Project

The SNOWDEPTH project will, as the first in the world, directly measure snow depths globally at high spatial resolution from freely available ICESat-2 NASA spaceborne laser altimetry data available since autumn 2018.

To generate global monthly snow depth maps, including for mountainous and forested areas, we will combine the ICESat-2-derived snow depths with Sentinel snow cover/depth data in an ensemble-based data assimilation (DA) framework.

This global snow depth data will fill a large data and knowledge gap within hydrology and cryosphere/climate sciences and is directly relevant for the three application cases within the project: permafrost, high-elevation precipitation and climate reanalysis. The project has two parts and is supported by field activities for ground reference.

In phase 1, we will develop algorithms to derive snow depths at two complementary scales:

• local snow depths from ICESat-2 profiles that capture the high spatial variability in areas with small-scale topography, and
• global snow depth maps with monthly temporal resolution, using DA methods.

In phase 2, we will use the derived snow depths within three application fields where they directly benefit to advance the state of the art:

• Permafrost: include snow depths in an existing model framework to greatly improve modelling of the ground thermal regime, both locally at targeted field sites and at global scale. The current lack of snow depth data is a key bottleneck for permafrost modelling.
• High-elevation precipitation: analyse how snow depths vary across orographic barriers to increase understanding of high-altitude precipitation processes. These are currently largely unconstrained due to lack of measurements.
• Climate reanalysis: verify and improve operational and climate reanalysis products through cross-comparison and improved process understanding. In data-sparse areas, reanalysis products are less accurate and largely model-driven given the lack of observations.

Project

Existing air quality (AQ) monitoring and management (AQMS) methods and evolving modelling practices across Norwegian and European cities have achieved significant improvements of AQ but further progress is needed due to some quality-driven requirements, such as low-latency AQ prediction. This can only be achieved by intelligent data processing at multiple levels of granularity.

To this end, affordable, effective and intelligent tools are needed that utilize the current advances in digitization of all spheres of society, providing radical innovation of air quality management.

The AirQMan project promises autonomous computational methods and techniques that can be used to develop such solutions, and has the potential for opening up a new era in air quality management. Our strong belief is that such a system can be realized across the Edge-Fog-Cloud continuum, extending data processing and computational intelligence from the Cloud to multiple levels of Fog nodes towards the edge of the network.

The project will develop AirQDM – a novel data processing design model that will autonomously determine the optimal data fusion processing flow, the right data sources, and the right trained deep learning (DL) model for maximizing the accuracy of a prediction related to an AQ request.

A second innovation of the project, AirQWare will determine (predict) the optimal distributed deployment for an efficient computation of the DL model while satisfying requirements on accuracy and latency, and adapt the deployment of the DL model during runtime as necessary to maintain accuracy and latency requirements.

By applying the AirQMan approach, the new generation of AQMS will provide: i) low-latency data validation and fusion to increase the accuracy of air quality evaluation, and to support intelligent services, respectively, and ii) cognitive decision making with various degrees of autonomy enabling low-latency actuations of AQ mitigations.