**5.1 Physical data integration**

Land physical dynamics such as elevation is vital physical input to LUC mapping. Digital elevation models (DEM) can be derived from stereo image pairs (e.g. ASTER) or radar (e.g. SRTM). Especially, vegetation formation and species vary according to elevation, aspect and climate. Using these ancillary data may improve accuracy of LUC maps (Coops et al. 2006, Şatr 2006). It is also possible to integrate soil characteristics into LUC mapping, because vegetation distribution and plant species are strongly dependent on soil depth, texture and moisture.

DEM was integrated to the DT and MLC classification in Eastern Mediterranean area discussed in section 4. Overall accuracy of the classification was increased approximately 4% and particularly bulrush, sand dunes and forestlands classified more accurately using DT. If topography vary in a study area, integrating the DEM may improve the LUC mapping accuracy. However, MLC classification overall accuracy was stable with and without DEM information. Most of the ancillary data increased the accuracy when using non-parametric techniques because parametric techniques like MLC uses the statistical equation to calculate distance of each LUC signature mean to the unknown pixel. However, DT creates rules based on the training data ranges, including elevation and spectral wavebands.

#### **5.2 Surface texture data**

Some of the variables can be produced using image wavebands such as surface texture and vegetation metrics. Surface textures are also used widely in LUC mapping. Many texture measures have been developed (Haralick et al. 1973, Kashyap et al. 1982, He and Wang 1990, Unser 1995, Emerson et al. 1999) and have been used for image classifications (Franklin and Peddle 1989, Narasimha Rao et al. 2002, Berberoglu et. al. 2000). Franklin and Peddle (1990) found that textures based on a grey-level co-occurrence matrix (GLCM) and spectral features of a SPOT HRV image improved the overall classification accuracy. Gong et al. (1992) compared GLCM, simple statistical transformations (SST), and texture spectrum (TS) approaches with SPOT HRV data, and found that some textures derived from GLCM and SST improved urban classification accuracy. Shaban and Dikshit (2001) investigated GLCM, grey-level difference histogram (GLDH), and sum and difference histogram (SADH) textures from SPOT spectral data in an Indian urban environment, and found that a combination of texture and spectral features improved the classification accuracy. The results based solely on spectral features increased about 9% to 17% with an addition of one or two texture measures. Furthermore, contrast, entropy, variance, and inverse difference

Land Use/Cover Classification Techniques

wavebands enhanced accuracy to 0.67.

**6. Conclusions** 

in change detection studies.

noise in an area (Figure 15).

and remotely sensed data.

techniques like RT or ANN are suggested.

Using Optical Remotely Sensed Data in Landscape Planning 49

percentage, correlation coefficiency obtained as 0.58. Vegetation metrics and MERIS

This chapter has demonstrated various issues in LUC classification including, ability of optical remotely sensed data, different classifiers, training data size and ancillary data in the example of Eastern Mediterranean region. Parametric, non-parametric hard and soft LUC

Selection of a classification scheme and the optical data are vital for a reliable result in LUC mapping. Remotely sensed data must be defined according to the mapping scale and study purpose. LUC classification scheme and level should be defined based on optical data ability such as spatial and spectral resolution. Image pre-processing such as, geometric registration, atmospheric correction, geometric correction and radiometric calibration are essential parts

Training data size, quality and mapping details are also important to select suitable classifier for LUC mapping. MLC, LDA, and DT techniques are useful for hard classification outputs. On the other hand, to derive a continuous map like cover percentage of each LUC or probability of each LUC needs soft classifiers such as RT and LMM. Training data size and quality affect the classification accuracy and classifier selection. Although model based classifiers has potential when strong training data set was used. In this case, data dependent classifiers can be chosen for better accurate LUC map. Linear techniques are suitable if mixture degree is small in a pixel. LMM is ideal if there are enough training data and pure pixel for each LUC. However, if training pixel size and pure pixels are weak, non-linear

Hard classifiers were performed inaccurately with coarse spatial resolution images (e.g. MODIS, MERIS, NOAA, SPOTveg) because of mixed pixel problem. Fuzzy classifiers are reduced this problem and provided better accuracy than hard classification. Hard pixel based mapping techniques were successful using medium spatial resolution data (e.g. Landsat TM/ETM, Aster and Alos AVNIR) in regional and local scale, however, for the specific purposes like detailed crop pattern mapping or urban pattern mapping, object based classification approach was recommended for more reliable LUC mapping. Object based classification is appropriate when using very high spatial resolution data (e.g. rapid eye, Ikonos, Aerial photos, Geoeye). In segmentation stage of object based classification, pixels were merged to create each segment or object according to spectral, structural and textural similarities. This method is tolerated the pixel misclassification if there is a pixel

In this chapter ancillary data integration were also discussed using several data from satellite remote sensing sensors. Three types of ancillary data were integrated to the DT hard classifier. DEM resulted the largest improvement in overall classification accuracy among others. Surface texture and vegetation indices were improved the accuracy of specific land cover types. When all data used together, overall classification accuracy were reduced. Additionally, more ancillary data is not important to enhance classification accuracy. Success of the ancillary data varies based on classification target, study area characteristics

mapping techniques in local scale were assessed. Main findings of this chapter are:

moment provided larger accuracy and the most appropriate window size was 7X7 and 9X9. Multiscale texture measures should be incorporated with original spectral wavebands to improve classification accuracy (Shaban and Dikshit 2001, Podest and Saatchi 2002, Butusov 2003). Recently, the geostatistic-based texture measures were found to provide better classification accuracy than using the GLCM-based textures (Berberoglu et al. 2000). For a specific study, it is often difficult to identify a suitable texture because texture varies with the characteristics of the landscape under investigation and the image data used. Identification of suitable textures involves determination of texture measure, image band, the size of moving window, and other parameters (Chen et al. 2004). The difficulty in identifying suitable textures and the computation cost for calculating textures limit the extensive use of textures in image classification, especially in a large area (Lu and Weng 2007).

To test the texture data on classification accuracy, five different GLCM was derived such as, variance, contrast, dissimilarity, homogeneity, entropy. These measurements incorporated with Landsat spectral wavebands in Eastern Mediterranean region. Overall accuracy was unchanged, however accuracies of settlement and agricultural land classes were increased 4- 5%. However, accuracy of bareground and sand dunes decreased using DT classifier.

#### **5.3 Vegetation indices**

Vegetation metrics are another ancillary data for more accurate LUC mapping. Deriving the metrics is dependent on the spectral resolution of an optical image. A vegetation index derived from combination of image wavebands. The most used vegetation indices are normalized difference vegetation index (NDVI), soil adjusted vegetation index (SAVI), normalized difference water index (NDWI), green vegetation index (GVI) and perpendicular vegetation index (PVI) at the literature. Vegetation indices indicate health condition (NDVI) and water content (NDWI) of the vegetation canopy. There are many textbooks and papers about calculation of vegetation indices. These indices provide extra information for LUC classification to discriminate subtle classes.

For instead, NDVI calculated using red and near infrared band (NIR) combination as shown in following equation (Rouse et al 1974);

$$\text{NIR} \text{ - RED} \mid \text{NIR} \text{ + RED} \tag{5}$$

NDVI data was included to Landsat TM data to show the effect of a vegetation index on LUC mapping. Overall accuracy was unchanged significantly, but sand dunes, baregrounds, deciduous classes were classified more accurately.

Besides, there are some indices specifically designed for sensors. For example; Envisat MERIS data has own chlorophyll index called MERIS terrestrial chlorophyll index (MTCI). Additionally, vegetation metrics such as fraction of photosynthetically active radiation (fPAR), leaf area index (LAI) and fraction of green vegetation covering a unit area of horizontal soil (fCover) can be obtained using specific equations from MERIS data. Berberoglu et al. (2009) used this vegetation metrics to improve RT soft classification accuracy using MERIS data. When only MERIS wavebands used to determine the tree cover percentage, correlation coefficiency obtained as 0.58. Vegetation metrics and MERIS wavebands enhanced accuracy to 0.67.
