Predicting tropical dry forest successional attributes from space: is the key hidden in image texture?

Abstract

Biodiversity conservation and ecosystem-service provision will increasingly depend on the existence of secondary vegetation. Our success in achieving these goals will be determined by our ability to accurately estimate the structure and diversity of such communities at broad geographic scales. We examined whether the texture (the spatial variation of the image elements) of very high-resolution satellite imagery can be used for this purpose. In 14 fallows of different ages and one mature forest stand in a seasonally dry tropical forest landscape, we estimated basal area, canopy cover, stem density, species richness, Shannon index, Simpson index, and canopy height. The first six attributes were also estimated for a subset comprising the tallest plants. We calculated 40 texture variables based on the red and the near infrared bands, and EVI and NDVI, and selected the best-fit linear models describing each vegetation attribute based on them. Basal area (R(2) = 0.93), vegetation height and cover (0.89), species richness (0.87), and stand age (0.85) were the best-described attributes by two-variable models. Cross validation showed that these models had a high predictive power, and most estimated vegetation attributes were highly accurate. The success of this simple method (a single image was used and the models were linear and included very few variables) rests on the principle that image texture reflects the internal heterogeneity of successional vegetation at the proper scale. The vegetation attributes best predicted by texture are relevant in the face of two of the gravest threats to biosphere integrity: climate change and biodiversity loss. By providing reliable basal area and fallow-age estimates, image-texture analysis allows for the assessment of carbon sequestration and diversity loss rates. New and exciting research avenues open by simplifying the analysis of the extent and complexity of successional vegetation through the spatial variation of its spectral information.

Figure 1. Study area (UTM zone 15n) and location of the secondary plots (▪) used for modeling their attributes from the texture derived from a Quickbird satellite image.

Figure 2. Fraction of the variation in vegetation attributes (median and range) explained by the descriptive (—♦—), predictive (- -○- -) and null (—▴—) models using a different number of textural attributes as explanatory variables.

For the descriptive and null models conventional R ² values are reported, while for the predictive models R ² _CV is reported, so the values are not strictly comparable (see Methods for explanation).

Figure 3. Observed (x-axes) vs. estimated (y-axes) values for the best descriptive (▴) and predictive (red +) linear models for vegetation attributes.

See Table 1 for vegetational attributes abbreviations. Digits 1, 2, and 3 refer to the number of textural variables included in the model as explanatory variables.