In line with the growing recognition of the need to move beyond point-to-point GIS analyses to realize dynamic insights into past landscapes, we turned to multivariate total landscape geospatial modeling increasingly common in ecology.
The obtained spectra were analysed chemometrically with the multi-way technique, parallel factor analysis (PARAFAC), resulting in a decomposition of the multivariate fluorescent landscape, whereby underlying spectra of the individual intrinsic fluorophors present in the cell mass were estimated.
In this research Kernel Density Estimation, multivariate spatial analysis, landscape pattern analysis, and Principal Component Analysis (PCA) were combined to model and characterise landscape gradients, and to analyse the structural features of fringe areas.
Sample sites were allocated based on a multivariate classification of landscape attributes.
In such a landscape, multivariate statistical analysis has been used to differentiate among the main hydrochemical processes occurring in the area, using three different approaches of factor analysis: (i) major elements, (ii) trace elements, (iii) both major and trace elements.
Where clear positive correlations between N concentrations in deposition and mosses exist in landscapes, multivariate ranking identifies the deposition as main influencing factor.
These new models suggest that genetic drift can operate when there exist neutral adaptive ridges in multivariate "holey adaptive landscapes" [ 3].
We described the landscape using multivariate ordination analyses of data characterizing the physiognomy of the municipalities.
To do so, we used techniques from modern multivariate statistics to disentangle widely used landscape metrics with respect to four landscape components: extent (E), resolution (R), percentage of suitable habitat cover (P), and spatial autocorrelation level (H).
Variation in the nearshore data was analyzed using multivariate stepwise regressions with respect to landscape characteristics of the adjacent coastal watersheds (US only).
