Search

interTwin Work Package 7 will provide a set of reusable components, called thematic modules, for the digital twins defined in WP4. In this document, we provide a high-level description of the environmental domain use cases and of the designed thematic modules. We also provide a set of common requirements derived from the analysis of the use cases and thematic modules that will need to be available in the Digital Twin Engine (DTE) core, designed in WP6.

The exponential increase in data volumes and complexities is causing a radical change in the scientific discovery process in several domains, including climate science. This affects the different stages of the data lifecycle, thus posing significant data management challenges in terms of data archiving, access, analysis, visualization, and sharing. The data space concept can support scientists' workflow and simplify the process towards a more FAIR use of data.In the context of the European Open Science Cloud (EOSC) initiative launched by the European Commission, the ENES Data Space (EDS) represents a domain-specific implementation of the data space concept. The service, developed in the frame of the EGI-ACE project, aims to provide an open, scalable, cloud-enabled data science environment for climate data analysis on top of the EOSC Compute Platform. It is accessible in the European Open Science Cloud (EOSC) through the EOSC Catalogue and Marketplace (https://marketplace.eosc-portal.eu/services/enes-data-space) and it also provides a web portal (https://enesdataspace.vm.fedcloud.eu) including information, tutorials and training materials on how to get started with its main features. The EDS integrates into a single environment ready-to-use climate datasets, compute resources and tools, all made available through the Jupyter interface, with the aim of supporting the overall scientific data processing workflow. Specifically, the data store linked to the ENES Data Space provides access to a multi-terabyte set of variable-centric collections from large-scale global climate experiments. The data pool consists of a mirrored subset of CMIP (Coupled Model Intercomparison Project) datasets from the ESGF (Earth System Grid Federation) federated data archive, collected and kept synchronized with the remote copies by using the Synda tool developed within the scope of the IS-ENES3 H2020 project. Community-based, open source frameworks (e.g., Ophidia) and libraries from the Python ecosystem provide the capabilities for data access, analysis and visualisation. Results and experiment definitions (i.e., Jupyter Notebooks) can be easily shared among users promoting data sharing and application re-use towards a more Open Science approach. An overview of the data space capabilities along with the key aspects in terms of data management will be presented in this work.

The Earth System Grid Federation (ESGF) is an international collaboration powering most global climate change research and managing the first-ever decentralized repository for handling climate science data, with multiple petabytes of data at dozens of federated sites worldwide. It is recognized as the leading infrastructure for the management and access of large distributed data volumes for climate change research and supports the Coupled Model Intercomparison Project (CMIP) and the Coordinated Regional Climate Downscaling Experiment (CORDEX), whose protocols enable the periodic assessments carried out by the IPCC, the Intergovernmental Panel on Climate Change. As trusted international repository, ESGF hosts and replicates data from a broader range of domains and communities in the Earth sciences leading thus to a strong support to standards for connecting data and application of FAIR data principles to ensure free and open access and interoperability with other similar systems in the Earth Sciences. ESGF includes a specific software component, funded by the H2020 projects IS-ENES2 and IS-ENES3, named ESGF Data Statistics, which takes care of collecting, analyzing, visualizing the data usage metrics and data archive information across the federation. It provides a distributed and scalable software infrastructure responsible for capturing a set of metrics both at single site and federation level. It collects and stores a high volume of heterogeneous metrics, covering coarse and fine grain measures such as downloads and clients statistics, aggregated cross and project-specific download statistics thus offering a more user oriented perspective of the scientific experiments. This allows providing a strong feedback on how much, how frequently and how intensively the whole federation is exploited by the end-users, as well as the most downloaded data, which somehow captures the level of interest from the community on some specific data. It also gives feedback on the less accessed data, which from one side can help designing larger-scale experiments in the future and on the other hand can help getting some insights on the long tail of research. On top of this, a view of the total amount of data published and available through ESGF offers users the possibility to monitor the status of the data archive of the entire federation. This contribution presents an overview of the Data Statistics capabilities as well as the main results in terms of data analysis and visualization.

In the context of the European Open Science Cloud, the ENES Data Space represents a domain-specific implementation of the data space concept, a digital ecosystem supporting scientific communities towards a more sustainable, effective, and FAIR use of data. Such ecosystem has been recently opened to climate users, offering datasets, tools, and services into a single environment with ready-to-use data and programmatic capabilities for the development of data science applications. Presently, the data store of the ENES Data Space provides access to models output from large-scale global experiments for climate model intercomparison. The storage and computational resources for the execution of the data space are provided by the EGI Federated Cloud e-Infrastructure. From a science gateway perspective, the ENES Data Space provides an interactive web-based environment based on the Jupyter project and available through the EOSC MarketPlace.

The intensification of extreme events, storm surges and coastal flooding in a climate change scenario increasingly influences human processes, especially in coastal areas where sea-based activities are concentrated. Predicting sea level near the coasts, with a high accuracy and in a reasonable amount of time, becomes a strategic task. Despite the developments of complex numerical codes for high-resolution ocean modeling, the task of making forecasts in areas at the intersection between land and sea remains challenging. In this respect, the use of machine learning techniques can represent an interesting alternative to be investigated and evaluated by numerical modelers. This article presents the application of the Long-Short Term Memory (LSTM) neural network to the problem of short-term sea level forecasting in the Southern Adriatic Northern Ionian (SANI) domain in the Mediterranean sea. The proposed multi-model architecture based on LSTM networks has been trained to predict mean sea levels three days ahead, for different coastal locations. Predictions were compared with the observation data collected through the tide-gauge devices as well as with the forecasts produced by the Southern Adriatic Northern Ionian Forecasting System (SANIFS) developed at the Euro-Mediterranean Center on Climate Change (CMCC), which provides short-term daily updated forecasts in the Mediterranean basin. Experimental results demonstrate that the multi-model architecture is able to bridge information far in time and to produce predictions with a much higher accuracy than SANIFS forecasts.