Statistical modeling within the Fathym Forecaster relies on a smaller dataset for model training, which enables the model to generate more consistent results.
Physical models are data driven. They require more raw input for training on a specific forecast point (road type, road base, heat transfer, shade, UV), which yields slower processing cycles and limits scale across cloud resources. Although the physical model will provide a more accurate forecast at one specific point, it loses its value as the user scales across thousands or millions of points along a road segment. The statistical model consistently outperforms the physical model in this use case.
Fathym’s road temperature forecast has been proven to be within 0.5°C during the morning and overnight hours and within 1°C during the heat of the day out to 52 hours, which exceeds the accuracy of physically-based road weather models deployed today.