At MET Norway, a small interdisciplinary team – the Sandbox – tries to improve the communication between the meteorologists and their audience. In 2021, we focused on the communication of forecast uncertainty. The Sandbox created, with input from internal and external experts, solutions for applying linguistic and visual tools for forecasters to communicate about uncertainty. In the article, we share our experiences and lessons learned.

Weather forecast refers to objective estimations of parameters such as temperature, wind, humidity etc. However, attempts have been made to communicate the weather forecast into a more subjective approach, such as the "feels like" temperature. We propose an architecture for an artificial intelligence-based system to provide a forecast that could be more meaningful and actionable for each individual person; a forecast much closer to the way that this person "lives" the weather conditions.

This work used machine learning to produce the first open source building height map of Ireland. This map is intended to more accurately determine Local Climate Zones for use in the underlying physiography dataset in the HARMONIE AROME numerical weather prediction model.