Use cases-old

Partners: space4environment

Use case objective  

Climate change poses several challenges to cities, such as droughts, urban heat waves, changing precipitation patterns, floods and (peri-)urban biodiversity loss. These impacts are interrelated with factors like land use activities around cities and the socio-economic setting. Datasets on these factors are available, but they are complex to integrate and analyze due to their heterogeneity, format and quality. The goal of UC1 is to harmonize the diverse datasets into structured data cubes and provide a comprehensive “toolkit” for their analysis.

Potential applications    

The data analysis toolkit should support European institutions, local policy makers and scientists to make well-informed decisions when addressing climate change’s multifaceted impacts.   

One European data cube collects indicators from different domains for many cities. It can be used to identify cities with similar characteristics, assess climate change impacts across the continent and the influence of different factors on cities adaptation capacity. 

On the local scale, we work closely with city municipalities to create city cubes and define specific goals. For example, study the effects of various environmental variables on perceived temperature. Where possible, solutions developed for one city will be scaled to other cities. 

The data cubes   

The European data cube contains data from the climate, land and socio-economic domains. Clustering analysis has been employed to discover cities that are similar with respect to the impact of climate change and their adaptation strategies.  

The data set was published in Zenodo: https://doi.org/10.5281/zenodo.11034578. 

To understand the effect of covariates on perceived temperature, the first step is to have an accurate measure. We aim at achieving it by integrating in the city cube weather station data. Where no station is available, the values will be predicted based on land surface temperature, DEM and other variables.  

Workflow   

The figure below shows the workflow we will follow. We will perform a cluster analysis of EU cities using data from the climate, land cover/land use and socio-economic domains (figure 1). 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.

Partners: Wageningen Environmental Research

Objective

The main aim of Use Case 2 is to investigate the impact of agricultural activities on the environment (e.g., soil, groundwater, emissions etc.) and further on biodiversity. Within the use case customized machine learning tools are utilized within data cube-based infrastructure. The expected results are established workflows and data pipelines including a prototype of a model that predicts causal relations between changes in farmland bird biodiversity and specific agricultural practices in the Netherlands.

Applications

The established model can be used by decision makers in agriculture and environmental protection by supporting better-informed decisions such as selecting more nature-inclusive practices promoting biodiversity through specific applications:

• Spatial categorization: The results of the observation and estimation steps for biodiversity can be used to categorize agricultural landscapes and e.g. administrative regions, based on predicted suitability.
• Casual modeling: Causal modelling allows reasoning about potential situations to answer ‘What-if?” type of questions and creating scenarios for farmland landscape development considering biodiversity favorable conditions.
• Smart tools: The presented approach aims at improved understanding of causalities between farm activities and changes in biodiversity. When results are sufficiently robust, the model could be incorporated into advisory tools for farmers or policy makers, to help assess the consequences of actions.

Approach

Three main data categories (biodiversity, environment and agriculture) are handled primarily within their individual processing flows and data cubes, which are then ultimately merged using causal machine learning. Modelling methods such as causal inference and discovery provide insights into the underlying mechanisms describing the impact of agricultural practices on biodiversity. They do not only statistically predict the correlations but also provide meaningful explanations for those predictions, enhancing the overall interpretability of the model results.

All the tools are expected to be provided within FAIRiCUBE hub as shared data infrastructure and documented[1][2].

---

[1] https://github.com/FAIRiCUBE

[2] https://fairicube.readthedocs.io/en/latest/

---

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

Objectives

The objective of Use Case 3 is to integrate genomic data of the fruit fly Drosophila melanogaster, which is one of the best-studied model organisms and a world-wide human commensal, with comprehensive environmental and climate information. This interdisciplinary approach aims to identify how environmental factors shape genetic variation and influence evolutionary processes. Taking benefit from already available and newly generated genomic datasets from European and North American populations, the study has two major goals:

I. To assess the influence of geography, environment and climate on genetic variation on natural fly populations on a continent-wide scale. By correlating population genomics with environmental data, the study aims to uncover genetic targets affected by environmental selection pressures.

II. To address the impact of urbanization on genetic variation and adaptation considering factors such as soil sealing, pollution, and habitat fragmentation. Understanding how urban environments affect species survival and adaptation is crucial amidst ongoing biodiversity loss and climate change.

Possible future applications

Overall, Use Case 3 aims to advance our understanding of the relationship between genetic variation, environmental factors, and evolutionary processes. By integrating diverse datasets and employing innovative analytical techniques, the study seeks to shed light on the mechanisms driving adaptation in D. melanogaster populations, with broader implications for biodiversity conservation and pest management strategies in the face of global environmental changes.

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.

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

Use Case objective    

UC4 addresses the pressing need to evaluate and map the potential for energy retrofitting and circularity in residential buildings to align with the European Union’s ambitious climate goals.  

Currently, buildings are major contributors to both energy demand and greenhouse gas emissions. More sustainable practices in construction hold promise for reducing environmental impact, enhancing resilience, and averting raw material price hikes.  

However, a significant challenge lies in the scarcity and fragmentation of data on building materials and properties. This gap impedes informed decision-making on investments and the promotion of circular and local materials. 

Possible applications    

UC4 aims to bridge this divide by developing an agile model which enables the assessment of in-situ materials, energy performance, and emissions of residential building stocks. The model will allow to estimate optimal renovation rates and evaluate the climate neutrality potentials in four European cities: Barcelona, Luxembourg City, Oslo, and Vienna.  These assessments may also be adapted for optimization work, considering local constraints such as fiscal and climate budgets, as well as the decarbonization of energy sources. 

Researchers, analysts, city planners, and sustainability consultants may find the developed model useful. In addition, the developed model is crucial for the EU Green Deal to achieve energy efficiency, reduce emissions, and promote sustainable construction. 

Data used  

Diverse data sources will be used, including airborne surveys and ground-based repositories. Tabular data will complement missing information, facilitating comprehensive decision-making regarding energy renovation and circularity initiatives. The use case will visualize its findings using the FAIRiCUBE hub, ensuring accessibility and usability for a wide range of stakeholders. 

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

Research problem 

Systems of habitat classification are an important tool in nature conservation. Usually, they classify habitats based on an artificial classification system which can be also paired with vegetation units occurring. However, these methods ignore taxa occurrences and environmental factors for the classification.  

Use Case objective 

Use Case 5 aims to enhance the conventional method used in habitat classification by using machine learning to identify environmental factors influencing vegetation communities and their presence in the habitats. The final goal of the use case is to implement a method that could improve the current classification system of the European Habitats. 

Workflow 

Habitats are selected from the European Nature Information System (EUNIS). The relative diagnostic taxa are used to retrieve the occurrence data from the Global Biodiversity Information Facility (GBIF). These data are first validated and checked for quality and then ingested as Occurrence Cubes.  

Environmental data are chosen based on their relevance on the occurrence of taxa and obtained from satellite data through EOX services. These are then combined with the occurrence data to produce Extended Occurrence Cubes which will be used in the Machine Learning approaches.  

In the machine Learning steps we use the Bootstrap aggregating strategy to predict the occurrence of taxa based on occurrence and environmental data. Lastly, we compare the predictions of diagnostic taxa of chosen habitats with the raster of EUNIS habitat types to check of overlaps and discrepancies.  

Our method will allow us to investigate communities distribution along environmental gradients and to determine locations with favorable environmental conditions and taxa associations in more realistic habitat types.