Catálogo de publicaciones - libros

Heterogeneous and imprecise ecological data and vague expert knowledge can be integrated more effectively using fuzzy approach. Fuzzy logic provides the means to combine numerical data and linguistic statements and to process both of them in one simulation step. Fuzzy sets with no sharply defined boundaries reflect better the continuous character of nature. The number of applications of fuzzy sets and fuzzy logic in ecological modelling and data analysis is constantly growing.

There also are an increasing number of applications of hybrid systems which combine the fuzzy techniques with other techniques, e.g. probabilistic approach, linear programming, neural networks, cellular automata or GIS technique. An increasing interest in the development of fuzzy expert systems for environmental management and engineering can also be expected.

Representing qualitative ecological knowledge is of great interest for ecological modelling. QR provides means to build conceptual models and to make qualitative knowledge explicit, organized and manageable by means of symbolic computing. This chapter discusses the main characteristics of QR using well-known examples. It also shows how this technology can be used to represent ecological knowledge and an overview is given of ecological applications that have already been developed using QR. Ongoing QR research focuses on improving QR tools and technology. An additional goal is to integrate quantitative knowledge with qualitative knowledge. In a collaborative work with ecologists, particularly in the construction of reusable knowledge libraries, it is possible to foresee a wider range of applications to ecological modelling and better ways of dealing with the complexity of ecological and environmental systems. But most of all, the deployment of QR technology for ecological purposes should become an important goal in itself because, as pointed out by (Rykiel 1989), “many questions of interest in ecology can be answered in terms of ‘better or worse’, ‘more or less’, ‘sooner or later’, etc.” and when quantitative methods are inadequate or lacking, it is still possible to make estimates, predictions, and decisions with scientific support.

We presented in this paper some ways to use SOMs for visualizing an abundance dataset. Due to its extreme adaptability, the SOM can have a number of variants that make it a very convenient tool for studying the ecological communities.

The SOM enhanced by the U-matrix method is an effective clustering method including techniques to display the species abundance or abiotic variables.

The SOM is a promising approach and completes the results obtained by classical methods of classification.

The results obtained with both methods match closely with the previous results. The predictive power of ANNs has often been demonstrated, and this new study puts to the fore their explicative power which is very interesting in ecological research.

This article paves the way forward for broad research concerning the contribution of the input variables in ANN’s, firstly by the use of other databases to test the methods, secondly by the discovery of new methods and finally by the investigation of other existing methods.

The previous sections have described some of the basic applications of evolutionary computation techniques to various aspects of ecological modelling. Although there are many areas that have not been given adequate attention, it is clear that the use of difference and differential equations, the modelling of cooperation and community structure, the use of space and spatial behavior and the construction of hierarchical organization are areas where evolutionary computation techniques match well with ecological modelling. Models from large-scale behavior of communities, through to the way in which genetic material evolves in a species, can be studied using these types of models. The future is extremely positive for these evolutionary techniques to support and extend the current understanding of ecological processes and functions.

The software LAGRAMGE for computational assemblage and adaptation of ODE by using the expert knowledge and measured data has been applied for the simulation of chl- in Lake Kasumigaura. As a result two types of chl- models were discovered: (1) chl- equations without considering zooplankton grazing assembled and trained by data of consecutive years were data of the last year was used for testing, and (2) chl- equations considering zooplankton grazing assembled and trained by data of the years 1986 to 1989. The test results of the different models have demonstrated that LAGRAMGE can discover ODE that allow to simulate chl- in Lake Kasumigaura for a variety of years. However the generalisation of discovered equations for unseen data of consecutive years was unsatisfactory, and the accuracy of calculated trajectories with regards to timing and magnitudes of peak events was moderate. The results have highlighted the importance of nutrients as growth limiting factors, and the need for considering functional algae groups in order to appropriately represent their selective grazing by zooplankton.

A hybrid evolutionary algorithm (HEA) has been developed to discover predictive rule sets in complex ecological data. It has been designed to evolve the structure of rule sets by using genetic programming and to optimise the random parameters in the rule sets by means of a genetic algorithm.

HEA was successfully applied to long-term monitoring data of the shallow, eutrophic Lake Kasumigaura (Japan) and the deep, mesotrophic Lake Soyang (Korea). The results have demonstrated that HEA is able to discover rule sets, which can forecast for 7-days-ahead seasonal abundances of blue-green algae and diatom populations in the two lakes with relatively high accuracy but are also explanatory for relationships between physical, chemical variables and the abundances of algal populations. The explanations and the sensitivity analysis for the best rule sets correspond well with theoretical hypotheses and experimental findings in previous studies.

The software LAGRAMGE for computational assemblage and adaptation of ODE by using the expert knowledge and measured data has been applied for the simulation of chl- in Lake Kasumigaura. As a result two types of chl- models were discovered: (1) chl- equations without considering zooplankton grazing assembled and trained by data of consecutive years were data of the last year was used for testing, and (2) chl- equations considering zooplankton grazing assembled and trained by data of the years 1986 to 1989. The test results of the different models have demonstrated that LAGRAMGE can discover ODE that allow to simulate chl- in Lake Kasumigaura for a variety of years. However the generalisation of discovered equations for unseen data of consecutive years was unsatisfactory, and the accuracy of calculated trajectories with regards to timing and magnitudes of peak events was moderate. The results have highlighted the importance of nutrients as growth limiting factors, and the need for considering functional algae groups in order to appropriately represent their selective grazing by zooplankton.

We presented in this paper some ways to use SOMs for visualizing an abundance dataset. Due to its extreme adaptability, the SOM can have a number of variants that make it a very convenient tool for studying the ecological communities.

The SOM enhanced by the U-matrix method is an effective clustering method including techniques to display the species abundance or abiotic variables.

The SOM is a promising approach and completes the results obtained by classical methods of classification.