Knowledge-Based Classification of Grassland Ecosystem Based on Multi-Temporal WorldView-2 Data and FAO-LCCS Taxonomy

Abstract

Grassland ecosystems can provide a variety of services for humans, such as carbon storage, food production, crop pollination and pest regulation. However, grasslands are today one of the most endangered ecosystems due to land use change, agricultural intensification, land abandonment as well as climate change. The present study explores the performance of a knowledge-driven GEOgraphic-Object—based Image Analysis (GEOBIA) learning scheme to classify Very High Resolution (VHR) images for natural grassland ecosystem mapping. The classification was applied to a Natura 2000 protected area in Southern Italy. The Food and Agricultural Organization Land Cover Classification System (FAO-LCCS) hierarchical scheme was instantiated in the learning phase of the algorithm. Four multi-temporal WorldView-2 (WV-2) images were classified by combining plant phenology and agricultural practices rules with prior-image spectral knowledge. Drawing on this knowledge, spectral bands and entropy features from one single date (Post Peak of Biomass) were firstly used for multiple-scale image segmentation into Small Objects (SO) and Large Objects (LO). Thereafter, SO were labelled by considering spectral and context-sensitive features from the whole multi-seasonal data set available together with ancillary data. Lastly, the labelled SO were overlaid to LO segments and, in turn, the latter were labelled by adopting FAO-LCCS criteria about the SOs presence dominance in each LO. Ground reference samples were used only for validating the SO and LO output maps. The knowledge driven GEOBIA classifier for SO classification obtained an OA value of 97.35% with an error of 0.04. For LO classification the value was 75.09% with an error of 0.70. At SO scale, grasslands ecosystem was classified with 92.6%, 99.9% and 96.1% of User’s, Producer’s Accuracy and F1-score, respectively. The findings reported indicate that the knowledge-driven approach not only can be applied for (semi)natural grasslands ecosystem mapping in vast and not accessible areas but can also reduce the costs of ground truth data acquisition. The approach used may provide different level of details (small and large objects in the scene) but also indicates how to design and validate local conservation policies.

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

“…Recently, several scientific projects and studies have focused on natural habitats detection and the monitoring of their conservation status by using EO products [26][27][28][29][30][31]. Satellite data have been used for mapping grasslands using multitemporal high resolution optical and multispectral optical data [32], forest communities using NDVI time series [33], coastal habitats using spectral mixing analysis [34,35], phenological analysis using Sentinel-2 vegetation indices time series [36,37], or the assessment of plant functional types using radar backscatter [38].…”

Superpixel-Based Regional-Scale Grassland Community Classification Using Genetic Programming with Sentinel-1 SAR and Sentinel-2 Multispectral Images

“…Sentinel-1 and Sentinel-2 are sensors developed by the European Space Agency (ESA) Copernicus for earth observation. The sensors are commonly used in vegetation studies owing to the high data quality and availability [4,38]. The Sentinel images used in this study (Table 2) were retrieved from Sentinels Scientific Data Hub (https://scihub.copernicus.eu/, accessed on 1 August 2020), resampled to 10 m using bilinear interpolation, geographically registered, and subset into the study area.…”

“…Grassland communities are considered the fundamental unit of grassland ecosystems [3]. Accurate classification of grassland communities is important for humans to understand and study grassland areas, and provides an important basis for rational use, effective conservation, and sustainable development [4]. Field surveys are a reliable way to classify grasslands.…”

Combined use of environmental and spectral variables with vegetation archives for large-scale modeling of grassland habitats

“…In contrast, national modeling of the land-use/land-cover (LULC) grassland class (Inglada et al, 2017), which includes both natural and non-natural grasslands (Allen et al, 2011), as well as the description of their management practices (Griffiths et al, 2020) is operational through the use of satellite time series. On this basis, many studies have translated the LULC grassland class into general grassland habitat types using decision rules based on very-high-spatial-resolution remote-sensing data acquired at local sites (Adamo et al, 2015, 2020; Moran et al, 2017). However, this approach raises the problem of one-to-many correspondence (Kosmidou et al, 2014), as well as that of the transferability of decision rules related to variation in the quality, number of acquisitions and type of remote sensing data available among local sites (Corbane et al, 2015).…”