Abstract
In the light of the “Biological Diversity” concept, habitats are cardinal pieces for biodiversity quantitative estimation at a local and global scale. In Europe EUNIS (European Nature Information System) is a system tool for habitat identification and assessment. Earth Observation (EO) data, which are acquired by satellite sensors, offer new opportunities for environmental sciences and they are revolutionizing the methodologies applied. These are providing unprecedented insights for habitat monitoring and for evaluating the Sustainable Development Goals (SDGs) indicators. This paper shows the results of a novel approach for a spatially explicit habitat mapping in Italy at a national scale, using a supervised machine learning model (SMLM), through the combination of vegetation plot database (as response variable), and both spectral and environmental predictors. The procedure integrates forest habitat data in Italy from the European Vegetation Archive (EVA), with Sentinel-2 imagery processing (vegetation indices time series, spectral indices, and single bands spectral signals) and environmental data variables (i.e., climatic and topographic), to parameterize a Random Forests (RF) classifier. The obtained results classify 24 forest habitats according to the EUNIS III level: 12 broadleaved deciduous (T1), 4 broadleaved evergreen (T2) and eight needleleaved forest habitats (T3), and achieved an overall accuracy of 87% at the EUNIS II level classes (T1, T2, T3), and an overall accuracy of 76.14% at the EUNIS III level. The highest overall accuracy value was obtained for the broadleaved evergreen forest equal to 91%, followed by 76% and 68% for needleleaved and broadleaved deciduous habitat forests, respectively. The results of the proposed methodology open the way to increase the EUNIS habitat categories to be mapped together with their geographical extent, and to test different semi-supervised machine learning algorithms and ensemble modelling methods.
Highlights
Licensee MDPI, Basel, Switzerland.Global-scale environmental issues, from climate change to biosphere integrity [1], are creating an intense social pressure and a growing need for information with appropriate reliability and suitable spatial scale that must be provided by the scientific community [2,3,4,5].it is strictly urgent to ensure the integrity of the Bio, Hydro, and Geosphere by following the advance of the high technologies
14385 plots were selected and classified in 24 forest habitats according to the EUNIS III level: 12 broadleaved deciduous (T1), four broadleaved evergreen (T2), and eight needleleaved forest habitats (T3) (Table 3)
This study demonstrates the suitability of the Sentinel-2 Multi-Spectral Instrument (MSI) derived information for the separability of broad cover forest habitat types (i.e., EUNIS II level, based on plant functional traits), as well as for the identification of detailed EUNIS classification types (i.e., III level), based on their ecological features [55]
Summary
Licensee MDPI, Basel, Switzerland.Global-scale environmental issues, from climate change to biosphere integrity [1], are creating an intense social pressure and a growing need for information with appropriate reliability and suitable spatial scale (from the local to global analysis and vice versa) that must be provided by the scientific community [2,3,4,5].it is strictly urgent to ensure the integrity of the Bio, Hydro, and Geosphere by following the advance of the high technologies. Global-scale environmental issues, from climate change to biosphere integrity [1], are creating an intense social pressure and a growing need for information with appropriate reliability and suitable spatial scale (from the local to global analysis and vice versa) that must be provided by the scientific community [2,3,4,5]. It is reasonable that the potential availability of a huge amount of “big data” in the future will allow for the use of advanced analytic techniques, extracting useful information from different large datasets, including those observing and measuring the ecosystem processes in response to environmental drivers of changes [7]. A multidisciplinary approach, including machine learning techniques, data mining, big data analytics, and ecological modelling, is highly recommended to interpret ecological processes and identify adequate solutions for the Anthropocene environmental issues [8]. The use of big data today represents a big challenge, from detailed analysis on specific topics or geographic areas to issues at wider scales and over broader timescales [5]
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
