The influence of environmental spatial structure on the life-history traits and diversity of species in a metacommunity

Several models have been proposed to understand how so many species can coexist in ecosystems. Despite evidence showing that natural habitats are often patchy and fragmented, these models rarely take into account environmental spatial structure. In this study we investigated the influence of spatial structure in habitat and disturbance regime upon species’ traits and species’ coexistence in a metacommunity. We used a population-based model to simulate competing species in spatially explicit landscapes. The species traits we focused on were dispersal ability, competitiveness, reproductive investment and survival rate. Communities were characterized by their species richness and by the four life-history traits averaged over all the surviving species. Our results show that spatial structure and disturbance have a strong influence on the equilibrium life-history traits within a metacommunity. In the absence of disturbance, spatially structured landscapes favour species investing more in reproduction, but less in dispersal and survival. However, this influence is strongly dependent on the disturbance rate, pointing to an important interaction between spatial structure and disturbance. This interaction also plays a role in species coexistence. While spatial structure tends to reduce diversity in the absence of disturbance, the tendency is reversed when disturbance occurs. In conclusion, the spatial structure of communities is an important determinant of their diversity and characteristic traits. These traits are likely to influence important ecological properties such as resistance to invasion or response to climate change, which in turn will determine the fate of ecosystems facing the current global ecological crisis.     

Null models reveal preferential sampling, spatial autocorrelation and overfitting in habitat suitability modelling

Nowadays, species are driven to extinction at a high rate. To reduce this rate it is important to delineate suitable habitats for these species in such a way that these areas can be suggested as conservation areas. The use of habitat suitability models (HSMs) can be of great importance for the delineation of such areas. In this study MaxEnt, a presence-only modelling technique, is used to develop HSMs for 223 nematode species of the Southern Bight of the North Sea. However, it is essential that these models are beyond discussion and they should be checked for potential errors. In this study we focused on two categories (1) errors which can be attributed to the database such as preferential sampling and spatial autocorrelation and (2) errors induced by the modelling technique such as overfitting, In order to quantify these adverse effects thousands of nulls models were created. The effect of preferential sampling (i.e. some areas where visited more frequenty than others) was investigated by comparing model outcomes based from null models sampling the actual sampling stations and null models sampling the entire mapping area (Raes and ter Steege, 2007). Overfitting is exposed by a fivefold cross-validation and the influence of spatial autocorrelation is assessed by separating test and training sets in space. Our results clearly show that all these effects are present: preferential sampling has a strong effect on the selection of non-random species models. Crossvalidation seems to have less influence on the model selection and spatial autocorrelation is also strongly present. It is clear from this study that predefined thresholds are not readily applicable to all datasets and additional tests are needed in model selection.     

The importance of spatial autocorrelation,extent and resolution in predicting forest bird occurrence

Concerns about declines in forest biodiversity underscore the need for accurate estimates of the distribution and abundance of organisms at large scales and at resolutions that are fine enough to be appropriate for management. This paper addresses three major objectives: (i) to determine whether the resolution of typical air photo-derived forest inventory is sufficient for the accurate prediction of site occupancy by forest birds. We compared prediction success of habitat models using air photo variables to models with variables derived from finer resolution, ground-sampled vegetation plots. (ii) To test whether incorporating spatial autocorrelation into habitat models via autologistic regression increases prediction success. (iii) To determine whether landscape structure is an important factor in predicting bird distribution in forest-dominated landscapes. Models were tested locally (Greater Fundy Ecosystem [GFE]) using cross-validation, and regionally using an independent data set from an area located ca. 250 km to the northwest (Riley Brook [RB]). We found significant positive spatial autocorrelation in the residuals of at least one habitat model for 76% (16/21) of species examined. In these cases, the logistic regression assumption of spatially independent errors was violated. Logistic models that ignored spatial autocorrelation tended to overestimate habitat effects. Though overall prediction success was higher for autologistic models than logistic models in the GFE, the difference was only significantly improved for one species. Further, the inclusion of spatial covariates did little to improve model performance in the geographically discrete study area. For 62% (13/21) of species examined, landscape variables were significant predictors of forest bird occurrence even after statistically controlling for stand-level variability. However, broad spatial extents explained less variation than local factors. In the GFE, 76% (16/21) of air photo and 81% (17/21) of ground plot models were accurate enough to be of practical utility (AUC > 0.7). When applied to RB, both model types performed effectively for 55% (11/20) of the species examined. We did not detect an overall difference in prediction success between air photo and ground plot models in either study area. We conclude that air photo data are as effective as fine resolution vegetation data for predicting site occupancy for the majority of species in this study. These models will be of use to forest managers who are interested in mapping species distributions under various timber harvest scenarios, and to protected areas planners attempting to optimize reserve function.     

Change in plant spatial patterns and diversity along the successional gradient of Mediterranean grazing ecosystems

In this study, we analyze the complexity of plant spatial patterns and diversity along a successional gradient resulting from grazing disturbance in four characteristic ecosystems of the Mediterranean region. Grazing disturbance include not only defoliation by animals, but also associated disturbances as animal trampling, soil compaction, and mineralization by deposition of urine and feces. The results show that woodland and dense matorral are more resistant to species loss than middle dense and scattered matorral, or grassland. Information fractal dimension declined as we moved from a dense to a discontinuous matorral, increasing as we moved to a more scattered matorral and a grassland. In all studied cases, the characteristic species of the natural vegetation declined in frequency and organization with grazing disturbance. Heliophyllous species and others with postrate or rosette twigs increased with grazing pressure, particularly in dense matorral. In the more degraded ecosystem, only species with well-adapted traits, e.g., buried buds or unpalatable qualities showed a clear increase with grazing. Indeed, the homogeneity of species distribution within the plant community declined monotonically with grazing impact. Conversely, the spatial organization of the characteristic plants of each community increased in the better-preserved areas, being also related to the sensitivity of the species to grazing impact. The degree of autocorrelation of plant spatial distribution at the species level and the information fractal dimension at the community level allow us to quantify the degree of degradation of natural communities and to determine the sensitivity of key species to disturbance.     

Modelling the effects of litter decomposition on tree diversity patterns

Current theories may not fully explain why latitudinal patterns of plant diversity differ between terrestrial and flooded ecosystems. Moreover, the co-occurrence of hyper diverse stands in lowland tierra firma (not inundated) forests and almost monospecific stands in mangroves and gallery riparian vegetation within the tropics remains enigmatic. Building on evidence from ecology and agriculture, we present a new model investigating the hypothesis that, besides the general positive feedback of plant growth by nutrients release, litter decomposition builds up an intra-specific negative feedback functionally linked with tree diversity. The model results were compared with extensive published data sets both across and within latitudinal zones. The model predicts correctly the biomass production and decomposition process, as well as the number of tree species, their relative abundance in all environmental conditions providing a novel, putative explanation also for the diversity variations observed within the tropics. The model demonstrates a possible mechanistic link between the carbon cycle and biodiversity patterns, which is interesting in the debate about advancing in the direction of a unifying ecosystem theory.     

Modelling directional spatial processes in ecological data

Distributions of species, animals or plants, terrestrial or aquatic, are influenced by numerous factors such as physical and biogeographical gradients. Dominant wind and current directions cause the appearance of gradients in physical conditions whereas biogeographical gradients can be the result of historical events (e.g. glaciations). No spatial modelling technique has been developed to this day that considers the direction of an asymmetric process controlling species distributions along a gradient or network. This paper presents a new method that can model species spatial distributions generated by a hypothesized asymmetric, directional physical process. This method is an eigenfunction-based spatial filtering technique that offers as much flexibility as the Moran's eigenvector maps (MEM) framework; it is called asymmetric eigenvector maps (AEM) modelling. Information needed to construct eigenfunctions through the AEM framework are the spatial coordinates of the sampling or experimental sites, a connexion diagram linking the sites to one another, prior information about the direction of the hypothesized asymmetric process influencing the response variable(s), and optionally, weights attached to the edges (links). To illustrate how this new method works, AEM is compared to MEM analysis through simulations and in the analysis of an ecological example where a known asymmetric forcing is present. The ecological example reanalyses the dietary habits of brook trout (Salvelinus fontinalis) sampled in 42 lakes of the Mastigouche Reserve, Québec.     

Diversity pattern and spatial scale: a study of a tropical rain forest of Malaysia

Scale is emerging as one of the critical problems in ecology because our perception of most ecological variables and processes depends upon the scale at which the variables are measured. A conclusion obtained at one scale may not be valid at another scale without sufficient knowledge of the scaling effect, which is also a source of misinterpretation for many ecological problems, such as the design of reserves in conservation biology.This paper attempts to study empirically how scaling may affect the spatial patterns of diversity (tree density, richness and Shannon diversity) that we may perceive in tropical forests, using as a test-case a 50 ha forest plot in Malaysia. The effect of scale on measurements of diversity patterns, the occurrence of rare species, the fractal dimension of diversity patterns, the spatial structure and the nearest-neighbour autocorrelation of diversity are addressed. The response of a variable to scale depends on the way it is measured and the way it is distributed in space.We conclude that, in general, the effect of scaling on measures of biological diversity is non-linear; heterogeneity increases with the size of the sampling units, and fine-scale information is lost at a broad scale. Our results should lead to a better understanding of how ecological variables and processes change over scale.     

Clustering species using a model of population dynamics and aggregation theory

The high species diversity of some ecosystems like tropical rainforests goes in pair with the scarcity of data for most species. This hinders the development of models that require enough data for fitting. The solution commonly adopted by modellers consists in grouping species to form more sizeable data sets. Classical methods for grouping species such as hierarchical cluster analysis do not take account of the variability of the species characteristics used for clustering. In this study a clustering method based on aggregation theory is presented. It takes account of the variability of species characteristics by searching for the grouping that minimizes the quadratic error (square bias plus variance) of some model’s prediction. This method allows one to check whether the gain in variance brought by data pooling compensate for the bias that it introduces. This method was applied to a data set on 94 tree species in a tropical rainforest in French Guiana, using a Usher matrix model to predict species dynamics. An optimal trade-off between bias and variance was found when grouping species. Grouping species appeared to decrease the quadratic error, except when the number of groups was very small. This clustering method yielded species groups similar to those of the hierarchical cluster analysis using Ward’s method when variance was small, that is when the number of groups was small.     

Effects of density-dependent dispersal behaviours on the speed and spatial patterns of range expansion in predator-prey metapopulations

Dispersal can strongly affect the spatiotemporal dynamics of a species (its spread, spatial distribution and persistence). We investigated how two dispersal behaviours, namely prey evasion (PE) and predator pursuit (PP), affect the dynamics of a predator-prey system. PE portrays the tendency of prey avoiding predators by dispersing into adjacent patches with fewer predators, while PP describes the tendency of predators to pursue the prey by moving into patches with more prey. Based on the Beddington predation model, a spatially explicit metapopulation model was built to incorporate PE and PP. Numerical simulations were run to investigate the effects of PE and PP on the rate of spread, spatial synchrony and the persistence of populations. Results show that both PE and PP can alter spatial synchrony although PP has a weaker desynchronising effect than PE. The predator-prey system without PE and PP expanded in circular waves. The effect of PE can push the prey to distribute in a circular ring front, whereas the effect of PP can change the circular waves to anisotropic expansion. Furthermore, weak PE and PP can accelerate the spread of prey while strong and disproportionate intensities slow down the range expansion. The effects of PE and PP further enhance the population size, break down the spatial synchrony and promote the persistence of populations.     

The effect of species response form on species distribution model prediction and inference

Ecological theory and current evidence support the validity of various species response curves according to a variety of environmental gradients. Various methods have been developed for building species distribution models but it is not well known how these methods perform under various assumptions about the form of the underlying species response. It is also not well known how spatial correlation in species occurrence affects model performance. These effects were investigated by applying an environmental envelope method (BIOCLIM) and three regression-based methods: logistic regression (LR), generalized additive modelling (GAM), and classification and regression tree (CART) to simulated species occurrence data. Each simulated species was constructed as a sum of responses with varying weights. Three basic species response curves were assumed: Gaussian (bell-shaped), Beta (skew) and linear. The two non-linear responses conform to standard ecological niche theory. All three responses were applied in turn to three simulated environmental variables, each with varying degrees of spatial autocorrelation. GAM produced the most consistent model performance over all forms of simulated species response. BIOCLIM and CART were inclined to underrate the performance of variables with a linear response. BIOCLIM was less sensitive to data density. LR was susceptible to model misspecification. The use of a linear function in LR underestimated the performance of variables with non-linear species response and contributed to increased spatial autocorrelation in model residuals. Omission of important environmental variables with non-linear species response also contributed to increased spatial autocorrelation in model residuals. Adding a spatial autocovariate term to the LR model (autologistic model) reduced the spatial autocorrelation and improved model performance, but did not correct the misidentification of the dominant environmental determinant. This is to be expected since the autologistic approach was designed primarily for prediction and not for inference. Given that various forms of species response to environmental determinants arise commonly in nature: (1) higher order functions should always be tested when applying LR in modelling species distribution; (2) spatial autocorrelation in species distribution model residuals can indicate that environmental determinants with non-linear response are missing from the model; and (3) deficiencies in LR model performance due to model misspecification can be addressed by adding a spatial autocovariate to the model, but care should be taken when interpreting the coefficients of the model parameters.     

Incorporating spatial autocorrelation into cellular automata model: An application to the dynamics of Chinese tamarisk (Tamarix chinensis Lour.)

Spatial autocorrelation (SAC) is frequently encountered in most spatial data in ecology. Cellular automata (CA) models have been widely used to simulate complex spatial phenomena. However, little has been done to examine the impact of incorporating SAC into CA models. Using image-derived maps of Chinese tamarisk (Tamarix chinensis Lour.), CA models based on ordinary logistic regression (OLCA model) and autologistic regression (ALCA model) were developed to simulate landscape dynamics of T. chinensis. In this study, significant positive SAC was detected in residuals of ordinary logistic models, whereas non-significant SAC was found in autologistic models. All autologistic models obtained lower Akaike's information criterion corrected for small sample size (AICc) values than the best ordinary logistic models. Although the performance of ALCA models only satisfied the minimum requirement, ALCA models showed considerable improvement upon OLCA models. Our results suggested that the incorporation of the autocovariate term not only accounted for SAC in model residuals but also provided more accurate estimates of regression coefficients. The study also found that the neglect of SAC might affect the statistical inference on underlying mechanisms driving landscape changes and obtain false ecological conclusions and management recommendations. The ALCA model is statistically sound when coping with spatially structured data, and the adoption of the ALCA model in future landscape transition simulations may provide more precise probability maps on landscape transition, better model performance and more reasonable mechanisms that are responsible for landscape changes.     

Natural and anthropogenic influences on the diversity structure of reef fish communities in the Tuamotu Archipelago (French Polynesia)

Despite the rapid rate of human-induced species losses, the relative influence of natural and anthropogenic factors on the functional diversity of species assemblages remains unknown for most ecosystems. A model was previously developed to predict the diversity structure of coral reef fish assemblages in 10 atolls of low human pressure and contrasting morphology of the Tuamotu Archipelago (French Polynesia). This existing model predicted smoothed histograms (spectra) of species richness according to size classes, diet classes and life-history classes of fish assemblages using a combination of environmental characteristics at different spatial scales. The present study applied the model to Tikehau, another atoll of the same archipelago where commercial fishing is practiced and where the same sampling strategy was reproduced. Significant differences appeared between predicted and observed species richness in several size, diet and life-history classes of fish assemblages in Tikehau. Two parameters which were not accounted for in the initial model, i.e. fishing pressure and atoll position within the archipelago, explained together 63% of variance in model residuals, >60% being explained by fishing pressure only. The respective effects of fishing and atoll position on the diversity of coral reef fish assemblages are discussed, with the potential of such modelling approach to assess the relative importance of factors affecting functional diversity within communities.     

Relationships between Plant and Animal Species Richness at a Regional Scale in China

Abstract:  Important questions in conservation biology and ecology include whether species diversities of different groups of organisms are correlated and, in particular, whether plant diversity influences animal diversity. I used correlation and partial regression analyses to examine the relationships between species richness of vascular plants and four major groups of terrestrial vertebrates (mammals, amphibians, reptiles, and birds) in 28 provinces in China. Species richness data were obtained from the literature. Environmental variables included normalized difference vegetation index, mean January temperature, mean annual temperature, annual precipitation, May through August precipitation, actual evapotranspiration, potential evapotranspiration, and elevation range. Species richness was strongly and positively correlated among the five groups of organisms. Plant richness was correlated with animal richness more strongly than the richness of different animal groups correlated with each other except for reptile richness, which had a slightly higher correlation with amphibian richness than with plant richness. Plant richness uniquely explained 41 times more variance in the species richness of the four vertebrate groups combined than environmental variables uniquely did, suggesting that plant richness influences terrestrial vertebrate richness at the regional scale examined. Because of strong correlations between the diversity of vascular plants and vertebrates, the diversity of vascular plants may be used as a surrogate for the diversity of terrestrial animals in China. My results have implications for selection of areas to be protected at both regional and local scales.     

Nonparametric spatial covariance functions: Estimation and testing

Spatial autocorrelation techniques are commonly used to describe genetic and ecological patterns. To improve statistical inference about spatial covariance, we propose a continuous nonparametric estimator of the covariance function in place of the spatial correlogram. The spline correlogram is an adaptation of a recent development in spatial statistics and is a generalization of the commonly used correlogram. We propose a bootstrap algorithm to erect a confidence envelope around the entire covariance function. The meaning of this envelope is discussed. Not all functions that can be drawn inside the envelope are candidate covariance functions, as they may not be positive semidefinite. However, covariance functions that do not fit, are not supported by the data. A direct estimate of the L₀ spatial correlation length with associated confidence interval is offered and its interpretation is discussed. The spline correlogram is found to have high precision when applied to synthetic data. For illustration, the method is applied to electrophoretic data of an alpine grass (Poa alpina).     

The role of local and landscape level measures of greenness in modelling boreal plant species richness

Measurements of primary productivity and its heterogeneity based on satellite images can provide useful estimates of species richness and distribution patterns. However, species richness at a given site may depend not only on local habitat quality and productivity but also on the characteristics of the surrounding landscape. In this study we investigated whether the predictions of species richness of plant families in northern boreal landscape in Finland can be improved by incorporating greenness information from the surrounding landscape, as derived from remotely sensed data (mean, maximum, standard deviation and range values of NDVI derived from Landsat ETM), into local greenness models. Using plant species richness data of 28 plant families from 440 grid cells of 25 ha in size, generalized additive models (GAMs) were fitted into three different sets of explanatory variables: (1) local greenness only, (2) landscape greenness only, and (3) combined local and landscape greenness. The derived richness–greenness relationships were mainly unimodal or positively increasing but varied between different plant families, and depended also on whether greenness was measured as mean or maximum greenness. Incorporation of landscape level greenness variables improved significantly both the explanatory power and cross-validation statistics of the models including only local greenness variables. Landscape greenness information derived from remote sensing data integrated with local information has thus the potentiality to improve predictive assessments of species richness over extensive and inaccessible areas, especially in high-latitude landscapes. Overall, the significant relationship between plants and surrounding landscape quality detected here suggests that landscape factors should be considered in preserving species richness of boreal environments, as well as in conservation planning for biodiversity in other environments.     

Vegetation zonation and management in the Damietta estuary of the River Nile

The zonation of the vegetation along the saline and freshwater marshes of the Damietta estuary of the Nile River was studied from near the river mouth to 20 km upstream. Downstream, the estuarine water is almost stagnant and highly saline with high concentrations of nutrients. This makes the habitat unsuitable for euhydrophytes. Upstream, the vegetation consists mostly of freshwater macrophytes. 75 sampling plots were established in representative stands of the upshore and upstream vegetation zones. Classification and ordination of the data revealed seven vegetation types, indicated A—G. The dominant species of the saline marshes werePhragmites australis, Tamarix nilotica andArthrocnemum macrostachyum (A),Zygophyllum aegyptium andPolygonum equisetiforme (B),Cynodon dactylon andSuaeda vera (C). In the freshwater marshes the dominants were:Ludwigia stolonifera, Persicaria lapathifolia (D),Typha domingensis (E),Eichhornia crassipes (F) andCeratophyllum demersum (G). The first axis of the ordination axis obtained with Detrended Correspondence Analysis can be associated with the upstream gradient. It separates the salt marsh vegetation groups from those of the freshwater marshes. Plant species richness increased upshore along both saline and freshwater marshes. The concentration of dominance increased upstream. Some aspects of proper management of estuarine vegetation are mentioned.     

Synthesis and spatial dynamics of socio-economic metabolism and land use change of Taipei Metropolitan Region

Ever since the concept of metabolism was extended from biological science by social scientists to analyze human systems, socio-economic metabolism has been extensively applied to explore resource consumption, asset accumulation, waste emissions, and complex processes of land use change in a socio-economic system. Current research in socio-economic metabolism and land use change has used accounting approaches for macroscopic comparisons of countries and regions. However, socio-economic metabolism has seldom been applied to the analysis of land use change. To simulate the spatial-temporal dynamics of socio-economic metabolism and land use change, this study adopts a spatial system modeling method to develop a Socio-Economic Metabolism and Land Use Change (SEMLUC) model for the Taipei Metropolitan Region. The simulation results illustrate that the Taipei Metropolitan Region is highly dependent on inflows of non-renewable energy and exhibits a spatial hierarchy of non-renewable energy consumption centering on Taipei's Main station. Additionally, urban assets provide feedback to natural and agricultural systems to extract additional resource inflows which, driven by the maximum power principle, accelerate the convergence of energy flows toward urban assets. Accumulating urban assets also facilitates inflows of non-renewable material to nearby cells thereby enhancing land use conversion to urban areas. This work also demonstrates the capability of ArcGIS software in simulating socio-economic metabolism and land use change in an urban system.     

Chaos and pattern formation in a spatial tritrophic food chain

The model of Hastings and Powell describes a tritrophic food chain that exhibits chaotic dynamics. The model assumes that the populations are homogeneously mixed, so that the probability that any two individuals interact is uniform and space can be ignored. In this paper we propose a spatial version of the Hastings and Powell model in which predators seek their preys only in a finite neighborhood of their home location, breaking the mixing hypothesis. Treating both space and time as discrete variables we derive a set of coupled equations that describe the evolution of the populations at each site of the spatial domain. We show that the introduction of local predator–prey interactions result in qualitatively distinct dynamics of predator and prey populations. The evolution equations for the predators involve averages over the local density of preys, whereas the equations for the preys involve double averages, where the local density of both preys and predators appear. Our numerical simulations show that local predation also leads to spontaneous pattern formation and to qualitative changes in the global dynamics of the system. In particular, depending on the size of the predation neighborhoods, the chaotic strange attractor present in the original model of Hastings and Powell can be replaced by a stable fixed point or by an attractor of simpler topology.     

Ecological responses to reductions in freshwater supply and quality in South Africa’s estuaries: lessons for management and conservation

Fresh water, a fundamental element of all estuarine ecosystems, is South Africa’s most limited natural resource. Recent projections indicate that by the year 2020 the country will be utilizing all its exploitable freshwater sources. Steeply increasing demands by a rapidly growing population on this limited commodity have already resulted in a severe reduction of water supplies to natural users such as estuaries — this trend is predicted to increase in the future. Concurrent with excessive water abstraction, poor land husbandry (e.g. soil erosion) in many catchment basins and pollution (e.g. salinization) in return flows have led to a serious deterioration in water quality. In contrast, a review of estuarine responses to varying flow regimes stresses the strong dependence of local systems on riverine fresh water inputs of adequate quantity and quality. Freshwater dependence is i.a. expressed in: flooding events that scour accumulated sediments, riverine nutrient input to drive estuarine phyto- and zooplankton production, axial salinity gradients that increase habitat and species diversity, and maintenance of open tidal inlets that prevent salinity and temperature extremes and facilitate larval exchange, fish migrations and tidal flushing of salt marshes. Thus, estuarine conservation will have to encompass management of rivers and watersheds and play an increasingly political role in decision processes concerning water allocations among ‘human’ and ‘natural’ users.     

Applications of artificial neural networks for patterning and predicting aquatic insect species richness in running waters

Two artificial neural networks (ANNs), unsupervised and supervised learning algorithms, were applied to suggest practical approaches for the analysis of ecological data. Four major aquatic insect orders (Ephemeroptera, Plecoptera, Trichoptera, and Coleoptera, i.e. EPTC), and four environmental variables (elevation, stream order, distance from the source, and water temperature) were used to implement the models. The data were collected and measured at 155 sampling sites on streams of the Adour–Garonne drainage basin (South-western France). The modelling procedure was carried out following two steps. First, a self-organizing map (SOM), an unsupervised ANN, was applied to classify sampling sites using EPTC richness. Second, a backpropagation algorithm (BP), a supervised ANN, was applied to predict EPTC richness using a set of four environmental variables. The trained SOM classified sampling sites according to a gradient of EPTC richness, and the groups obtained corresponded to geographic regions of the drainage basin and characteristics of their environmental variables. The SOM showed its convenience to analyze relationships among sampling sites, biological attributes, and environmental variables. After accounting for the relationships in data sets, the BP used to predict the EPTC richness with a set of four environmental variables showed a high accuracy (r=0.91 and r=0.61 for training and test data sets respectively). The prediction of EPTC richness is thus a valuable tool to assess disturbances in given areas: by knowing what the EPTC richness should be, we can determine the degree to which disturbances have altered it. The results suggested that methodologies successively using two different neural networks are helpful to understand ecological data through ordination first, and then to predict target variables.