Menu Close

Use cases

  • Environmental Adaptation Genomics in Drosophila

    Partner: Naturhistorisches Museum Wien, Natural History Museum Vienna (NHMW)

    Combining earth observation and genomics data to study the evolutionary history of the fruit fly Drosophila melanogaster

    In our “Drosophila genomics” use case, we take advantage of comprehensive earth observation data for climate and land use available in the public domain. Martin Kapun briefly introduces this use case in the following video clip.

    In this use case we will combine environmental data with genomic information of fruit fly DNA samples from more than 300 European Drosophila melanogaster populations that were densely sampled through time and space by DrosEU (https://droseu.net), our partner consortium. We are developing tools that facilitate extracting information for sample coordinates from gridded datasets to identify links between genetic variation along the whole Drosophila melanogaster genome and environmental variation. This approach will allow to identify genes that are putatively under selection and involved in adaptation to environmental change. Using machine learning approaches, we further aim to identify combinations of environmental factors that may influence the genetic diversity in natural populations which will help us to better understand the impact of climate change on the accelerating biodiversity crisis.

  • UC1: Spatial and temporal assessment of neighbourhood building stock

    Partners: Stiftelsen Norsk Institutt for Luftforskning, Norwegian Institute for Air Research

    Climate change poses several challenges to European cities, such as droughts, urban heat waves, changing precipitation patterns, floods and (peri-)urban biodiversity loss. These impacts are interrelated with multiple factors such as land use activities around cities and the local socio-economic setting. Large datasets on these factors are available, but they are complex to integrate and analyze due to their different sources, formats and quality. Data cubes and the integration of data therein allow to assess their relationship.

    The primary goal of UC1 is to furnish stakeholders from European institutions (policy makers, urban planners and NGOs) with a comprehensive “toolkit,” to make well-informed decisions to address the multifaceted impacts of climate change. We will perform a cluster analysis of EU cities using data from the climate, land cover/land use and socio-economic domains (see figure). This initiative will be executed on dual fronts: at the European level, encompassing approximately 800 cities, and at the local level, involving a focused approach on selected few test cities.

    The analysis allows to identify cities with similar characteristics, assess different climate change impacts across the continent and the influence of different factors on cities adaptation capacity. It can also help identify positive examples and best practices which could inspire other cities. The created information can be provided in a tailor-made format such as short factsheets and visualizations for non-technical users or more specific maps, visualizations and even the underlying data for researchers or data engineers.

  • Biodiversity occurrence cubes

    Partner: Naturhistorisches Museum Wien, Natural History Museum Vienna (NHMW)

    One core concern of biodiversity research pertains to gaining a better understanding of the multitude of factors influencing whether species flourish or wither depending on their local environment. To date, this research was painstaking, with researchers manually gathering data on potentially relevant factors before they can commence their analyses. In this use case, we aim to leverage the diverse resources becoming available in spatiotemporal grids to widen the scope of potential factors that can be correlated with species distribution; these identified correlations must then be vetted by domain experts to identify underpinning causalities before being utilized at a wider scope for predictions. In addition, available point-based occurrence data stemming from both specimens and observations will be transformed to multidimensional gridded formats for integration and analysis with other FAIRiCUBE holdings.

  • UC2: Agriculture and biodiversity nexus

    Partners: Wageningen Environmental Research

    This use case investigates the impact of agriculture activities on biodiversity within the agricultural landscape as the main environment. The main objective is to improve the knowledge about the correlation between biodiversity and different agricultural practices using a machine learning approach which is consistent across different regions. This would provide a step forward in making more precise estimates of e.g. biodiversity in a spatial context, by linking biodiversity with human activities in agricultural areas and related changes in the physical conditions (e.g., soil, groundwater, emissions etc.). Finally, it aims at increasing awareness about data cubes and AI in domain stakeholders involved in the smart agriculture and biodiversity fields. This is particularly interesting for stakeholders such as local policy makers and environmental organisations, to support them in making better-informed decisions such as selecting more nature-inclusive practices promoting biodiversity.

    As the basic conceptual design of the agriculture – biodiversity interaction, this use case uses the Dutch Biodiversity Monitor (DBM)[1], which measures the effect on biodiversity from the impact agricultural activities have on the physical conditions of the environment. One of the major goals of the DBM is to reward farmers for their performance on biodiversity. This can be done by multiple agents such as value chain partners, regional governments and possibly also through payments of the Common Agricultural Policy (CAP).

    In the use case, three main data categories are considered: biodiversity data, environmental data, and agricultural data (Figure 2). Each of these data categories is handled primarily within their individual processing flow where distinctive data cubes are generated. The flows are then ultimately merged using causal machine learning.


    [1]

    https://biodiversiteitsmonitormelkveehouderij.nl/docs/Biodiversiteitsmonitor_engels.pdf
  • UC 4: Urban adaptation to climate change

    Partners: space4environment and Stiftelsen Norsk Institutt for Luftforskning, Norwegian Institute for Air Research

    Buildings are vital to our civilization, providing shelter and protection from the environment. However, they also contribute significantly to energy use (40%) and greenhouse gas emissions (36%). Many existing buildings lack sustainability due to historical construction practices predate sustainability concerns for instance energy efficiency, environmental impacts and material conservation. Despite this, they are expected to remain in use by 2050.

    The EU aims to improve building energy performance to achieve carbon neutrality by 2050 through initiatives like the “Renovation wave” and “Fit for 55”. Yet, the current rate of energy retrofitting is insufficient, exacerbated by challenges such as the Ukraine invasion and COVID-19 pandemic, hindering progress towards EU climate goals.

    To improve energy retrofitting rates, a comprehensive approach is essential, considering both broad city/country strategies and detailed building-level analysis. This involves a bottom-up approach, assessing individual buildings to prioritize renovation efforts effectively. UC4 facilitates this process by evaluating residential building energy performance and determining renovation priorities through multi-objective optimization. In addition, UC 4 uses and evaluates the power of machine learning in birding the gaps in data and finding new model to extract new information from the existing data. Some of these activities are data gap filling, classification, and semantic segmentation that UC 4 is testing.