Earth Observation and Biodiversity Big Data for Forest Habitat Types Classification and Mapping

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 Forest (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.

Earth Observation for Phenological Metrics (EO4PM): Temporal Discriminant to Characterize Forest Ecosystems

“…The start and the end of growing season is intended to represent seasonal bounds of photosynthetic tissues development phases. Diversely, the end of season comes at the end of the period of leaf-mineral nutrient remobilization during leaf senescence, when the plant is curtailing chlorophyll production revealing various accessory pigments, determining yellowing or browning of leaves, and consequently, driving the starting of fall foliage [61]. Vegetation normally changes more quickly during greenup than senescence [32], as noticeable from Figure 4.…”

“…Forest plant communities, together with their own typical floristic composition, show exclusive phenological dynamics recognizable by vegetation indices time series [42]. Both vegetation indices time series [42,61] and land surface phenological metrics [61,92] has been successfully used to classify plant communities and natural habitats, discriminating vegetation patterns dominated by species with similar phenology features. Multivariate statistical analysis conducted in this research study allowed to understand how the three generated datasets (the smoothed vegetation curve, the temporal statistics, and the phenological metrics) have the capacity to serve as temporal discriminants to detect forest ecosystems processes responses to environmental gradients.…”

“…The archive includes georeferenced vegetation plots with species list and cover abundance. The sub-dataset used in this study takes into account vegetation plots smaller than 200 m 2 and with a geographic localization accuracy ranging from 0.1 to 30 m. Following the EUNIS (European Nature Information System) II and III level hierarchical classification nomenclature [60] 14,385 plots from the EVA dataset were selected and classified (Table 1) [61]. Figure 1 shows the spatial distribution of forest stands along the Italian peninsula at II level EUNIS classification.…”

“…Figure 1 shows the spatial distribution of forest stands along the Italian peninsula at II level EUNIS classification. These forest types at EUNIS level II were used to estimate the smoothed vegetation curve and the temporal statistics, while regarding the phenological metrics estimate, only deciduous broadleaved forest types (T1) at EUNIS III level were considered from the vegetation plot records of the archive, since for the evergreen forest types is more difficult to identify the timing of the onset of greenness and senescence due to the lower temporal fluctuation of the vegetation index time series [61,62] and snow prevalence during wintertime in mountain ecosystems [55], hiding evergreen forests.…”

Comparison of LAI Estimates from High Resolution Satellite Observations Using Different Biophysical Processors

“…LAI information is widely adopted for crop monitoring and for numerical modeling applications [2], to derive phenological metrics [3], and to identify and map the main crop types [4]. It has also been demonstrated to be effective to monitor vegetation dynamics [5] and to map terrestrial natural habitats [6].…”