Presentation is loading. Please wait.

Presentation is loading. Please wait.

Spatial Inference of Vegetation Vulnerability for the Ecological Economical Zoning of Minas Gerais Luis M. T. Carvalho 1 Moisés S. Ribeiro 2, Luciano T.

Similar presentations


Presentation on theme: "Spatial Inference of Vegetation Vulnerability for the Ecological Economical Zoning of Minas Gerais Luis M. T. Carvalho 1 Moisés S. Ribeiro 2, Luciano T."— Presentation transcript:

1 Spatial Inference of Vegetation Vulnerability for the Ecological Economical Zoning of Minas Gerais Luis M. T. Carvalho 1 Moisés S. Ribeiro 2, Luciano T. de Oliveira 1 Thomaz C. A. Oliveira 1, Julio N. Louzada 3 José R. S. Scolforo 1, Antonio D. Oliveira 1 1 Departamento de Ciências Florestais 2 Departamento de Engenharia 3 Departamento de Biologia

2 Ecological Economical Zoning of Minas Gerais Introduction ZEE Zones subject to a certain model of use according to degrees of natural vulnerability and social potentiality. ZEE-MG implemented by the Government of Minas Gerais to support policy making by means of a statewide diagnosis of economical, social, ecological and biophysical sustainability. NATURAL VULNERABILITY the capacity of resisting or recovering from impacts caused by human activities.

3 Ecological Economical Zoning of Minas Gerais Introduction ZEE/MG Vulnerability Biotic Flora Fauna Physical Soils Erosion Water Climate Potentiality Institutional Productive Natural Human

4 Ecological Economical Zoning of Minas Gerais Objectives to investigate alternative methods of spatial inference, viz. fuzzy logic and neural networks for generating maps of vegetation vulnerability for the State of Minas Gerais, and to evaluate their suitability to be used instead of weighted overlay.

5 Ecological Economical Zoning of Minas Gerais Study site and data sets The study area comprises the whole State of Minas Gerais. Data compiled and included in the ZEE-MG were structured in a GIS using the raster data model with a spatial resolution of 270x270m. Indicators of vegetation vulnerability were derived from a 30x30m resolution land cover map (Scolforo & Carvalho, 2006) and from priority conservation areas (Drummond et al., 2005)

6 Ecological Economical Zoning of Minas Gerais Flora ConservationHeterogeneityRelevance Conservation Priority Indicators of Vegetation Vulnerability

7 Ecological Economical Zoning of Minas Gerais 30m 6 : Regional total 270m Rocky Field Cerrado stricto sensu Semideciduous Forests Indicators 1 to 9: Regional Relevance

8 Ecological Economical Zoning of Minas Gerais Grass landRocky grass land Open savanna Savanna stricto sensuSavanna woodlandSavanna palm land Deciduous forestSemi deciduous forestEvergreen forest

9 Ecological Economical Zoning of Minas Gerais 30m 11 270m Native Vegetation Others Indicator 10: Conservation Degree

10 Ecological Economical Zoning of Minas Gerais

11 30m 3 270m Campo rupestre Cerrado stricto sensu Floresta Estacional Semidecidual Indicator 11: Spatial Heterogeneity

12 Ecological Economical Zoning of Minas Gerais

13 Conservation Priority classesVulnerability classes NoneVery low CorridorLow PotentialMedium High Very high, Extreme and SpecialVery high Indicator 12: Conservation Priority

14 Ecological Economical Zoning of Minas Gerais

15 Methods Albers Conic Equal Area Projection (datum SAD-69). Spatial inference using weighted overlay, fuzzy logic, and neural networks. Vulnerability represented by the models outputs were classified as (1) Very low, (2) Low, (3) Medium, (4) High, and (5) Very high.

16 Ecological Economical Zoning of Minas Gerais Weighted Overlay Simple and straightforward technique. Weights represent the importance of each variable, as well as the importance of each classe according to a given objective. Allows the inclusion of expert knowledge. 1 2 3 11 1 1 1 1 1 2 2 22 3 3 3 3 3 2 2 2 2 2 2 2 2 Peso = 75%Peso = 25% + =

17 Ecological Economical Zoning of Minas Gerais IndicatorIndicator weightClassClass weight Regional relevance8Very low1 Low6 Medium10 High12 Very high12 Degree of conservation12Very low1 Low6 Medium10 High12 Very high12 Spatial heterogeneity4Very low1 Low6 Medium10 High12 Very high12 Conservation priority12Very low1 Low2 Medium6 High12 Very high12

18 Ecological Economical Zoning of Minas Gerais Fuzzy Logic Input data values are rescaled using the assumption of continuous membership values (i.e., fuzzyfication). Environmental data are normally modeled using the symmetric fuzzy models as generated by Kandel (1986):

19 Ecological Economical Zoning of Minas Gerais Fuzzy Logic Fuzzy operators allow the combination of layers containing fuzzy values through a process of fuzzy overlay. Operator Fuzzy Gamma:

20 Ecological Economical Zoning of Minas Gerais Fuzzy Logic Operator Fuzzy Convex Sum. If A 1,.....,A k are subsets of X, and w 1,......,w k are non negative weights then the convex combination of A 1,....,A k is:

21 Ecological Economical Zoning of Minas Gerais Neural Networks Clustering algorithms of the machine learning field. Models of biological neurons and networks. Unsupervised clustering Self Organizing Maps (with and without k-means) Fuzzy ArtMap

22 Ecological Economical Zoning of Minas Gerais Neural Networks ParameterSOM (without k-means)SOM (with k-means) Input layer neurons12 Output layer neurons936 Initial neighborhood radius5.249.49 Minimum learning rate0.5 Maximum learning rate11 Iterations874,080628,992 Quantization Error0.02410.0187 SOM neural network parameters:

23 Ecological Economical Zoning of Minas Gerais Neural Networks ParameterFuzzy ArtMap F1 layer neurons24 F2 layer neurons6 Choice parameter0.01 Learning rate1 Vigilance parameter0.95 Iterations48,923 Fuzzy ArtMap neural network parameters:

24 Ecological Economical Zoning of Minas Gerais Results and Discussion Weighted overlay x Fuzzy logic:

25 Ecological Economical Zoning of Minas Gerais Results and Discussion Weighted overlay x Neural networks:

26 Ecological Economical Zoning of Minas Gerais

27 Conclusions and Future Studies The evaluated methods are less intuitive, dependent on a number of arbitrary parameters, demand more computational power, and do not provide significant improvements when compared to the map produced using weighted overlay, Fuzzy logic seems to be a promising approach and further research will be carried out in order to test different fuzzification methods, as well as different fuzzy operators, Neural networks will be disregarded due to the difficulties in setting the necessary parameters, and A framework to collect field data will be developed to provide a robust base to carry out vulnerability map comparisons

28 Thank You ! Contact: passarinho@ufla.br


Download ppt "Spatial Inference of Vegetation Vulnerability for the Ecological Economical Zoning of Minas Gerais Luis M. T. Carvalho 1 Moisés S. Ribeiro 2, Luciano T."

Similar presentations


Ads by Google