Search

We present Plato, a novel semantic data cube system leveraging Ontology-Based Data Access technologies. The concept of semantic data cubes, pioneered by Augustin et al., offers a novel approach to managing Earth Observation data, intertwining symbolic high-level concepts with raw numerical values. While data cube infrastructures have gained prominence, Plato stands out by bridging the gap between ontology-driven semantics and multidimensional data storage, enabling users to glean insights from data in a more intuitive and integrated manner. By employing Ontology-Based Data Access methodologies, Plato establishes connections between ontologies capturing geospatial knowledge and underlying data sources, facilitating seamless querying and interpretation. In this paper we describe the software architecture of Plato, we discuss its applications in the context of the DeepCube project and we evaluate its performance with real data from these applications.

Abstract Climate change exacerbates the occurence of extreme droughts and heatwaves, increasing the frequency and intensity of large wildfires across the globe. Forecasting wildfire danger and uncovering the drivers behind fire events become central for understanding relevant climate‐land surface feedback and aiding wildfire management. In this work, we leverage Deep Learning (DL) to predict the next day's wildfire danger in a fire‐prone part of the Eastern Mediterranean and explainable Artificial Intelligence (xAI) to diagnose model attributions. We implement DL models that capture the temporal and spatio‐temporal context, generalize well for extreme wildfires, and demonstrate improved performance over the traditional Fire Weather Index. Leveraging xAI, we identify the substantial contribution of wetness‐related variables and unveil the temporal focus of the models. The variability of the contribution of the input variables across wildfire events hints into different wildfire mechanisms. The presented methodology paves the way to more robust, accurate, and trustworthy data‐driven anticipation of wildfires.