Google Earth Engine (GEE) is a versatile cloud platform in which pixel-based (PB) and object-oriented (OO) Land Use–Land Cover (LULC) classification approaches can be implemented, thanks to the availability of the many state-of-art functions comprising various Machine Learning (ML) algorithms. OO approaches, including both object segmentation and object textural analysis, are still not common in the GEE environment, probably due to the difficulties existing in concatenating the proper functions, and in tuning the various parameters to overcome the GEE computational limits. In this context, this work is aimed at developing and testing an OO classification approach combining the Simple Non-Iterative Clustering (SNIC) algorithm to identify spatial clusters, the Gray-Level Co-occurrence Matrix (GLCM) to calculate cluster textural indices, and two ML algorithms (Random Forest (RF) or Support Vector Machine (SVM)) to perform the final classification. A Principal Components Analysis (PCA) is applied to the main seven GLCM indices to synthesize in one band the textural information used for the OO classification. The proposed approach is implemented in a user-friendly, freely available GEE code useful to perform the OO classification, tuning various parameters (e.g., choose the input bands, select the classification algorithm, test various segmentation scales) and compare it with a PB approach. The accuracy of OO and PB classifications can be assessed both visually and through two confusion matrices that can be used to calculate the relevant statistics (producer’s, user’s, overall accuracy (OA)). The proposed methodology was broadly tested in a 154 km² study area, located in the Lake Trasimeno area (central Italy), using Landsat 8 (L8), Sentinel 2 (S2), and PlanetScope (PS) data. The area was selected considering its complex LULC mosaic mainly composed of artificial surfaces, annual and permanent crops, small lakes, and wooded areas. In the study area, the various tests produced interesting results on the different datasets (OA: PB RF (L8 = 72.7%, S2 = 82%, PS = 74.2), PB SVM (L8 = 79.1%, S2 = 80.2%, PS = 74.8%), OO RF (L8 = 64%, S2 = 89.3%, PS = 77.9), OO SVM (L8 = 70.4, S2 = 86.9%, PS = 73.9)). The broad code application demonstrated very good reliability of the whole process, even though the OO classification process resulted, sometimes, too demanding on higher resolution data, considering the available computational GEE resources.

With the general objective of producing a 2018–2020 Land Use/Land Cover (LULC) map of the Maiella National Park (central Italy), useful for a future long-term LULC change analysis, this research aimed to develop a Landsat 8 (L8) data composition and classification process using Google Earth Engine (GEE). In this process, we compared two pixel-based (PB) and two object-based (OB) approaches, assessing the advantages of integrating the textural information in the PB approach. Moreover, we tested the possibility of using the L8 panchromatic band to improve the segmentation step and the object’s textural analysis of the OB approach and produce a 15-m resolution LULC map. After selecting the best time window of the year to compose the base data cube, we applied a cloud-filtering and a topography-correction process on the 32 available L8 surface reflectance images. On this basis, we calculated five spectral indices, some of them on an interannual basis, to account for vegetation seasonality. We added an elevation, an aspect, a slope layer, and the 2018 CORINE Land Cover classification layer to improve the available information. We applied the Gray-Level Co-Occurrence Matrix (GLCM) algorithm to calculate the image’s textural information and, in the OB approaches, the Simple Non-Iterative Clustering (SNIC) algorithm for the image segmentation step. We performed an initial RF optimization process finding the optimal number of decision trees through out-of-bag error analysis. We randomly distributed 1200 ground truth points and used 70% to train the RF classifier and 30% for the validation phase. This subdivision was randomly and recursively redefined to evaluate the performance of the tested approaches more robustly. The OB approaches performed better than the PB ones when using the 15 m L8 panchromatic band, while the addition of textural information did not improve the PB approach. Using the panchromatic band within an OB approach, we produced a detailed, 15-m resolution LULC map of the study area.

Seminatural grasslands are among the most threatened habitats in Europe and worldwide, mainly due to changes in/abandonment of their traditional extensive use by grazing animals. This study aimed to develop an innovative model that integrates plant biodiversity, animal husbandry, and geo-informatics to manage and preserve seminatural grasslands in protected areas. With this objective, an integrated study was conducted on the seminatural grasslands in the hilly, montane, and (to a minimum extent) subalpine belts of the Maiella National Park, one of Europe’s most biodiversity-rich protected sites. Plant biodiversity was investigated through 141 phytosociological relevés in homogeneous areas; the pastoral value was calculated, and grasslands’ productivity was measured together with the main nutritional parameters. Uni- and multivariate statistical analyses were performed to identify the main grassland vegetation types, their indicator species and ecological–environmental characteristics, and their pastoral and nutritional values’ variability and differences. A total of 17 grassland types, most of which correspond to habitat types listed in Annex I to the 92/43/EEC Directive, were identified and characterised in terms of their biodiversity and potential animal load. To allow for near-real-time analysis of grasslands, an NDVI-based web interface running on Google Earth Engine was implemented. This integrated approach can provide decision-making support for protected-area managers seeking to develop and implement sustainable grassland management practices that ensure the long-term maintenance of their biodiversity.

Tassi, A. and Gil, A., 2020. A low-cost Sentinel-2 data and Rao's Q diversity index-based application for detecting, assessing and monitoring coastal land-cover/land-use changes at high spatial resolution. In: Malvárez, G. and Navas, F. (eds.), Global Coastal Issues of 2020. Journal of Coastal Research, Special Issue No. 95, pp. 1315-1319. Coconut Creek (Florida), ISSN 0749-0208.Coastal zones in small oceanic islands as the Archipelago of the Azores (Portugal) are very sensitive territories severely threatened by climate change, natural disasters, biological invasions, infrastructure and tourism development, and also agriculture intensification. Land-cover/land-use changes are one of the most relevant indicators for monitoring and assessing coastal spatial planning and management policies in insular territories. This paper describes the application of a low-cost Rao's Q diversity index-based remote sensing tool able to provide a systematic and accurate coastal land-cover/land-use monitoring system in small oceanic islands, using free and open access Sentinel-2 multispectral satellite data and Terceira island (Archipelago of the Azores, Portugal) as the case-study area. Results indicate that about 7% (∼300 hectares) of Terceira Island's coastal zone (∼4290 hectares) have changed their land-cover/ land-use between March 2017 and December 2018 (21 months). Agricultural areas (4.1%), urban areas (2.1%) and bare soil areas (0.6%) are the categories showing more relevant changes.