IIn the past year, something of a revolution has hit the world of weather forecasting, as artificial intelligence-based weather forecasts have emerged. Traditional weather forecasting methods rely on creating a digital three-dimensional grid that replicates the state of the atmosphere at the start of the forecast as closely as possible.
Once this “initialized state” is determined, complex equations are used to predict how the state of the atmosphere will evolve in the hours and days ahead. For decades, much research has been done to improve these predictions, focusing on getting the starting point right, increasing the vertical and horizontal resolution of these grids, and, of course, making refinements to the equations.
The new generation of AI weather forecasters takes a completely different approach, learning from analyzing years of initialized data instead of using equations. AI tools are statistical models, so they look for patterns in initialized data over the last few decades and then use them to make predictions. Despite the lack of physical equations, they are remarkably accurate and can be performed in a fraction of the time of traditional methods.
In the world of commodity trading, where accurate forecasting is a key determinant of speculation on the price of food, energy or raw materials, the agility these new models offer to adjust forecast horizons and the time it takes to make a forecast has , to accelerate. has been embraced by traders and analysts looking to gain an advantage.
