The milestone presents in the first part the general criteria that will be followed in the next stages of SHOWCASE T2.7 for the selection of biodiversity and ecosystem service indicators to map them under different management scenarios. In the second part, the milestone reports an example of biodiversity indicators modeling and mapping resorting to machine learning algorithms, for the case study area of Baixo and Central Alentejo in Portugal. In order to integrate in the spatial analysis the impact of the intensity of olive growing on biodiversity richness, a new land use map was created resorting to Google Earth Engine and Sentinel-2 MSI products. The new map was used as categorical predictor, along with other covariates, in the spatial modelling of two biodiversity richness indicators and resulted to be a major driver of both indicators. Maps of prediction accuracy are provided as well.
Selection of biodiversity indicators for spatial temporal modelling
Mara Ottoboni;
2022
Abstract
The milestone presents in the first part the general criteria that will be followed in the next stages of SHOWCASE T2.7 for the selection of biodiversity and ecosystem service indicators to map them under different management scenarios. In the second part, the milestone reports an example of biodiversity indicators modeling and mapping resorting to machine learning algorithms, for the case study area of Baixo and Central Alentejo in Portugal. In order to integrate in the spatial analysis the impact of the intensity of olive growing on biodiversity richness, a new land use map was created resorting to Google Earth Engine and Sentinel-2 MSI products. The new map was used as categorical predictor, along with other covariates, in the spatial modelling of two biodiversity richness indicators and resulted to be a major driver of both indicators. Maps of prediction accuracy are provided as well.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
