Employing a spatio-temporal contingency table for the analysis of cork oak cover change in the Sa Serra region of Sardinia

Abstract

Land cover change analyses are common and, especially in the absence of explanatory variables, they are mainly carried out by employing qualitative methods such as transition matrices or raster operations. These methods do not provide any estimation of the statistical significance of the changes, or the uncertainty of the model and data, and are usually limited in supporting explicit biological/ecological interpretation of the processes determining the changes. Here we show how the original nearest-neighbour contingency table, proposed by Dixon to evaluate spatial segregation, has been extended to the temporal domain to map the intensity, statistical significance and uncertainty of land cover changes. This index was then employed to quantify the changes in cork oak forest cover between 1998 and 2016 in the Sa Serra region of Sardinia (Italy). The method showed that most statistically significant cork oak losses were concentrated in the centre of Sa Serra and characterised by high intensity. A spatial binomial-logit generalised linear model estimated the probability of changes occurring in the area but not the type of change. We show how the spatio-temporal Dixon's index can be an attractive alternative to other land cover change analysis methods, since it provides a robust statistical framework and facilitates direct biological/ecological interpretation.

Figure 1

Study area of Sa Serra (within white contour). Background from Google Earth (Image: Google, Landsat/Copernicus). Source administrative limits: http://dati.regione.sardegna.it/dataset/limiti-amministrativi-comunali under CC-BY-4.0 licence.

Figure 2

Land cover in the Sa Serra region in 1998 (a) and 2016 (b). Maps were made using ArcMap 10.4 (http://desktop.arcgis.com/en/arcmap/). Source administrative limits: http://dati.regione.sardegna.it/dataset/limiti-amministrativi-comunali under CC-BY-4.0 licence.

Figure 3

Land cover changes in Sa Serra during the period 1998–2016. Panel a: Land cover changes. Panel b: Dixon’s index of segregation. Panel c: Uncertainty of the Dixon’s index of segregation. The Dixon’s index of segregation (Panel b) has unlimited boundaries. Values larger than 0 means segregation, i.e. points with cork oak forest in 1998 are closer to points that became cork oak forest in 2016; conversely negative values mean association, i.e. points with cork oak forest in 1998 changed or are closer to point that changed from cork oak forest to another land cover in 2016. Larger is the value, larger is the rate of segregation, i.e. areas with values equal to −4 are experiencing a rate of change that is double from areas with values equal to -2. Standardised uncertainty varies from 0 to 1 (Panel c), where 1 means largest interquartile range (not possible to infer an accurate value of the index). Maps were made using ArcMap 10.4 (http://desktop.arcgis.com/en/arcmap/). Source administrative limits: http://dati.regione.sardegna.it/dataset/limiti-amministrativi-comunali under CC-BY-4.0 licence.

Figure 4

Cork oak forest cover probability of presence in 2016. Panel a: probability of presence of cork oak forest cover as obtained from the spatially explicit binomial-logit generalised linear model. Panel b: standardised uncertainty where 1 means largest interquartile range of the probability at that location. Maps were made using ArcMap 10.4 (http://desktop.arcgis.com/en/arcmap/). Source administrative limits: http://dati.regione.sardegna.it/dataset/limiti-amministrativi-comunali under CC-BY-4.0 licence.