Suha Berberoglu

The integration of spectral and textural information using neural networks for land cover mapping in the Mediterranean

The aim of this study was to develop an efficient and accurate procedure for classifying Mediterranean land cover with remotely sensed data. Combinations of artificial neural networks (ANN) and texture analysis on a per-field basis were used to classify a Landsat Thematic Mapper image of the Cukurova Deltas, Turkey, into eight land cover classes. This study integrated spectral information with measures of texture, in the form of the variance and the variogram. The accuracy of the ANN was greater than that of maximum likelihood (ML) when using spectral data alone and when using spectral and textural data. The use of texture measures through the per-pixel and per-field majority rule approaches were found to reduce classification accuracy because the field boundaries were enlarged and so overwhelmed the measures of texture. In contrast, the per-field approach (where the field was specified prior to analysis) combined with texture information increased significantly classification accuracy. However, the accuracy decreased as the variogram lag increased. The accuracy with which land cover could be classified in this region was maximised at 89% by using a per-field, ANN approach in which semivariance at a lag of 1 pixel was incorporated as textural information. This is 15% greater than the accuracy achieved using a standard per-pixel ML classification. The primary limitation of the use of the per-field approach was noted to be the need for prior knowledge of field boundaries which may be resolved using existing data or through some form of edge-detection routine.

ASSESSING DIFFERENT REMOTE SENSING TECHNIQUES TO DETECT LAND USE/COVER CHANGES IN THE EASTERN MEDITERRANEAN

This paper describes different change detection techniques, including image differencing, image rationing, image regression and change vector analysis (CVA) to assess their effectiveness for detecting land use/cover change in a Mediterranean environment. Three Landsat TM scenes recorded on 7 July 1985, 27 July 1993 and 21 July 2005 were used to minimize change detection error introduced by seasonal differences. Images were geometrically, atmospherically and radiometrically corrected. The four change detection techniques were applied and an object-based supervised classification was used as a crossclassification to determine ‘from–to’ change which enabled assessment of the four techniques. The change vector analysis resulted in the largest overall accuracy of 75.25 and 75.55% for the 1985–1993 and 1993–2005 image pairs, respectively. The ratio yielded the least accurate results with an overall accuracy of 59.10 and 61.05% for the 1985–1993 and 1993–2005 image pairs, respectively. Different change detection algorithms have their own merits and advantages. However, the change vector analysis change detection technique was the most accurate model for handling the variability present in Mediterranean land use/cover.

Texture classification of Mediterranean land cover

Maximum likelihood (ML) and artificial neural network (ANN) classifiers were applied to three Landsat Thematic Mapper (TM) image sub-scenes (termed urban, agricultural and semi-natural) of Cukurova, Turkey. Inputs to the classifications comprised (i) spectral data and (ii) spectral data in combination with texture measures derived on a per-pixel basis. The texture measures used were: the standard deviation and variance and statistics derived from the co-occurrence matrix and the variogram. The addition of texture measures increased classification accuracy for the urban sub-scene but decreased classification accuracy for agricultural and semi-natural sub-scenes. Classification accuracy was dependent on the nature of the spatial variation in the image sub-scene and, in particular, the relation between the frequency of spatial variation and the spatial resolution of the imagery. For Mediterranean land, texture classification applied to Landsat TM imagery may be appropriate for the classification of urban areas only.

A comparison of texture measures for the per-field classification of Mediterranean land cover

Land cover of a Mediterranean region was classified within an artificial neural network (ANN) on a per-field basis using Landsat Thematic Mapper (TM) imagery. In addition to spectral information, the classifier used geostatistical structure functions and texture measures extracted from the co-occurrence matrix. Geostatistical measures of texture resulted in a more accurate classification of Mediterranean land cover than statistics derived from the co-occurrence matrix. The primary advantage of geostatistical measures was their robustness over a wide range of land cover types, field sizes and forms of class mixing. Spectral information and the variogram (geostatistical texture measure) resulted in the highest overall classification accuracies.

Mapping and monitoring of coastal wetlands of Çukurova Delta in the Eastern Mediterranean region

The aim of this research was to link vegetation characteristics, such as spatial and temporal distribution, and environmental variables, with land cover information derived from remotely sensed satellite images of the Eastern Mediterranean coastal wetlands of Turkey. The research method was based on (i) recording land cover characteristics by means of a vegetation indicator, and (ii) classifying and mapping coastal wetlands utilizing a Landsat Thematic Mapper (TM) image of Çukurova Deltas in Turkey. Vegetation characteristics of various habitats, such as sand dunes, salt marshes, salty plains and afforestation areas, were identified by field surveys. A Landsat TM image of 4 July 1993 was pre-processed and then classified using the Maximum Likelihood (ML) algorithm and Artificial Neural Networks (ANN). As a result of this supervised classification, the land cover types were classified with a largest accuracy of 90.2% by ANN. The classified satellite sensor imagery was linked to vegetation and bird census data, which were available through literature in a Geographical Information System (GIS) environment to determine the spatial distribution of plant and bird biodiversity in this coastal wetland. The resulting data provide an important baseline for further investigations such as monitoring, change detections and designing conservation policies in this coastal ecosystem.

The impact of historical exclusion on the calibration of the SLEUTH urban growth model

Abstract This paper aims to emphasize the importance of the calibration process in urban growth modeling studies. The application of cellular automata (CA) in urban modeling can give insights into a wide variety of urban phenomena. The SLEUTH model, being as a well-tested CA, was utilized. Calibration data for the model were acquired from different sources of remotely sensed data recorded in 1967, 1977, 1987, 1998 and 2007. In this context three different excluded maps representing different scenarios were utilized during the calibration process in order to analyze the effects of different policies on urban growth. Each calibration scenario yielded its own parameter values. Thirteen calibration metrics for each scenario were derived. Integrating different exclusion layers to the beginning of the calibration process has reduced the number of possible growth patterns. The overall growth characteristics of Adana were similar for all calibration results and defined as organic growth except for the fact that the spatial allocation and the amount of potential urban pixels were different.

Mapping percentage tree cover from Envisat MERIS data using linear and nonlinear techniques

The aim of this study was to predict percentage tree cover from Envisat Medium Resolution Imaging Spectrometer (MERIS) imagery with a spatial resolution of 300 m by comparing four common models: a multiple linear regression (MLR) model, a linear mixture model (LMM), an artificial neural network (ANN) model and a regression tree (RT) model. The training data set was derived from a fine spatial resolution land cover classification of IKONOS imagery. Specifically, this classification was aggregated to predict percentage tree cover at the MERIS spatial resolution. The predictor variables included the MERIS wavebands plus biophysical variables (the normalized difference vegetation index (NDVI), leaf area index (LAI), fraction of photosynthetically active radiation (fPAR), fraction of green vegetation covering a unit area of horizontal soil (fCover) and MERIS terrestrial chlorophyll index (MTCI)) estimated from the MERIS data. An RT algorithm was the most accurate model to predict percentage tree cover based on the Envisat MERIS bands and vegetation biophysical variables. This study showed that Envisat MERIS data can be used to predict percentage tree cover with considerable spatial detail. Inclusion of the biophysical variables led to greater accuracy in predicting percentage tree cover. This finer-scale depiction should be useful for environmental monitoring purposes at the regional scale.

Modeling Potential Distribution and Carbon Dynamics of Natural Terrestrial Ecosystems: A Case Study of Turkey

We derived a simple model that relates the classification of biogeoclimate zones, (co)existence and fractional coverage of plant functional types (PFTs), and patterns of ecosystem carbon (C) stocks to long-term average values of biogeoclimatic indices in a time- and space-varying fashion from climate–vegetation equilibrium models. Proposed Dynamic Ecosystem Classification and Productivity (DECP) model is based on the spatial interpolation of annual biogeoclimatic variables through multiple linear regression (MLR) models and inverse distance weighting (IDW) and was applied to the entire Turkey of 780,595 km2 on a 500 m × 500 m grid resolution. Estimated total net primary production (TNPP) values of mutually exclusive PFTs ranged from 108 ± 26 to 891 ± 207 Tg C yr-1 under the optimal conditions and from 16 ± 7 to 58 ± 23 Tg C yr-1 under the growth-limiting conditions for all the natural ecosystems in Turkey. Total NPP values of coexisting PFTs ranged from 178 ± 36 to 1231 ± 253 Tg C yr-1 under the optimal conditions and from 23 ± 8 to 92 ± 31 Tg C yr-1 under the growth-limiting conditions. The national steady state soil organic carbon (SOC) storage in the surface one meter of soil was estimated to range from 7.5 ± 1.8 to 36.7 ± 7.8 Pg C yr-1 under the optimal conditions and from 1.3 ± 0.7 to 5.8 ± 2.6 Pg C yr-1 under the limiting conditions, with the national range of 1.3 to 36.7 Pg C elucidating 0.1% and 2.8% of the global SOC value (1272.4 Pg C), respectively. Our comparisons with literature compilations indicate that estimated patterns of biogeoclimate zones, PFTs, TNPP and SOC storage by the DECP model agree reasonably well with measurements from field and remotely sensed data.

Mapping regional forest fire probability using artificial neural network model in a Mediterranean forest ecosystem

ABSTRACT Forest fires are one of the most important factors in environmental risk assessment and it is the main cause of forest destruction in the Mediterranean region. Forestlands have a number of known benefits such as decreasing soil erosion, containing wild life habitats, etc. Additionally, forests are also important player in carbon cycle and decreasing the climate change impacts. This paper discusses forest fire probability mapping of a Mediterranean forestland using a multiple data assessment technique. An artificial neural network (ANN) method was used to map forest fire probability in Upper Seyhan Basin (USB) in Turkey. Multi-layer perceptron (MLP) approach based on back propagation algorithm was applied in respect to physical, anthropogenic, climate and fire occurrence datasets. Result was validated using relative operating characteristic (ROC) analysis. Coefficient of accuracy of the MLP was 0.83. Landscape features input to the model were assessed statistically to identify the most descriptive factors on forest fire probability mapping using the Pearson correlation coefficient. Landscape features like elevation (R = −0.43), tree cover (R = 0.93) and temperature (R = 0.42) were strongly correlated with forest fire probability in the USB region.

Modeling Forest Productivity Using Envisat MERIS Data

The aim of this study was to derive land cover products with a 300-m pixel resolution of Envisat MERIS (Medium Resolution Imaging Spectrometer) to quantify net primary productivity (NPP) of conifer forests of Taurus Mountain range along the Eastern Mediterranean coast of Turkey. The Carnegie-Ames-Stanford approach (CASA) was used to predict annual and monthly regional NPP as modified by temperature, precipitation, solar radiation, soil texture, fractional tree cover, land cover type, and normalized difference vegetation index (NDVI). Fractional tree cover was estimated using continuous training data and multi-temporal metrics of 47 Envisat MERIS images of March 2003 to September 2005 and was derived by aggregating tree cover estimates made from high-resolution IKONOS imagery to coarser Landsat ETM imagery. A regression tree algorithm was used to estimate response variables of fractional tree cover based on the multi-temporal metrics. This study showed that Envisat MERIS data yield a greater spatial detail in the quantification of NPP over a topographically complex terrain at the regional scale than those used at the global scale such as AVHRR.