Mohammad Mansourmoghaddam; Iman Rousta; Mohammad Sadegh Zamani; Mohammad Hossein Mokhtari; Mohammad Karimi Firozjaei; Seyed Kazem Alavipanah
Abstract
The effect of urban thermal islands due to intersections with major environmental challenges of the 21st century is one of the most important studies on environmental phenomena, and in this regard, the study of the land surface temperature gives a clear perspective of the thermal islands in cities, which, ...
Read More
The effect of urban thermal islands due to intersections with major environmental challenges of the 21st century is one of the most important studies on environmental phenomena, and in this regard, the study of the land surface temperature gives a clear perspective of the thermal islands in cities, which, according to the warm and dry climate of Yazd, examines the status and factors affecting the land surface temperature in this city seem to be necessary. This research, using the spectrally and spatially fused image of Landsat-8, for August 2020, and using machine learning algorithms, tries to model the changes in land surface temperature by calculating different parameters related to urban land perspective. Based on the results of this study, the spectral-spatial fusion of Landsat-8 with Sentinel-2 by Pan sharpening, increased 10.7% of the overall accuracy and 16.5% of the Kappa coefficient in the classification of this image. The study also showed that most neighboring parameters associated with land cover are ranked 1 to 11 of influencing the land surface temperature of Yazd city. In this area, the proximity to bare lands in the radius of 100, 50, and 150 meters ranked 1 to 3 of the most important parameters affecting the land surface temperature respectively. This study showed that the change in land cover arrangement could affect the land surface temperature and changing the bare lands to the built-up areas, up to 1.1°C, to vegetation, up to 2.1°C, and changing 30% of bare land to vegetation, up to 1.6°C can reduce the average land surface temperature in Yazd. Also, this study showed that two different models of vegetation simulation in Yazd city showed that the "land-sparing " model could reduce the average land surface temperature in Yazd by 1.3° and the "land-sharing" model by 1.4°C.
Ahmad Malek Nejad Yazdi; Hassan Ghassemian; Vahid Esavi
Volume 7, Issue 3 , November 2015, , Pages 65-82
Abstract
Most of common classification algorithms in remote sensing are based on spectral characteristics of the pixels. These approaches result in ignorance of many precious information, such as texture, in the classification process. The urban environment has an inhomogeneous texture, which makes land covers ...
Read More
Most of common classification algorithms in remote sensing are based on spectral characteristics of the pixels. These approaches result in ignorance of many precious information, such as texture, in the classification process. The urban environment has an inhomogeneous texture, which makes land covers detection a complicated process. In this study, use of texture extracted from the panchromatic image of ALI detector for improvement of Hyperion image's classification accuracy in urban regions was analyzed. Classification carried out using Random Forests method and in five different scenarios. These scenarios included: 1- Classification of the fused image by CNT method (Without Incluion of Texture Information), The other four scenarios covered the classification used by simultaneous use of texture extracted by Gray Level Co-occurrence Matrix »GLCM« in 4 different window sizes: 3,5,7,9 and fused image. Results of these analyses revealed that use of texture information as a useful parameter can lead to an enormous improvement in classification accuracy. Our findings showed that use of texture resulted in an increase in overall accuracy by around 10 percent from 80.47 to 90.74 percent . Many of land use/land covers such as roads, residential and industrial areas also experienced the improvement in producer and user accuracies. OOB error as an essential random forests parameter inclined as far as 11 percent from 19.86 to 8.87 percent. Moreover, the GLCM feature vectors such as mean and contrast achieved high ranks in importance evaluation in random forests classification. Increase of window size also led to a rise of classification accuracy and the window size 9 gained the highest accuracy accordingly.