The science of weather forecasting has a long history. As early as 650 BC. The Babylonians used cloud patterns and astrology to make predictions. But weather forecasting didn’t take off until the 19th century.
Fast-forward 150 years, and the science of weather forecasting has changed beyond recognition. Today, thanks to supercomputers, it is possible to make more accurate forecasts about the weather. With today’s knowledge, and especially data, these powerful computers can produce smart data about the weather tomorrow, the day after tomorrow and who knows, even next month.
Faster and better results
“The data used in weather forecasting comes from a variety of sources, provided by satellites, weather stations, balloons, planes, and even ships.”
To do their job, supercomputers need data. The same goes for the weather forecast. The data used for this comes from various sources, provided by satellites, weather stations, balloons, planes, and even ships. In addition, weather forecasters have access to the Global Telecommunication System (GTS), which collects and distributes data four times a day at six-hour intervals.
The data provided by these sources can range from five hundred gigabytes to one terabyte. Before this data can be used, it is subject to quality control. Once this process is complete, mathematical models make predictions. These models – already in use since the 19th century – are equations that describe the state, motion, and evolution of time for atmospheric parameters such as wind and temperature.
Unprecedented powerful computing power
Converting these equations into accurate predictions requires computational power. If we divide a large country into a network of blocks of ten kilometers in length, a significant level of computational power is required to make local predictions within each block. But making predictions about smaller blocks presents a real challenge. Thunderstorms and small-scale effects are closely related to the local weather. With a web so large for a small mass, these effects are easy to overlook. He is like a hunter. For catching small fish, a fine net is needed.
The smaller surface area requires an extraordinary amount of computing power. For example, it may take 100 computer nodes to make a prediction on a network of blocks of ten kilometers in length. But forecasting over a three-mile network of the same region requires sixteen times as much computing power. For a more concentrated area of 2.5 km, the computing power should be increased by sixteen times.
“Thanks to technological advances, the four-day forecast is now as accurate as the one-day forecast it was 30 years ago.”
Given the amount of computing power required for these computations, scientists are looking to artificial intelligence (AI) technologies. Instead of using powerful calculations to predict weather based on current conditions, AI systems look at data from the past. This has a significant impact on weather forecasts. For example, the UK Met Office recently conducted an experiment using artificial intelligence technology to predict floods and storms. Based on radar maps from 2016 to 2018, the system was able to accurately predict 2019 precipitation patterns in nearly 90 percent of cases. Thanks to advances in technology, four-day forecasts are now as accurate as the one-day forecasts they were thirty years ago.
New technologies herald an era of more accurate weather forecasting. Despite this, long-term forecasts about the weather will not be 100% accurate. This is because the equations used to make weather forecasts are nonlinear – there is a certain kind of weirdness to them.
In addition, the science of weather forecasting is relatively late. Although technology doubles computing power approximately every two years, it still takes longer before science actually puts this power to good use in their knowledge and research.
However, weather forecasts have greatly improved thanks to the current computing power. To give an example of the difference between the past and the present, a weather model that would have lasted 600 years on computer systems in the 1960s now only lasts 15 minutes on a standard server.
As computing power advances in the coming years, as well as scientific knowledge about weather patterns, it will be possible to predict with greater accuracy. This is critical, because by predicting severe weather, supercomputers can save lives and have a huge impact on the world.
(Author Zaphiris Christidis is Lenovo’s weather segment lead.)
“Travel enthusiast. Alcohol lover. Friendly entrepreneur. Coffeeaholic. Award-winning writer.”