test and measure the model's performance. It will also work to create more specialized systems to work in real-world conditions.

A New Jersey high schooler, Selina Zhang is no stranger to the spotted lanternfly (斑衣蜡蝉). The now 18-year-old first noticed it when visiting a market near her hometown of Annandale in primary school. It jumped from a plant to a plant to feed on their sap (汁液), affecting over 70 species. In its wake, the plants became stressed, which increased their chances of falling ill and being attacked.

“As I got older, I wanted to take concrete action,” says Zhang. “So I’ve built ArTreeficial, a solar -powered, self-cleaning and artificial -intelligence-driven tree that attracts the spotted lanternfly and removes it using an electric shock.”

On top of conducting an extensive literature review of existing researches, Zhang carefully observed the spotted lanternflies in the wild for weeks, tracking how they grew over time and how they travelled over unfamiliar structures. She took over 500 photos of them, which she logged in a personal database.

Zhang wanted to create a tree-like structure that copied the tree of heaven, a known host plant of the spotted lanternfly, as the primary lure (诱饵) for her trap. So, she uprooted the umbrella from her family’s yard and got to work. First, she used ultrasound to give off a smell made from the essence of the tree of heaven from ArTreeficial’s trunk to attract them. Second, she designed a double-layered electric net for the tree, which would use machine learning to shock spotted lanternflies once they landed on the tree. Then, Zhang used her database of photos to inform and program her AI model.

Zhang’s net s are divided into multiple squares going up and down the structure. When a spotted lanternfly steps on the inner net, the Al model operates. Electricity courses through that particular section, while the rest remain inactive, and the insect is attacked.

Julie Urban, a spotted lanternfly expert at Pennsylvania State University, says that Zhang’s AI approach is incredibly innovative and could be useful in multiple environments.

A new electric car from Sweden comes in a flatpack (散装组件) box and it needs putting together.

Stockholm-based Luvly, founded in 2015, designed the microcar to be small and very light so that it could reduce the emissions (排放) that regular shipping entails.

There are countless tiny cars and electric tiny cars that are too small to be considered passenger vehicles. They are becoming very popular in Europe because of convenience, affordability, and a smaller carbon footprint.

To fill this niche (空缺), Luvly will introduce its first model, the Luvly O, later in 2024. The car will roll out in Stockholm, Paris, and Madrid.

The modern two-seater has a top speed of 55 mph (90 kph) with a 62-mile (100 km) distance per charge. It comes with two portable (便携的) batteries that do not use car chargers. In fact, you can recharge from your workplace or home. This is enough for the majority of travels and trips in the city surroundings.

The cars are not a DIY project. In order to be road safe, the flatpacks will be delivered to licensed car factories to put them together.

Tiny cars are not new and they have actually been around since the 1950s. These small lightweight vehicles have developed a name of being unsafe. That’s due to the light designs and limited crumple areas (防撞缓冲区).

Microcars also are not required to be crash tested because they are not subject to the same safety rules but the Luvly O is safe. For light vehicles to compete with cars, and hopefully win cars, they must be safe. People will not accept that you change from driving an SUV to driving what is really a motorbike with a shell. The Luvly O was actually inspired by Formula One cars that are light but have a strong base plate.

Luvly plans to license its flat-pack design to other carmakers, allowing them to build their own models. This is the best way to develop this city mini car.