Project

A good indoor environment at school is important for the health and well-being of pupils and staff, and has a significant impact on pupils' learning outcomes.

Good maintenance of buildings and operation of the technical facilities is important to have good indoor climate, but it is also crucial that staff and pupils use the school buildings correctly and are involved in practical indoor environment work at school level.

This requires that staff and pupils are aware of and have knowledge of how their behavior affects the indoor climate, as well as how the individual can contribute to ensuring as good an indoor climate as possible at the school.

Data from indoor climate sensors, combined with information about how employees and pupils experience indoor climate and related health problems, can provide new opportunities to both identify indoor climate problems, find the cause and identify the right measures, and to create new tools that engage and involve the users of the school buildings.

Today's schools are largely equipped with sensor systems for indoor climate, but there are no tools to collect data on user experiences. Data from integrated sensors is to a small extent available to the school. Information on connections between sensor data and experiences is currently lacking.

DIGG-MIN-SKOLE vill combine data from sensors that are an integral part of the school's technical facilities and/or individual indoor climate sensors with self-acquired data related to user experience.

This data will be used to develop a machine learning model that can estimate the probability that the users will experience reduced well-being/health problems, which factors in the indoor climate are most likely to be the cause of the health problems (temperature, light conditions, noise, CO₂ etc.) and identify targeted mitigating measures at school /classroom level.

Unit managers, staff and students must contribute to the design of (part) tools so that the results from the machine learning model are suitable for use in the school's everyday life. The end result will be a technical specification and demonstration of a user-oriented management system (BOF) in several schools.

Project

The project is a continuation of the first phase of the SEN4POL project and will evaluate the potential of using satellite data for mapping and predicting birch pollen in Norway.

The project exploits the satellite data provided by the Sentinel-2 and Sentinel-3 platforms, that are operated by the European Copernicus programme, in order to provide spatially more detailed information about vegetation status and surface properties.

This information is then used to developed improved predictions regarding the onset of the birch pollen season. We primarily use the Ocean and Land Color Instrument (OLCI) and the Sea and Land Surface Temperature Radiometer (SLSTR) on Sentinel-3 and the Multi Spectral Instrument (MSI) onboard of the Sentinel-2-plattform.

The long-term goal of this multiple-phase project is to develop an automated satellite-based pollen service that can be operated and used internally at NAAF for contributing to the ongoing work related to the governmental mandate that this organisation has to deliver pollen predictions to the public.

The project is a collaboration between NILU, Norwegian Computing Center and the Norwegian Asthma and Allergy Association.