Seasonal Forecasting Engine

The aim of SFE is to develop a state-of-the-art operational seasonal climate prediction system for Northern Europe and the Arctic. Our motivation is that many companies and public stakeholders face climate-related risks that must be managed to stay competitive and to protect life, property and the environment. Tailored seasonal predictions can be helpful tools for risk mitigation, and they can guide more efficient use of resources in many sectors of society, including agriculture, energy, water, transportation, and insurance. To our users, the SFE will be accessible through a flexible interface which can be queried to obtain predictions of relevant climate indices and variables. Under the hood, our ‘engine’ consists of statistical algorithms that merge vast amounts of data into unified forecasts.

The 5-year project is funded by the Research Council of Norway. Read more on the SFE project’s web page (Norwegian web page here).

Bjerknes Climate Prediction Unit

The BCPU’s primary objective is to enhance climate prediction to the level where it benefits society, and thus facilitate the needed transition to operational forecasts. The centre focuses on predicting climate in the Atlantic-to-Arctic sector and surrounding continents from a season to a decade and beyond.

The 5-year project is funded by the Trond Mohn Foundation and the University of Bergen. Read more on the BCPU project’s web page.


CONFER is a multi-national collaboration to bolster resilience to climate impacts and reduce disaster risk in East Africa, potentially reaching 365 million people in eleven countries. Our main objective is to co-develop dedicated climate services for the water, energy and food security sectors with stakeholders and end-users, to enhance their ability to plan for and adapt to seasonal climate fluctuations. The scientific work in CONFER is ambitious and aims to break new ground along three inter-related tracks. First, we will secure end-user engagement by using the Greater Horn of Africa Climate Outlook Fora, which are held three times per year and attract about 200 stakeholders, as platforms for co-production of new and dedicated climate services for our focus sectors. Second, we will improve on the accuracy and local detail of numerical prediction model outputs for East Africa, with a particular focus on seasonal prediction. Third, we will develop statistical and machine learning tools to obtain a new level of seasonal forecast skill based on numerical models and high- resolution satellite data. We will also involve our scientific experts in a large training and capacity development programme designed to enhance climate information uptake in our focus sectors.