Download
Cite as:
Meyer, H. (2010): <b>Predicting land use/land cover changes in a tropical mountain forest of Ecuador for future SVAT prediction. A modelling approach and result validation based on GIS and remotely sensed data </b> Marburg University, <i>bachelor thesis</i>

Resource Description

Title: Predicting land use/land cover changes in a tropical mountain forest of Ecuador for future SVAT prediction. A modelling approach and result validation based on GIS and remotely sensed data
Short Name: Predicting land use/land cover changes
FOR816dw ID: 1035
Publication Date: 2010-09-03
License and Usage Rights:
Resource Owner(s):
Individual: Hanna Meyer
Contact:
Abstract:
Soil-vegetation-atmosphere transfer (SVAT) is to be predicted for 2050/2100 for a study area <br/> in the southern Ecuadorian Andes. SVAT models require information on land use/ land cover <br/> (LUC) as lower boundary conditions. Since the study area suffers from high deforestation <br/> rates, LUC cannot be assumed as staying constant with time. A spatially explicit land use/land <br/> cover change (LUCC) model is therefore needed for future SVAT prediction. <br/> The numbers of approaches of LUCC modelling are numerous. Difficulties are due to <br/> complex interactions of social and biophysical drivers of change. <br/> In this study a model of LUCC was built using information of past changes derived by <br/> remotely sensed data. Special focus was on forest development patterns. A training period of <br/> 14 years between 1987 and 2001 was chosen. Two LUC classifications were accomplished to <br/> Landsat data of the start and end date of this period. A change detection of the training period <br/> provided the basis for predictive LUCC modelling. Potential drivers for LUCC were applied <br/> to the model as GIS layers. The modelling procedure consisted of a combination of Markov <br/> chain analysis (MCA) for quantitative modelling and multi-layer perceptron (MLP) for <br/> revealing potential locations of change. A multi-objective land allocation (MOLA) served as <br/> final integration step. 14 LUC transitions were considered in the modelling procedure. <br/> Unconsidered LUC classes were assumed to stay constant in the future. The model results <br/> were maps of LUC for 2006, 2010 and afterwards for every 10 years up to 2100. An internal <br/> validation was performed with the training data. The results of the prediction were validated <br/> by comparing the model output of 2006 to an ASTER LUC classification of the same time. <br/> The validation methodology comprised crisp and fuzzy map comparison using Kappa <br/> statistics. <br/> The study area featured a deforestation of 13.61% in the training period. The model was able to <br/> explain deforestation in the training period 51% better than just by chance. The location of <br/> predicted deforestation reached a better than chance agreement of 30%. Predicted quantities of <br/> deforestation were 59% conforming with the reference. The validation of the prediction <br/> indicated the difficulty of modelling human impact on the ecosystem. Prospects and limitations <br/> of the model were identified with suggestions for future research tasks. The results of this <br/> study are assumed to present a good groundwork for future SVAT models.
Keywords:
| Ecuador | remote sensing | artificial neuronal network | deforestation | fuzzy map comparison | markov chain analysis | models of land-use/land-cover change |
Literature type specific fields:
THESIS
Degree: bachelor
Degree Institution: Marburg University
Total Pages: 68
Metadata Provider:
Individual: Bernhard Runzheimer
Contact:
Online Distribution:
Download File: http://www.lcrs.de/publications.do?citid=1035


Quick search

  • Publications:
  • Datasets: