Alessia Portaccio
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Alessia Portaccio has a total of 40 co-authors. Here are the top co-authors by number of shared publications:
- Thomas Campagnaro
Department of Land, Environment, Agriculture and Forestry (TESAF), Università degli Studi di Padova, Legnaro, Italy
2 shared publications - Tommaso Sitzia
Department Land, Environment, Agriculture and Forestry Università degli Studi di Padova Legnaro Italy
2 shared publications Alberto Testolin
1 shared publication- Alberto Testolin
University of Padova
1 shared publication Aleš Poljanec
1 shared publicationAndrea Favaretto
1 shared publication
Latest Publications
- Open Access
- 30 July 2026
- Published by Elsevier in SSRN Electronic Journal
ECO-AID: Bridging Ecoacoustics, Artificial Intelligence, and Satellite Networks to Monitor Biodiversity in Remote Areas
Biodiversity conservation in remote areas is hindered by a lack of scalable, real-time monitoring infrastructure. Indeed, existing ecoacoustic approaches are typically constrained by the need for extensive human supervision to process large datasets of recordings, which need to be gathered from remote areas. To address these challenges, this paper introduces ECO-AID, an integrated monitoring framework that bridges ecoacoustics, artificial intelligence, and non-terrestrial networks. The ECO-AID framework leverages deep learning for automated, edge-based detection of target animal species and exploits Low Earth Orbit (LEO) satellite constellations to facilitate data transmission and processing in regions lacking terrestrial telecommunication infrastructure. Our methodological approach integrates standardized field recording protocols with expert-annotated datasets to fine-tune deep learning models on regional species, and exploits a hierarchical system architecture where LEO satellites act as both communication backbones and distributed edge-computing nodes, allowing for rapid, energy-efficient event detection and data management. Validation on field recordings demonstrates that fine-tuned deep learning models can accurately detect a wide range of bird vocalizations, while simulation-based evaluations demonstrate that satellite-edge processing effectively balances computational load and power consumption, extending the operational lifetime of battery-powered sensing nodes. Further experimental validation, using Starlink connectivity as a case study, confirms the feasibility of the proposed framework in challenging environmental conditions. By coupling systematic data collection with advanced AI-driven processing and satellite-enabled communication, ECO-AID therefore provides a modular, scalable solution for biodiversity monitoring. This integrated approach enhances the responsiveness of conservation strategies, offering a robust tool for informed management in remote ecosystems.
- 30 July 2026
- Published by Elsevier in SSRN Electronic Journal
Open AccessECO-AID: Bridging Ecoacoustics, Artificial Intelligence, and Satellite Networks to Monitor Biodiversity in Remote Areas
Biodiversity conservation in remote areas is hindered by a lack of scalable, real-time monitoring infrastructure. Indeed, existing ecoacoustic approaches are typically constrained by the need for extensive human supervision to process large datasets of recordings, which need to be gathered from remote areas. To address these challenges, this paper introduces ECO-AID, an integrated monitoring framework that bridges ecoacoustics, artificial intelligence, and non-terrestrial networks. The ECO-AID framework leverages deep learning for automated, edge-based detection of target animal species and exploits Low Earth Orbit (LEO) satellite constellations to facilitate data transmission and processing in regions lacking terrestrial telecommunication infrastructure. Our methodological approach integrates standardized field recording protocols with expert-annotated datasets to fine-tune deep learning models on regional species, and exploits a hierarchical system architecture where LEO satellites act as both communication backbones and distributed edge-computing nodes, allowing for rapid, energy-efficient event detection and data management. Validation on field recordings demonstrates that fine-tuned deep learning models can accurately detect a wide range of bird vocalizations, while simulation-based evaluations demonstrate that satellite-edge processing effectively balances computational load and power consumption, extending the operational lifetime of battery-powered sensing nodes. Further experimental validation, using Starlink connectivity as a case study, confirms the feasibility of the proposed framework in challenging environmental conditions. By coupling systematic data collection with advanced AI-driven processing and satellite-enabled communication, ECO-AID therefore provides a modular, scalable solution for biodiversity monitoring. This integrated approach enhances the responsiveness of conservation strategies, offering a robust tool for informed management in remote ecosystems.
- Open Access
- 28 February 2026
- Published by Italian Society of Sivilculture and Forest Ecology (SISEF) in iForest - Biogeosciences and Forestry
- Vol. 19 (1) , 18-27
Bird response to forest structure and composition and implications for sustainable mountain forest management
Assessing how bird richness across ecological guilds of mountain-breeding birds responds to changes in forest attributes may inform the development of sustainable management strategies. In this study, we surveyed forest structure and bird communities across 148 sampling units in France and Italy to identify threshold values for stand variables that influence bird species richness. The sampling covered an altitudinal range from 805 to 1555 m a.s.l. and was mainly dominated by mountain beech and Alpine coniferous forests. We modelled species richness of overall bird communities and individual ecological guilds in response to structural and compositional attributes and topographic variables using generalized modelling. Bird species richness was negatively associated with stand-level total tree density. However, higher silver fir density was associated with greater species richness across most bird guilds, which preferred mixed woods and heterogeneous stand structure. An increase in deadwood volume had a significant positive effect on all guilds, confirming the importance of old-growth forest features for forest birds. Threshold values indicating a shift in species richness of bird guilds were identified only for some stand structural attributes (i.e., total basal area and deadwood volume). Our results suggest that the conservation of biodiversity in forest bird communities may benefit from management strategies that maintain mixed, relatively open canopies and promote deadwood retention to ensure the availability of associated habitats. Our approach lays the groundwork for further research, applying this methodology to additional variables and biodiversity metrics.
- 28 February 2026
- Published by Italian Society of Sivilculture and Forest Ecology (SISEF) in iForest - Biogeosciences and Forestry
- Vol. 19 (1) , 18-27
Open AccessBird response to forest structure and composition and implications for sustainable mountain forest management
Assessing how bird richness across ecological guilds of mountain-breeding birds responds to changes in forest attributes may inform the development of sustainable management strategies. In this study, we surveyed forest structure and bird communities across 148 sampling units in France and Italy to identify threshold values for stand variables that influence bird species richness. The sampling covered an altitudinal range from 805 to 1555 m a.s.l. and was mainly dominated by mountain beech and Alpine coniferous forests. We modelled species richness of overall bird communities and individual ecological guilds in response to structural and compositional attributes and topographic variables using generalized modelling. Bird species richness was negatively associated with stand-level total tree density. However, higher silver fir density was associated with greater species richness across most bird guilds, which preferred mixed woods and heterogeneous stand structure. An increase in deadwood volume had a significant positive effect on all guilds, confirming the importance of old-growth forest features for forest birds. Threshold values indicating a shift in species richness of bird guilds were identified only for some stand structural attributes (i.e., total basal area and deadwood volume). Our results suggest that the conservation of biodiversity in forest bird communities may benefit from management strategies that maintain mixed, relatively open canopies and promote deadwood retention to ensure the availability of associated habitats. Our approach lays the groundwork for further research, applying this methodology to additional variables and biodiversity metrics.
- Open Access
Linking Acoustic Indices to Vegetation and Microclimate in a Historical Urban Garden: Setting the Stage for a Restorative Soundscape
Urban soundscapes are increasingly recognized as fundamental for both ecological integrity and human well-being, yet the complex interplay between the vegetation structure, seasonal dynamics, and microclimatic factors in shaping these soundscapes remains poorly understood. This study tests the hypothesis that vegetation structure and seasonally driven biological activity mediate the balance and the quality of the urban acoustic environment. We investigated seasonal and spatial variations in five acoustic indices (NDSI, ACI, AEI, ADI, and BI) within a historical urban garden in Castelfranco Veneto, Italy. Using linear mixed-effects models, we analyzed the effects of season, microclimatic variables, and vegetation characteristics on soundscape composition. Non-parametric tests were used to assess spatial differences in vegetation metrics. Results revealed strong seasonal patterns, with spring showing increased NDSI (+0.17), ADI (+0.22), and BI (+1.15) values relative to winter, likely reflecting bird breeding phenology and enhanced biological productivity. Among microclimatic predictors, temperature (p < 0.001), humidity (p = 0.014), and solar radiation (p = 0.002) showed significant relationships with acoustic indices, confirming their influence on both animal behaviour and sound propagation. Spatial analyses showed significant differences in acoustic patterns across points (Kruskal–Wallis p < 0.01), with vegetation metrics such as tree density and evergreen proportion correlating with elevated biophonic activity. Although the canopy height model did not emerge as a significant predictor in the models, the observed spatial heterogeneity supports the role of vegetation in shaping urban sound environments. By integrating ecoacoustic indices, LiDAR-derived vegetation data, and microclimatic parameters, this study offers novel insights into how vegetational components should be considered to manage urban green areas to support biodiversity and foster acoustically restorative environments, advancing the evidence base for sound-informed urban planning.
Open AccessLinking Acoustic Indices to Vegetation and Microclimate in a Historical Urban Garden: Setting the Stage for a Restorative Soundscape
Urban soundscapes are increasingly recognized as fundamental for both ecological integrity and human well-being, yet the complex interplay between the vegetation structure, seasonal dynamics, and microclimatic factors in shaping these soundscapes remains poorly understood. This study tests the hypothesis that vegetation structure and seasonally driven biological activity mediate the balance and the quality of the urban acoustic environment. We investigated seasonal and spatial variations in five acoustic indices (NDSI, ACI, AEI, ADI, and BI) within a historical urban garden in Castelfranco Veneto, Italy. Using linear mixed-effects models, we analyzed the effects of season, microclimatic variables, and vegetation characteristics on soundscape composition. Non-parametric tests were used to assess spatial differences in vegetation metrics. Results revealed strong seasonal patterns, with spring showing increased NDSI (+0.17), ADI (+0.22), and BI (+1.15) values relative to winter, likely reflecting bird breeding phenology and enhanced biological productivity. Among microclimatic predictors, temperature (p < 0.001), humidity (p = 0.014), and solar radiation (p = 0.002) showed significant relationships with acoustic indices, confirming their influence on both animal behaviour and sound propagation. Spatial analyses showed significant differences in acoustic patterns across points (Kruskal–Wallis p < 0.01), with vegetation metrics such as tree density and evergreen proportion correlating with elevated biophonic activity. Although the canopy height model did not emerge as a significant predictor in the models, the observed spatial heterogeneity supports the role of vegetation in shaping urban sound environments. By integrating ecoacoustic indices, LiDAR-derived vegetation data, and microclimatic parameters, this study offers novel insights into how vegetational components should be considered to manage urban green areas to support biodiversity and foster acoustically restorative environments, advancing the evidence base for sound-informed urban planning.
- Open Access
- 23 July 2025
- Published by MDPI AG in Information
- Vol. 16 (8) , 628
Fine-Tuning BirdNET for the Automatic Ecoacoustic Monitoring of Bird Species in the Italian Alpine Forests
The ongoing decline in global biodiversity constitutes a critical challenge for environmental science, necessitating the prompt development of effective monitoring frameworks and conservation protocols to safeguard the structure and function of natural ecosystems. Recent progress in ecoacoustic monitoring, supported by advances in artificial intelligence, might finally offer scalable tools for systematic biodiversity assessment. In this study, we evaluate the performance of BirdNET, a state-of-the-art deep learning model for avian sound recognition, in the context of selected bird species characteristic of the Italian Alpine region. To this end, we assemble a comprehensive, manually annotated audio dataset targeting key regional species, and we investigate a variety of strategies for model adaptation, including fine-tuning with data augmentation techniques to enhance recognition under challenging recording conditions. As a baseline, we also develop and evaluate a simple Convolutional Neural Network (CNN) trained exclusively on our domain-specific dataset. Our findings indicate that BirdNET performance can be greatly improved by fine-tuning the pre-trained network with data collected within the specific regional soundscape, outperforming both the original BirdNET and the baseline CNN by a significant margin. These findings underscore the importance of environmental adaptation and data variability for the development of automated ecoacoustic monitoring devices while highlighting the potential of deep learning methods in supporting conservation efforts and informing soundscape management in protected areas.
- 23 July 2025
- Published by MDPI AG in Information
- Vol. 16 (8) , 628
Open AccessFine-Tuning BirdNET for the Automatic Ecoacoustic Monitoring of Bird Species in the Italian Alpine Forests
The ongoing decline in global biodiversity constitutes a critical challenge for environmental science, necessitating the prompt development of effective monitoring frameworks and conservation protocols to safeguard the structure and function of natural ecosystems. Recent progress in ecoacoustic monitoring, supported by advances in artificial intelligence, might finally offer scalable tools for systematic biodiversity assessment. In this study, we evaluate the performance of BirdNET, a state-of-the-art deep learning model for avian sound recognition, in the context of selected bird species characteristic of the Italian Alpine region. To this end, we assemble a comprehensive, manually annotated audio dataset targeting key regional species, and we investigate a variety of strategies for model adaptation, including fine-tuning with data augmentation techniques to enhance recognition under challenging recording conditions. As a baseline, we also develop and evaluate a simple Convolutional Neural Network (CNN) trained exclusively on our domain-specific dataset. Our findings indicate that BirdNET performance can be greatly improved by fine-tuning the pre-trained network with data collected within the specific regional soundscape, outperforming both the original BirdNET and the baseline CNN by a significant margin. These findings underscore the importance of environmental adaptation and data variability for the development of automated ecoacoustic monitoring devices while highlighting the potential of deep learning methods in supporting conservation efforts and informing soundscape management in protected areas.
- Open Access
- 8 August 2022
- Published by Cambridge University Press (CUP) in Bird Conservation International
- Vol. 33, 1-18
Birds and Natura 2000: a review of the scientific literature
Summary: The Natura 2000 network, the pillar of biodiversity conservation in Europe, still shows some knowledge gaps after almost 30 years since its implementation. As birds are a taxonomic group that is underrepresented in the literature related to Natura 2000 compared to their importance in the EU Directives, this review investigated the characteristics of the scientific research dedicated to birds in relation to Natura 2000. This review focused on 169 peer-reviewed articles covering a period of 25 years (1995–2019). Most studies were set within single Natura 2000 site or regions within countries, and concerned terrestrial habitats, particularly wetlands. The terrestrial Mediterranean biogeographical region and marine Atlantic region had the greatest number of publications, while Spain, Italy, and France were the countries with the highest number of reviewed articles. The number of publications was correlated to Natura 2000 coverage at both country and biogeographical region level. Bird species were studied mainly at a community or single-species level and most publications studied distribution and occurrence of the bird species of interest, while very few assessed the conservation status of the species. Only a few articles set within Natura 2000 sites addressed the issues of habitat suitability for birds or the effectiveness of conservation efforts. Both Annex I and non-Annex I bird species were examined in the literature, with most species having decreasing population trends at the European scale. Future research on bird conservation and Natura 2000 should focus on marine ecosystems as well as habitats that have received less attention despite their important role in a changing future (alpine and urban types). Moreover, future studies should encompass larger spatial scales and those species for which status and trends are still not thoroughly investigated. Finally, it would be important to enhance research efforts on the conservation status and effectiveness in relation to the network.
- 8 August 2022
- Published by Cambridge University Press (CUP) in Bird Conservation International
- Vol. 33, 1-18
Open AccessBirds and Natura 2000: a review of the scientific literature
Summary: The Natura 2000 network, the pillar of biodiversity conservation in Europe, still shows some knowledge gaps after almost 30 years since its implementation. As birds are a taxonomic group that is underrepresented in the literature related to Natura 2000 compared to their importance in the EU Directives, this review investigated the characteristics of the scientific research dedicated to birds in relation to Natura 2000. This review focused on 169 peer-reviewed articles covering a period of 25 years (1995–2019). Most studies were set within single Natura 2000 site or regions within countries, and concerned terrestrial habitats, particularly wetlands. The terrestrial Mediterranean biogeographical region and marine Atlantic region had the greatest number of publications, while Spain, Italy, and France were the countries with the highest number of reviewed articles. The number of publications was correlated to Natura 2000 coverage at both country and biogeographical region level. Bird species were studied mainly at a community or single-species level and most publications studied distribution and occurrence of the bird species of interest, while very few assessed the conservation status of the species. Only a few articles set within Natura 2000 sites addressed the issues of habitat suitability for birds or the effectiveness of conservation efforts. Both Annex I and non-Annex I bird species were examined in the literature, with most species having decreasing population trends at the European scale. Future research on bird conservation and Natura 2000 should focus on marine ecosystems as well as habitats that have received less attention despite their important role in a changing future (alpine and urban types). Moreover, future studies should encompass larger spatial scales and those species for which status and trends are still not thoroughly investigated. Finally, it would be important to enhance research efforts on the conservation status and effectiveness in relation to the network.
- 1 August 2015
- Published by Elsevier in Renewable and Sustainable Energy Reviews
- Vol. 48, 608-623
Renewable energies and ecosystem service impacts
- 1 August 2015
- Published by Elsevier in Renewable and Sustainable Energy Reviews
- Vol. 48, 608-623
Renewable energies and ecosystem service impacts