Journal of Environmental Biology

NDVI indicated changes in vegetation and their relations to climatic comfort factors in Demre-Ak?ay Sub basin, Turkey

 ????????????????????

A. Benliay¹, T. Yilmaz¹*, R. Olgun² and M.K. Ak³ ????? 

¹Akdeniz University Faculty of Architecture, Department of Landscape Architecture, Antalya, 07070, Turkey

²Akdeniz University, Serik G-S. Sural Vocational School of Higher Education, Department of Park and Horticulture, Antalya, 07500, Turkey

³D?zce University Faculty of Forestry Department of Landscape Architecture, D?zce, 81620, Turkey

*Corresponding Author Email : tahsin@akdeniz.edu.tr

Paper received: 02.04.2019 ?????? ???????????????????????????????????????Revised received: 20.09.2019 ???????????? ???????????????????????????????Accepted: 05.12.2019

Abstract

Aim: The aim of this study was to evaluate the relationship between vegetation change obtained by NDVI analysis and climatic comfort factors by using an artificial neural network model.

Methodology: Fethiye, Elmalı, Kaş, Finike, Kemer, Korkuteli, Antalya, Tefenni and Kale climatic station's temperature, humidity and wind data were evaluated during this study. Moreover, four Landsat TM satellite images (2006 - 2016) were used as 2 for each year to detect Normalized Difference Vegetation Index (NDVI) values. Climatic comfort maps were created by ArcMap10.3 software using? Kriging Method. Difference maps for climatic comfort and NDVI values of satellite images between 2006 - 2016 were created. At the pixel scale, these data were used for teaching artificial neural network model by Neural Designer software in randomly selected 500 points. All NDVI values (-1 - 1) and possible vegetation changes (-1 - 1) that could occurs in the study area were entered as input to the trained neural network model and the possible values of climate comfort change values were determined.

Results: Most significant 2006 NDVI average and mean values were observed at 0.7, 0.6 and 0.5. In the value of NDVI in 2016 forecast, climatic comfort values could get higher in an area which can change into a mediocre or low vegetation value. The maximum average and mean values were 1.0, 0.9 and 0.8. This forecast shows that there could be positive and negative major changes between the climatic comfort values that may occur.

Interpretation: Artificial neural networks are the recent ways for such studies and are rapidly developing. Understanding artificial neural networks boundaries and advantages will allow for more efficient modeling tools. As in every part of life, the use of artificial neural networks is expected to increase day by day in landscape planning and design studies.

Keywords: Artificial Neural Networks, NDVI, Climatic comfort

Copyright ? 2020 Triveni Enterprises. All rights reserved. No part of the Journal can be reproduced in any form without prior permission. Responsibility regarding the authenticity of the data, and the acceptability of the conclusions enforced or derived, rest completely with the author(s).