• Energy Research

Forest-type classification is a very complex and difficult subject. The complexity increases with urban and peri-urban forests because of the variety of features that exist in remote sensing images. The success of forest management that includes forest preservation depends strongly on the accuracy of forest-type classification. Several classification methods are used to map urban and peri-urban forests and to identify healthy and non-healthy ones. Some of these methods have shown success in the classification of forests where others failed. The successful methods used specific remote sensing data technology, such as hyper-spectral and very high spatial resolution (VHR) images. However, both VHR and hyper-spectral sensors are very expensive, and hyper-spectral sensors are not widely available on satellite platforms, unlike multi-spectral sensors. Moreover, aerial images are limited in use, very expensive, and hard to arrange and manage. To solve the aforementioned problems, an advanced method, self-organizing–deep learning (SO-UNet), was created to classify forests in the urban and peri-urban environment using multi-spectral, multi-temporal, and medium spatial resolution Sentinel-2 images. SO-UNet is a combination of two different machine learning technologies: artificial neural network unsupervised self-organizing maps and deep learning UNet. Many experiments have been conducted, and the results showed that SO-UNet overwhelms UNet significantly. The experiments encompassed different settings for the parameters that control the algorithms.

Italy is the second largest extra-virgin olive oil (EVOO) producer within the European Union. Despite its importance in preserving rural landscape and in supporting household economy, the EVOO sector faces several constraints due to high management costs, small farm size, lack of cooperation and investment, production vulnerability, and farmers’ ageing. Such a number of weak points suggests the need to identify and adopt innovative approaches, at both the farm and oil mill levels. In order to address these priorities, a fuzzy cognitive mapping (FCM) survey was carried out in Umbria region, central Italy, involving key local stakeholders of the EVOO value chain in the Orvieto district. Based on stakeholders’ perception and knowledge, this paper aims to identify and evaluate the most relevant components of the local olive oil value chain, and predict scenarios responding to hypothetical changes of the same components. These stakeholders were firstly invited to each build an individual fuzzy cognitive map and then, grouped all together, build a joint fuzzy cognitive map. Finally, the maps represented both the individual and the grouped stakeholders’ perceptions. The maps were translated into adjacency matrices in order to create an FCM model by applying the software “Mental Modeler”. In total, 24 participants, including practitioners, multipliers, researchers, suppliers and members of local administration, participated in the survey. The component analysis and the scenario analysis highlighted several priority issues: to preserve the ecosystem functioning, to implement cooperation, innovation and education, to adapt and mitigate climate change. The main novelty of this study is that all stakeholders’ categories in the EVOO sector recognize several challenges to sustain the EVOO value chain, in particular, climate change adaptation and mitigation.

We present our first results for the SIDATIM research project. This EU project is designed to assess the potential of a new agroforestry system consisting of timber trees and a promising new energy crop called Sida hermaphrodita. The first part of SIDATIM is devoted to assessing the growth and use of Sida hermaphrodita. Sida is not only suitable for heat and energy production, but can also be used for the production of various materials. In Poland Sida has displayed impressive growth, generating dry biomass yields of more than 20 tons per hectare. Yet, there is little data on Sida growth in other European countries. Here, we present new results on the growth of two different Sida provenances, the competitive potential of their seeds when sown together with seed mixtures of native plants, and adaptation of the species to drought and shade. In the second research pillar of SIDATIM, the research focus lies on the production of valuable timber trees in an agricultural setting - in particular, at the edges of fields or in existing hedgerows. Finally, we investigate in a synthetic approach how these two land utilization concepts can be combined in a modern agroforestry system.

It is recognised that several constraints such as the lack of knowledge and expertise of farmers, land users and policy makers concerning agroforestry systems establishment and management hamper the adoption of agroforestry systems (Camilli et al. 2017). AFINET project acts at EU level in order to direct research results into practice and promote innovative ideas to face challenges and solve practitioners' problems. AFINET proposes an innovative methodology based on the creation of a European Interregional Network, linking different Regional Agroforestry Innovation Networks (RAINs). RAINs represent different climatic, geographical, social and cultural conditions and enclose a balanced representation of the key actors with complementary types of expertise (farmers, policy makers, advisory services, extension services, etc.). The Italian RAIN is focused on the Extra-Virgin Olive Oil (EVOO) value chain, with the main aim to promote agroforestry management of local olive orchards. Olive trees are still managed traditionally, often in marginal sites, with minimal mechanization and relatively low external inputs such as chemical treatments in comparison to other crops. The presence of permanent crops (olive trees) guarantees a partially tree cover reducing hydrogeological risk. Soil management usually keeps natural grassing reducing soil carbon emission and increasing soil fertility (Bateni et al. 2017). Intercropping with cereals and/or fodder legumes and livestock can also be practiced in olive orchards, increasing the complexity of the olive tree multifunctional system. Moreover, olive orchards can be managed as agroforestry systems since they can be intercropped with arable crops (cereals, legumes) and/or combined with livestock (sheep, poultry). The RAIN process, involving local stakeholders, highlighted the main bottlenecks of the EVOO value chain related to communication and dissemination of knowledge, technical and management aspects, market and policy. In order to contrast bottlenecks and exploit opportunities of the olive oil supply chain, the identified innovations are: i) adoption of best practices: testing and experimenting innovative agroforestry systems introducing different crop/animals species and varieties; ii) improve the management of the olive orchards: encouraging and increasing the organic production; iii) valorisation of olive processing residues: identifying and testing innovative products (bio-materials, olive paste as example); iv) arise the awareness among consumers: educating people about the benefits of olive oil consumption, creating networks among stakeholders, improving marketing and commercialization. Creating a Bio-district, defined as a geographical area where farmers, citizens, tourist operators, associations and public authorities enter into an agreement for the sustainable management of local resources, emerged a powerful tool to implement the innovation in the local EVOO value chain.

Rapporto di ricerca sulla seconda missione effettuata con la Fondazione Giovanni Paolo II per lo sviluppo rurale dei produttori di dattero di Jericho (Palestina). Contenuti: - Tecnicheper uso sostenibile delle risorse: suolo, acqua, fertilizzazione - Analisi di gestione per il miglioramento delle aziende agricole - Valorizzazione delle varietà locali

The activity involved several date palm plantations (Phoenix dactylifera L.), as part of the project of John Paul II Foundation. The producers visited are moving in a very difficult socio-political and environmental context but they seem generally willing to communicate the problems and strengths of the agro-ecosystem of interest, despite a tendency to practice in the management and resolution of cultural problems. and market. However, it was possible to obtain valuable information and dialogue from local operators. This was essential to be able to propose and discuss possible solutions to the critical issues evaded in inspections and to set in motion at least locally a series of virtuous measures aimed at increasing socio-ecological resilience.

All'interno della collaborazione con la Fondazione Giovanni Paolo II, gli autori hanno realizzato dei questionari socio-ecologici, in grado di evidenziare le caratteristiche qualitative e quantitative di natura agroa-mbientale e socio-economica. I dati raccolti sono stati sottoposti ad analisi statistica (ANOVA, PCA e regressioni lineari) e discussi in base alle caratteristiche emerse dalle interviste in loco che accompagnavano la somministrazione dei questionari.

The value chain of sweet cherry in Lebanon is affected by several constraints with a negative influence on local economy and socioecology. Main aim was to analyse relevant phases of the value chain, possibly suggesting solutions towards a Quality Management System. We especially focused on agricultural practices and socioeconomic characteristics of different farming systems. Stable isotope compositions (?13C and ?15N) were analysed on leaf and soil samples from different farms, in order to get ecophysiological insights on water-use efficiency and nitrogen plant dynamics. Agronomic and socioeconomic data were acquired by subministrating surveys to selected pools of farmers. Soils rich in organic matters are fertile and support efficient resources use and plant productivity. Some Lebanese areas showed a higher socioeconomic sus-tainability. This was associated with a higher socioecological resilience, especially in terms of reduced farming costs, sustainable use of environmental resources and increased local capacity building.