Alessandro D'ANca

An accurate spatial distribution of forest species composition is essential for biodiversity monitoring, management and protection. Combining this information with field structural metrics (e.g., basal area, species co-occurrences, canopy height) significantly improves our ability to estimate ecosystem functions and understand their relationship with biodiversity. These insights are crucial for regional biodiversity assessments, territorial planning, and forest management, contributing directly to nature conservation. A geospatial approach is particularly valuable when studying forest biodiversity dynamics, as it allows for the analysis of species composition and interactions within a community-based framework.Recent advancements in high spatial resolution remote sensing have shown the effectiveness of machine learning algorithms, with rapid progress driven by developments in artificial intelligence. The integration of remote sensing data with AI-based methods has proven useful. In our study, we leverage Earth Observation (EO) data derived from Sentinel-2 satellite imagery, including maximum, minimum, median, and near-extremes percentiles of the NDVI and its standard deviation as a key index of forest canopy, density, health and irregularity. We also incorporate Sentinel-2 canopy height derived data, which is essential for understanding forest structure and vertical stratification. These combined metrics provide a comprehensive understanding of vegetation phenology and heterogeneity, supporting more accurate assessments of forest composition and structure.Field data for this study are derived from forest inventory datasets, serving as the foundation for calibrating and validating the models, enabling precise estimations of species composition, basal area, and other structural parameters critical to biodiversity monitoring.Mechanistic species distribution models (SDMs) and community assembly (JSDMs) models have driven substantial advancements in biodiversity research, offering insights into environmental filtering and competitive dynamics within ecosystems. In this study, we present a hybrid geospatial approach that combines SDM — specifically, Hierarchical Modeling of Species Communities — with AI algorithms to map forest species composition, relative abundance, and basal area across Italy. This approach is crucial for applications in biodiversity conservation and forest management, enabling more informed decision-making for land and forest management.Our hybrid framework integrates EO-derived features from Sentinel-2 (e.g., canopy height, NDVI metrics) with pedological and bioclimatic variables, functional traits, Community Weighted Means, Functional Dispersion Index, and phylogenetic distances. By modeling these variables, we aim to capture the complex interrelations between forest species and their environment. To further enhance interpretability, we employ a Machine Learning algorithm based on association rule learning,The integration of remote sensing data and AI methodologies, combined with field inventory datasets, can provide a powerful tool for biodiversity research and forest management. The incorporation of field data ensures the accurate calibration and validation of models, improving the reliability of predictions. This geospatial approach, leveraging Sentinel-2 EO data, not only advances our capacity to monitor species distributions but also contributes to understanding forest ecosystem dynamics in the context of nature conservation. By bridging remote sensing, AI, and field data, we offer a comprehensive framework to address the multifaceted challenges in biodiversity, ecosystem services, and sustainable land management.

Rainfall-induced soil erosion is recognized as a significant threat to both human and ecosystem health, leading to habitat degradation, food insecurity, disruptions to socio-economic activities, and damage to infrastructure. Addressing and mitigating soil erosion has become a priority in global and national strategies, therefore requiring multitemporal large-scale assessments to understand how precipitation patterns, soil properties, and surface conditions interact and contribute to erosion in specific areas and over time. In these assessments, the land cover and management, and natural vegetation dynamics components play a critical role in reducing soil susceptibility to erosion. These components are represented by a specific parameter (C-factor) in the Universal Soil Loss Equation (USLE) and its updated versions. While numerous methods exist for determining the C-factor (e.g., in situ survey, remote sensing observation, data-driven models), these approaches are diverse and often have limitations, from neglecting phenological sub-annual dynamics to long timeliness, low update frequency, and coarse spatial resolution, among others. As a result, making their selection for specific purposes is challenging. In this talk, we will present a comprehensive review of existing methodologies to assess C-factor by examining their development, strengths, and drawbacks. We will provide practical examples from selected case studies across Europe to show methods’ applicability, allow cross-comparison, and guide their choice. Finally, we will explore emerging methodologies leveraging Earth Observation and Artificial Intelligence and the advances in neural networks trained on ESA Sentinel-2 data within the framework of two European-funded projects (i.e., SDGs-EYES and EO4EU).

The Urgent Tsunami Computing procedures discussed herein are designed to quantify potential hazards resulting from seismically-induced tsunamis following an earthquake, with a temporal scope ranging from minutes to a few hours. The presented workflow employs comprehensive simulations, encompassing the entire tsunami propagation process, while accounting for uncertainties associated with source parameters, tsunamigenesis and wave propagation dynamics. Within the EuroHPC eFlows4HPC project, we present a High-Performance Computing (HPC) workflow tailored for urgent tsunami computation in which the Probabilistic Tsunami Forecast (PTF) code has been restructured and adapted for seamless integration into a PyCOMPSs framework. This framework enables parallel execution of tasks and includes simulations from Tsunami-HySEA numerical model within a unified computational environment. Of particular significance is the workflow's capability to incorporate new datasets, such as focal mechanism data, seismic records, or real-time tsunami observations. This functionality facilitates an "on-the-fly" update of the PTF, ensuring that the forecasting model remains responsive to the latest information. The development of this workflow involves a systematic exploration of diverse scenarios, realistic simulations, and the assimilation of incoming data. The overarching goal is to rigorously diminish uncertainties, thereby producing updated probabilistic forecasts without compromising precision and enhancing risk mitigation efforts far from the seismic source. Improved risk management, achieved by informing decision-making in emergency situations, underscores the importance of this development. We will showcase the technical advancements undertaken to tailor the workflow for HPC environments, spanning from the developers' perspective to that of the end user. Additionally, we will highlight the scientific enhancements implemented to leverage the full potential of HPC capabilities, aiming to significantly reduce result delivery times while concurrently enhancing the accuracy and precision of our forecasts.

The advances in Earth System Models (ESM), jointly with the availability of more powerful computing infrastructures and novel solutions for Big Data and Machine Learning (ML) is allowing to push research in the climate change field forward. In such context, workflows are fundamental tools to automate the complex processes of model simulations, data preparation and analyses. Such tools are becoming more important as the complexity and heterogeneity in the software and computing infrastructures, as well as the data volumes to be handled, grow. However, integrating into a single workflow simulation and data centric processes can be very challenging due to their different requirements.This work presents an end-to-end workflow including the steps from the numerical ESM simulation run to the analysis of extreme weather events (e.g., heat waves and tropical cyclones) developed in the context of the eFlows4HPC EuroHPC project. It represents a real case study which requires components from High Performance Computing (HPC), Big Data and ML to carry out the workflow. In particular, the contribution demonstrates how the eFlows4HPC software stack can simplify the development, deployment, orchestration and execution of complex end-to-end workflows for climate science, as well as improve their portability over different computing infrastructures.

The Italian territory is located at the heart of one of the global hot spots of climate change, where the implementation of climate‐smart land management practices is imperative to guarantee the present and future maintenance of ecosystem functions as well as the sustainability of human socioeconomic activities. The project HIGHLANDER (HIGH performance computing to support smart LAND sERvices) led by Cineca aims at building a comprehensive and multi‐sector framework for land‐management decision‐making in Italy. The project relies on high quality information on different components of the landscape, with a focus on climate‐driven processes, and state‐of‐the‐art computing infrastructures. The HIGHLANDER Data Portal maximizes the impact of HIGHLANDER results by providing access to data products and services. In this article, we describe the architectural features of the platform, as well as the available HIGHLANDER datasets and downstream applications.

Current scientific workflow systems do not typically integrate simulation-centric and data-centric aspects due to their very different software/infrastructure requirements. A transparent integration of such components into a single end-to-end workflow would lead to a more efficient and automated way for generating insights from large simulation data. This work presents a complex case study related to extreme events analysis of future climate data that integrates in the same workflow numerical simulations, Big Data analytics and Machine Learning models. The case study is being implemented in the context of the eFlows4HPC project using the project’s software stack for deployment and orchestration of the workflow. The solution implemented in the project has shown to simplify the development and execution of end-to-end climate workflows with heterogeneous software requirements. Moreover, such an approach can, in the long term, increase the reuse of workflows by scientists and their portability over different HPC infrastructures.

Preventing and fighting wildfires in the forests and rural areas of Epirus and Apulia has become increasingly demanding due to climate change and socioeconomic factors, i

The scientific discovery process has been deeply influenced by the data deluge started at the beginning of this century. This has caused a profound transformation in several scientific domains which are now moving towards much more collaborative processes. In the climate sciences domain, the ENES Data Space aims to provide an open, scalable, cloud-enabled data science environment for climate data analysis. It represents a collaborative research environment, deployed on top of the EGI federated cloud infrastructure, specifically designed to address the needs of the ENES community. The service, developed in the context of the EGI-ACE project, provides ready-to-use compute resources and datasets, as well as a rich ecosystem of open source Python modules and community-based tools (e.g., CDO, Ophidia, Xarray, Cartopy, etc.), all made available through the user-friendly Jupyter interface. In particular, the ENES Data Space provides access to a multi-terabyte set of specific variable-centric collections from large community experiments to support researchers in climate model data analysis experiments. The data pool of the ENES Data Space consists of a mirrored subset of CMIP datasets from the ESGF federated data archive collected by using the Synda community tool in order to provide the most up to date datasets into a single location. Results and output products as well as experiment definitions (in the form of Jupyter Notebooks) can be easily shared among users through data sharing services, which are also being integrated in the infrastructure, such as EGI DataHub.The service was opened in the second part of 2021 and is now accessible in the European Open Science Cloud (EOSC) through the EOSC Portal Marketplace (https://marketplace.eosc-portal.eu/services/enes-data-space). This contribution will present an overview of the ENES Data Space service and its main features.