Nilgun Guneroglu

Remote sensing of tea plantations using an SVM classifier and pattern-based accuracy assessment technique

Tea (Camellia sp.) and its plantation are very important on a worldwide scale as it is the second-most consumed beverage after water. Therefore, it becomes necessary to map the widely distributed tea plantations under various geographies and conditions. Remote-sensing techniques are effective tools to map and monitor the impact of tea plantation on land-use/land-cover (LULC). Remote sensing of tea plantations suffers from spectral mixing as these plantation areas are generally surrounded by similar types of green vegetation such as orchards and bushes. This problem is mainly tied to planting style, topography, and spectral characteristics of tea plantations, and the side effects are observed as low classification accuracies after the classification process. In this study, to overcome this problem, a three-step approach was proposed and implemented on a test area with high slope. As a first step, spectral and multi-scale textural features based on Gabor filters were extracted from high resolution multispectral digital aerial images. Similarly, based on the wavelength range of the sensor, a modified normalized difference vegetation index (MNDVI) was applied to distinguish the green vegetation cover from other LULCs. The second step involves the classification of multidimensional textural and spectral feature combinations using a support vector machine (SVM) algorithm. As a final step, two different techniques were applied for evaluating classification accuracy. The first one is a traditional site-specific accuracy assessment based on a confusion matrix calculating statistical metrics for different feature combinations. The overall accuracy and kappa values were calculated as 93.68% and 0.92, 93.82% and 0.92, and 97.40% and 0.97 for LULC maps produced by red, green, and blue (RGB), RGB + MNDVI, and RGB + MNDVI + Gabor features, respectively. The second accuracy assessment technique was the pattern-based accuracy assessment. The technique involves polygon-based fuzzy local matching. Three comparison maps showing local matching indices were obtained and used to compute the global matching index (g) for LULC maps of each feature set combination. The g values were g(RGB) (0.745), g(RGB+MNDVI) (0.745), and g(RGB+MNDVI+Gabor) (0.765) for comparison maps. Finally, based on accuracy assessment metrics, the study area was successfully classified and tea plantation features were extracted with high accuracy.

Evaluation of urban heat island effect in Turkey

Recently, the rate of urbanisation has accelerated due to increasing population density which causes unexpected environmental disturbances and problems. One of the major problems encountered to date is the change in the land use/cover (LULC) structure. Increasing the impervious surface cover has changed microclimatic properties of urbanised areas by altering their thermal characteristics. One of the most important problems facing urban planning today is the phenomena known as the urban heat island (UHI), which is largely due to the changing the character of LULC. In this study, to create a national picture of the UHI structure in Turkey, seven cities, namely Istanbul, Bursa, Ankara, Izmir, Gaziantep, Erzurum and Trabzon, each located in different climatic regions of Turkey, were investigated. The Gaussian fitting technique was applied to characterise the UHI effect in the seven cities in the study. An original contribution of the current study was that the rural reference temperature surface was automatically determined by a proposed algorithm including the automatic masking of input data, as well as the application of iterative Gaussian low-pass filtering during the fitting procedure. Within this context, the daytime and nighttime surface urban heat island (SUHI) effect was modelled and temporally analysed from 1984 to 2011 for all the sub-regions using remote sensing techniques. Furthermore, atmospheric UHI was also investigated using the mobile transect method. The findings from this study suggest that UHI is a major environmental problem in urbanised areas, both atmospheric UHI and SUHI were detected in all cities in the study area, and this problem was found to have rapidly increased from 1984 to 2011. Finally, as inferred from the multiple regression results, it can be concluded that the UHI problem in Turkey might have resulted from the altered LULC structure, as well as anthropogenic pressure on and interference in city planning geometries.