How do we create our multi-location weather forecast?

We have recently expanded our weather forecast up to 15 days into the future for the entire world. But how do we construct this weather forecast? This article describes the data sources we use and the analysis and processing that we perform to provide you with the weather forecast data.

The datasources – global and local weather models

Our forecast data, as does any modern forecast, starts with a set of computer weather models. Weather models are computer processes that take as input the current state of the atmosphere and use that information to calculate how the atmosphere will change over coming hours and days. The models are based on the physics and chemistry of the atmosphere (and their interaction with the ocean and land masses).

A global model output for surface temperature

Accurately representing the current state of the atmosphere is fundamental to applying the physical and chemical simulations in the computer model to create an accurate prediction. The current state is fed into the computer model from many different types of weather sources. Observations from weather stations and instruments on the ground, sea and in the air are used as are remote measurements from satellites and weather radar.

The computer model then divides the atmosphere into cells where the initial conditions of each cell is set from the observations fed into the model. These cells are arranged in three-dimensional grids. The grids span both geographical area of the model on the ground but also the vertically into the atmosphere. Understanding how the atmosphere behaves above the ground is critical to understanding the weather on the ground. The computer model then steps forwards through time from the initial state and calculates the changes in each cell as they interact with each other over hours and days.

As the size of the cells is reduced, the accuracy of the model forecast is increased. Therefore a model which consists of smaller cells will be more accurate for a longer period than one with larger cells. However the more cells in the model, the more powerful the computer must be in order to process it. Many of the leading weather forecast models are now run on some of the world’s most powerful super computers.

Leading global weather models include the United States National Weather Service’s Global Forecast System (GFS) and the European Center for Medium-Range Weather Forecast (ECMWF) model. The most powerful models are global models that require many cells within their model matrix span the entire atmosphere. The accuracy of the weather forecast can be improved by also running global models in combination with localized models that focus on smaller geographical regions. These local models can use smaller cells and a limited forecast time period to reduce the necessary computing power. These limitations allow the models to be much more accurate for the smaller geogrpahical region and timeframe. For example, localized moddels are available for the United States, Canada, Europe and Australia.

As we have seen, the accuracy of the model relies heavily on the initial conditions, the computer algorithms used to represent the atmosphere, and the computing power available to process the particular model. Differences in any of these factors leads to inevitable differences in the weather forecasted generated by these models. These differences help to assign confidence to the weather forecast. When most models agree, the confidence of the weather forecast being correct is high but when the predictions of the models disagree then the confidence drops. In that case, localized models or local wether forecasting knowledge can be used to help make more accurate predictions.

The Visual Crossing Weather Forecast

The Visual Crossing Weather forecast is the combination of multiple global and local weather forecast models. By combining models we ensure that we achieve the highest degree of accuracy. When multiple models exist, we favour the results of the mesonet (or localized) models as these generally have higher accuracy. Once the combined weather forecast dataset has been created from the models, we then run it through a series of post-processing steps. These processes ensure consistency, accuracy, and the most optimal delivery structure so that multi-location weather forecast look ups can be made instantly via the Weather API or data download page.

The multiple models combine to provide up to 15 days of global forecast coverage. In Visual Crossing Weather, this information is available at the hourly and daily level. For forecast periods beyond 7-10 days, the forecast is only run at three hour intervals.

Many weather element values are included in the weather forecast data including temperature, rainfall, wind, and snowfall. For more information on the variables that are available, please see our weather data documentation .

We hope this introduction to our weather forecast is useful. If you are looking for weather forecast data itself, please check out our weather data and weather API pages to get started.