Earth Observation and Biodiversity Big Data for Forest Habitat Types Classification and Mapping
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 a...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-03-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/13/7/1231 |
| _version_ | 1797540265174499328 |
|---|---|
| author | Emiliano Agrillo Federico Filipponi Alice Pezzarossa Laura Casella Daniela Smiraglia Arianna Orasi Fabio Attorre Andrea Taramelli |
| author_facet | Emiliano Agrillo Federico Filipponi Alice Pezzarossa Laura Casella Daniela Smiraglia Arianna Orasi Fabio Attorre Andrea Taramelli |
| author_sort | Emiliano Agrillo |
| collection | DOAJ |
| description | 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. |
| first_indexed | 2024-03-10T12:57:38Z |
| format | Article |
| id | doaj.art-f8424a048374411895950ea7643e5685 |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-10T12:57:38Z |
| publishDate | 2021-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-f8424a048374411895950ea7643e56852023-11-21T11:47:04ZengMDPI AGRemote Sensing2072-42922021-03-01137123110.3390/rs13071231Earth Observation and Biodiversity Big Data for Forest Habitat Types Classification and MappingEmiliano Agrillo0Federico Filipponi1Alice Pezzarossa2Laura Casella3Daniela Smiraglia4Arianna Orasi5Fabio Attorre6Andrea Taramelli7Italian National Institute for Environmental Protection and Research (ISPRA), Via Vitaliano Brancati 48, 00144 Roma, ItalyItalian National Institute for Environmental Protection and Research (ISPRA), Via Vitaliano Brancati 48, 00144 Roma, ItalyItalian National Institute for Environmental Protection and Research (ISPRA), Via Vitaliano Brancati 48, 00144 Roma, ItalyItalian National Institute for Environmental Protection and Research (ISPRA), Via Vitaliano Brancati 48, 00144 Roma, ItalyItalian National Institute for Environmental Protection and Research (ISPRA), Via Vitaliano Brancati 48, 00144 Roma, ItalyItalian National Institute for Environmental Protection and Research (ISPRA), Via Vitaliano Brancati 48, 00144 Roma, ItalyDepartment of Environmental Biology, University of Roma “La Sapienza”, Piazzale Aldo Moro 5, 00185 Roma, ItalyItalian National Institute for Environmental Protection and Research (ISPRA), Via Vitaliano Brancati 48, 00144 Roma, ItalyIn 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.https://www.mdpi.com/2072-4292/13/7/1231forest habitathabitat classificationhabitat mappinghabitat monitoringRandom Forestssupervised machine learning modelling |
| spellingShingle | Emiliano Agrillo Federico Filipponi Alice Pezzarossa Laura Casella Daniela Smiraglia Arianna Orasi Fabio Attorre Andrea Taramelli Earth Observation and Biodiversity Big Data for Forest Habitat Types Classification and Mapping Remote Sensing forest habitat habitat classification habitat mapping habitat monitoring Random Forests supervised machine learning modelling |
| title | Earth Observation and Biodiversity Big Data for Forest Habitat Types Classification and Mapping |
| title_full | Earth Observation and Biodiversity Big Data for Forest Habitat Types Classification and Mapping |
| title_fullStr | Earth Observation and Biodiversity Big Data for Forest Habitat Types Classification and Mapping |
| title_full_unstemmed | Earth Observation and Biodiversity Big Data for Forest Habitat Types Classification and Mapping |
| title_short | Earth Observation and Biodiversity Big Data for Forest Habitat Types Classification and Mapping |
| title_sort | earth observation and biodiversity big data for forest habitat types classification and mapping |
| topic | forest habitat habitat classification habitat mapping habitat monitoring Random Forests supervised machine learning modelling |
| url | https://www.mdpi.com/2072-4292/13/7/1231 |
| work_keys_str_mv | AT emilianoagrillo earthobservationandbiodiversitybigdataforforesthabitattypesclassificationandmapping AT federicofilipponi earthobservationandbiodiversitybigdataforforesthabitattypesclassificationandmapping AT alicepezzarossa earthobservationandbiodiversitybigdataforforesthabitattypesclassificationandmapping AT lauracasella earthobservationandbiodiversitybigdataforforesthabitattypesclassificationandmapping AT danielasmiraglia earthobservationandbiodiversitybigdataforforesthabitattypesclassificationandmapping AT ariannaorasi earthobservationandbiodiversitybigdataforforesthabitattypesclassificationandmapping AT fabioattorre earthobservationandbiodiversitybigdataforforesthabitattypesclassificationandmapping AT andreataramelli earthobservationandbiodiversitybigdataforforesthabitattypesclassificationandmapping |