National Scale Land Cover Classification for Ecosystem Services Mapping and Assessment, Using Multitemporal Copernicus EO Data and Google Earth Engine

Abstract

Land-Use/Land-Cover (LULC) products are a common source of information and a key input for spatially explicit models of ecosystem service (ES) supply and demand. Global, continental, and regional, readily available, and free land-cover products generated through Earth Observation (EO) data, can be potentially used as relevant to ES mapping and assessment processes from regional to national scales. However, several limitations exist in these products, highlighting the need for timely land-cover extraction on demand, that could replace or complement existing products. This study focuses on the development of a classification workflow for fine-scale, object-based land cover mapping, employed on terrestrial ES mapping, within the Greek terrestrial territory. The processing was implemented in the Google Earth Engine cloud computing environment using 10 m spatial resolution Sentinel-1 and Sentinel-2 data. Furthermore, the relevance of different training data extraction strategies and temporal EO information for increasing the classification accuracy was also evaluated. The different classification schemes demonstrated differences in overall accuracy ranging from 0.88% to 4.94% with the most accurate classification scheme being the manual sampling/monthly feature classification achieving a 79.55% overall accuracy. The classification results suggest that existing LULC data must be cautiously considered for automated extraction of training samples, in the case of new supervised land cover classifications aiming also to discern complex vegetation classes. The code used in this study is available on GitHub and runs on the Google Earth Engine web platform.

MAES_GR: A Web-Based, Spatially Enabled Field Survey Platform for the MAES Implementation in Greece

“…Many studies in the past employed field data alone or along with remote sensing measurements for direct ES assessment [25]. Based on a comprehensive needs' assessment, similar to earlier studies, we further identified that field surveys are also considered essential for providing timely data for assessing the accuracy of remote sensing-based efforts for ecosystem type mapping [23]. They are also essential for ground validation of EC and ES availability and flows [20,22] estimated through spatial analysis.…”

“…The initial step to begin the assessment is to select the relevant ecosystem type at the most detailed level that can be identified by the surveyor at the plot, i.e., MAES level 1, 2, 3 or at the habitat type level (most detailed). For the delineation of the ecosystem type classification scheme, we followed the typology proposed by previous studies for Greece, which allows the correspondence of all terrestrial habitat types to the MAES Level 1, 2, 3 ecosystem type classes [21][22][23]31]. Table 1 presents an example of the typology for wetland classes, while the detailed typology for all terrestrial ecosystems is included in Table S1.…”

“…Since 2015, Greece has been developing methodologies, actions, and capacity building workshops and projects to integrate MAES into management practices and decision-making processes (e.g., [20][21][22][23]). These efforts, conducted under the requirements of the EU Biodiversity Strategy, are mainly supported by the Action A.3 of the Life Integrated Project "LIFE-IP 4 NATURA" [24], led by the Hellenic Ministry of Environment and Energy, which aims to implement the MAES approach at the national, regional and local (case-study) level.…”

“…While ground data from other European or national biodiversity relevant monitoring schemes have the potential to provide certain ES parameters, in general they are of limited use due to the missing cross-reference between the original data-recording scheme and MAES implementation needs [26]. In addition, such monitoring schemes with coarse update intervals present discrepancies and outdatedness in comparison to the actual landscape structure [23].…”

Validation of Visually Interpreted Corine Land Cover Classes with Spectral Values of Satellite Images and Machine Learning

“…OAs of our classifications were almost as good as in these studies, but we used the CLC polygons, which was a relevant difference. Verde et al [63] elaborated a national-level land cover mapping scheme for ecosystem services. They applied superpixel segmentation and, similarly to our approach, used the RF classifier and their best result was an OA of 79%.…”