• Rural Digital Europe
• Research dataclose
• Other research productsclose
• IT close
• Rural Digital Europe close

NOTE: We discovered some errors in the data for images after February 2019. They will be fixed in version >= 1.1.x, until then, usage of the data after Feb 2019 is not advised. The rest of the data is fine. This is the data to the same-titled Data paper, which can be found at https://doi.org/10.3390/data5010001. Along with auxilary files for the cloudremoval package, and example scripts on how to access chunks of the data. The files contain: python-cloudremoval-aux-data.tar.gz : auxilary data (altitude, aspect, ...) to run the cloudremoval module which can be found at https://gitlab.inf.unibz.it/earth_observation_public/modis_snow_cloud_removal python-example-data-access.html : Example script how to access parts of the data using python R-example-data-access.html : Example script how to access parts of the data using R zenodo_01_original.tar.gz : time series of snow cover maps, developed at the Institute for Earth Observation, Eurac Research, Bolzano, Italy. More information in same-title Data paper (https://doi.org/10.3390/data5010001), and for algorithm at https://doi.org/10.3390/rs5010110. zenodo_02_cloudremoval.tar.gz : time series of cloud filtered maps, based on 2. above, using code mentioned in 1. More information in same-titled Data paper. The maps are GeoTIFF with integer based values: 0 = no data; 1 = snow; 2 = land; 3 = cloud; 4&5 = water bodies / nodata Version history: 1.0.0 : initial upload 1.0.1 : changes after revision of Data paper 1.0.2 : added example scripts

In its 2011 White Paper the Commission set the objective of shifting 30% of road freight over 300 km to other modes, such as rail or waterborne transport, by 2030. By 2050 the share is to be increased to 50%. In addition to supporting these decarbonisation objectives, a shift from road to rail offers to ease congestion on roads, lower the pressure on road infrastructures by taking over the heaviest loads and by reducing the risks linked to transporting dangerous goods. Yet, the progress achieved to date in the Member States remains insufficient, as the share of rail freight stagnates at around 18%. To ensure that rail freight takes off, its performance needs to improve drastically in terms of quality and efficiency. The sector and the legislators need to think fresh and bold and to consider holistically what can be done to overcome this stagnation.

Spraying in agriculture represents a societal challenge due to its negative impact in human and animal health and in environment. Increasing spraying efficiency towards the objective of "right time, right amount, right place", involves reduction of losses and, consequently, amount of phytopharmaceuticals used, water usage, and human and animal exposure to pesticides, and the increase of the spraying system availability while reducing labour costs. Furthermore, adoption of new ecological spraying treatments to increase both yield and treatment efficiency is desirable. Agriculture in rough terrain is also challenging, due to the steepness of some terrain, lack of space to manoeuvre, difficulties of communications due to natural obstacles and harsh atmospheric conditions associated. To cope with these challenges a consortium with complementary precision farming actors was formed for Slopebot project, bringing together steep slope vineyards associations (CERVIM and ADVID), robotics and agricultural machinery RTD institutions (INESC TEC, DFKI, and CNR - IMAMOTER), agrofood and vineyard RTD institutions (ceiA3 and IFV), robotics and agricultural machinery SMEs (TEKEVER-AS, IKNOWHOW, V.M.A., and KommTek Intelligente Lösungen), and an institution devoted to innovation in the sector (INOVISA). Slopebot's solution will be a safe and autonomous precision spraying tool integrated into a modular unmanned tractor (robotics platform). It will focus on steep slope vineyards but also looking for the applicability in other high-value permanent crops in rough terrain. Slopebot will bring the TRL of the technologies involved from 3 to 5. This increment is driven by five main RTD topics: localization and navigation system; advanced sprayer tool with Variable Rate Technology (VRT); safety systems; compliance and interoperability; and modularity. Slopebot will contribute to build up its market segment aligned to the European Strategic Robotics Agenda and create new business opportunities.

Le catene di processamento Sentinel-2 costituiscono l'elemento di back end per la generazione dei prodotti relativi allo stato delle colture agricole, derivati da telerilevamento satellitare (Missione ESA Sentinel 2), visualizzabili dagli utenti del progetto mediante apposita interfaccia web (https://telemod.get-it.it). L'algoritmo R, parzialmente derivato dalla libreria R sen2r (https://github.com/ranghetti/sen2r), ha la funzione di cercare i dati Sentinel-2 disponibili su ESA SciHub, scaricarli, processarli nel formato di output, calcolare gli indici spettrali a partire dai dati di riflettanza e generare da essi i prodotti informativi sullo stato della variabilità intra-appezzamento. L'esecuzione automatizzata dell'algoritmo consente di mantenere aggiornato l'archivio dei prodotti senza la necessità di intervento manuale.

Digital connectivity – loosely defined as connecting people through digital means promises to enhance our quality of life, as envisaged in Japan’s ‘Society 5.0’, which aims to spur economic growth and solve social problems digitally. On the other hand, digital connectivity also creates challenges and demands a quest for optimum equilibrium between economic growth and national as well as human security. The COVID-19 pandemic which erupted in late 2019 has accelerated world dependence on digital connectivity in order to sustain human contact. Digital means have allowed us to continue our lives, work and pleasure connections, and have simultaneously expanded digital risks at home and globally. The COVID-19 scenario has also demonstrated how digital technology can even threaten our sovereignty and basic values such as freedom, democracy, privacy, human rights and dignity. Japan and the EU approach the digital age with a common emphasis on leading standards to set and promote a human-centred digital connectivity. The two zones can cooperate bilaterally and beyond in responding to challenges on digital connectivity, as is stipulated in three key documents, namely Japan-EU Economic Partnership Agreement (EPA), Japan-EU Strategic Partnership Agreement (SPA) and Japan-EU Partnership

isapiens@home is a three layer platform composed by a Cloud layer, a Middle layer and a Physical layer designed to address issues related to Cyber-Physical Systems (CPS) and Internet of Things (IoT). isapiens@home hides heterogeneity by providing a Virtual Object concept, and addresses the distributed nature of CPS/IoT applications by introducing a distributed multi-agent system on top of the physical part. isapiens@home aims to get the computation close to the sources of information (i.e., the physical devices), thus decreasing the need for remote communications. Furthermore, it addresses the dynamic adaptivity requirements of CPS fostering the use of Swarm Intelligence algorithms. isapiens@home also exploits the Cloud to carry out high computational tasks when needed.

FP6-2004-IST-4 MATHESIS 027574 The overall objective of the MATHESIS project is to explore fundamental aspects of social communication and adaptive behaviour, namely the process of assigning meaning to the actions of other subjects. This will be demonstrated by developing artificial cognitive agents able to acquire a motor repertory by observational learning. Observational learning is understood here as the capacity to acquire an action strategy through observation only, without the experimentation needed in learning procedures, which mostly use trial-and-error (e.g., reinforcement learning).

Recent breakthroughs in the development of Artificial Intelligence (AI) have initiated heated debates regarding its governance. As of today, the success of AI relies on machine learning – the ability of algorithms to learn from, and find patterns in, large amounts of data. Consequently, governance of AI will in practice mean policies regarding both the design and access to algorithms, as well as collection and usage of information. Regarding the latter, the European Union (EU) has put in place a comprehensive normative framework: the General Data Protection Regulation (GDPR)1, applicable since 25 May 2018. Based on the discussion that took place during the School of Transnational Governance’s High-Level Policy Dialogue on 26 June 2018, we present three actionable recommendations for global and local policymakers coming to grasp with the questions of AI Governance