Scientists Develop New AI System to Predict Weather Changes
Aiming at preventing energy waste, a team of US researchers has developed a new AI system that can predict the accuracy of weather forecasts and use this information to better control heating systems inside houses.
The new system includes a mathematical model that considers building characteristics such as the size and shape of rooms, the construction materials, and the position of windows, and takes them all into consideration when setting up the interior heating system so it can meet the temperatures changes.
Fengqi You, a professor in energy systems engineering at Cornell University, says the smart control system can reduce energy usage by up to 10%, according to a case study his team has conducted on a nearly 90-year-old building on Cornell's campus, the German News Agency reported.
The Tech Xplore website cited You saying: "If the building itself could be 'smart' enough to know the weather conditions, it could make better adjustments to automatically control its heating and cooling systems to save energy and make occupants more comfortable."
"For instance, if I know the sun is going to come up very soon, it's going to be warm, then you probably don't need to heat the house so much. If I know a storm is coming tonight, then I try to heat up a little bit so I can maintain a comfortable level. We try to make the energy system smart, so it can predict a little bit of the future and make the optimal decisions," You added.
The researchers fed the new system with years' worth of data on forecasts and actual weather conditions to train it on making accurate weather predictions later. The model can detect uncertainty not just in temperature but many other factors including precipitation and sunlight.
You sees that combining the machine learning algorithms and the mathematical programming methods creates a system that can control home heating systems and irrigation in agriculture, and other facilities in urban and rural communities, whether in closed or opened places.
"We don't have a perfect way to forecast the weather, so the best thing we can do is combine AI and mechanistic modeling together," You concluded.