There’s a saying in most states about the variability of weather, but it may be truest of Arizona. If you don’t like the conditions, give it 5 minutes or about 200 miles.

That can make things challenging for the Arizona Department of Transportation’s (DOT’s) statewide road weather manager. However, Kevin Duby, who took over the role about a year ago, is up to the task.

A series of research projects to determine the optimal quantity and placement of road weather information systems (RWISs) led by Tae J. Kwon, an assistant professor at the University of Alberta, has recently concluded.

The Aurora Program-sponsored Phase III project developed a systematic, yet transferrable, method for estimating key road surface condition variables between RWIS stations using large-scale data and advanced modeling techniques such as Geostatistics for spatial inference and mapping and Deep Learning for image recognition.

Rivers in the sky with more than twice the water in the Amazon that can become fire hoses of rainfall and wind wreaking havoc on the West Coast is not the start of a climate-related thriller hitting theaters this summer.

Atmospheric rivers, as this weather phenomenon is called, are a reality for western states that can have beneficial impacts—such as replenishing water supplies in drier climates—but often have more negative impacts like decreasing the safety on roadways.

In addition to the implementation of road weather information systems (RWIS) across the state, the Iowa DOT is also evaluating the use of a new system called Pikalert, which provides weather forecasts for each DOT roadway up to 72 hours into the future and includes alerts and treatment recommendations.

By filling the gaps in existing networks, Mini-RWIS increase the value of existing road condition models by expanding their ability to provide the high-resolution forecasting for accurate decision making.