|
Determining Effective Factors on Land Surface Temperature of Tehran Using LANDSAT Images And Integrating Geographically Weighted Regression With Genetic Algorithm
|
Amer Karimi   , Parham Pahlavani * , Behnaz Bigdeli |
| University of Tehran |
|
|
Abstract: (3335 Views) |
| Due to urbanization and changes in the urban thermal environment and since the land surface temperature (LST) in urban areas are a few degrees higher than in surrounding non-urbanized areas, identifying spatial factors affecting on LST in urban areas is very important. Hence, by identifying these factors, preventing this phenomenon become possible using general education, inserting rules and also retaining efficient management policies and more monitoring to counter the stimulating factors of increasing land surface temperature. The goal of this research is to identify the effective factors on land surface temperature in Tehran. In this regard, a geographically weighted regression (GWR) was used to identify the effective factors and a genetic algorithm (GA) was employed to select the best combination of these factors. The recommended combination method is a suitable method for spatial regression issues, because it is compatible with two unique properties of spatial data, i.e. the spatial autocorrelation and spatial non-stationarity. In this study, land surface temperature data in Tehran was obtained on August 18, 2014 and August 21, 2015 using Landsat 8 satellite imagery, and was used in two methods of Gaussian and Tri-cubic weighting in GWR. The values of 1-R2 by using the Gaussian kernel were equal to 0.21752 and 0.23448, as well as by using the the Tri-cubic kernel were equal to 0.10452 and 0.14494 for August 18, 2014 and August 21, 2015, respectively. The results showed that the effects of factors such as land use, construction density, and distance from roads on land surface temperature in Tehran were more than other factors. Also, using the tri-cubic kernel for GWR provided more accurate results. |
|
| Keywords: Land Surface Temperature, Geographic Weighted Regression, Genetic Algorithm. |
|
|
Full-Text [PDF 2314 kb]
(1543 Downloads)
|
Type of Study: Research |
Subject:
GIS
Received: 2018/04/7 | Accepted: 2018/06/30 | Published: 2019/12/21
|
|
|
|
|
|
|
| Send email to the article author |
|
|
