Dimensionality Reduction and Classification of Hyperspectral Images Using Object-Based Image Analysis

Object-based image analysis (OBIA) has attained great importance for the delineation of landscape features, particularly with the accessibility to satellite images with high spatial resolution acquired by recent sensors. Statistical parametric classifiers have become ineffective mainly due to their assumption of normal distribution, vast increase in the dimensions of the data and availability of limited ground sample data. Despite pixel-based approaches, OBIA takes semantic information of extracted image objects into consideration, and thus provides more comprehensive image analysis. In this study, Indian Pines hyperspectral data set, which was recorded by the AVIRIS hyperspectral sensor, was used to analyse the effects of high dimensional data with limited ground reference data. To avoid the dimensionality curse, principal component analysis (PCA) and feature selection based on Jeffries–Matusita (JM) distance were utilized. First 19 principal components representing 98.5% of the image were selected using the PCA technique whilst 30 spectral bands of the image were determined using JM distance. Nearest neighbour (NN) and random forest (RF) classifiers were employed to test the performances of pixel- and object-based classification using conventional accuracy metrics. It was found that object-based approach outperformed the traditional pixel-based approach for all cases (up to 18% improvement). Also, the RF classifier produced significantly more accurate results (up to 10%) than the NN classifier.     

The aftermath of 2011 Van earthquakes: evaluation of strong motion, geotechnical and structural issues

October 23rd, 2011 M _L 6.7 (M _w 7.2 KOERI) Tabanli-Van Earthquake caused damage in a widespread area specifically in the settlement regions throughout the Lake Van. A number of 58 buildings totally collapsed during the shake with 52 of them however, reported to be in Ercis district. 17 days after this destructive event, another earthquake of M _L 5.6 hit the region again on the 9th of November having the epicentral location at Edremit district. The second earthquake mostly affected the central region of Van province with a number of 25 totally collapsed buildings and furthermore it significantly increased the existing structural damages. Strong motion records from both earthquakes and their impacts on structures as well as geotechnical issues are studied in this paper. Extensive liquefaction triggered lateral spread, landslide and slope failure cases were observed mainly at non-residential areas. Soil amplification is evaluated to be one of the main reasons for the heavy damage occurred in Ercis. Furthermore, site investigations and damage assessment performed after each earthquake proved that the observed damages are strongly correlated with insufficient qualities of structural materials, inadequate detailing and poor workmanship.     

Analytical investigation of the observed damage in an RC building after March 08, 2010 Kovancilar-Turkey earthquake

Although the M _w  = 6.1 Kovancilar-Turkey earthquake of March 8, 2010 had a moderate intensity with a recorded PGA of 0.07g, it caused heavy damages in 2870 residential buildings having traditional or masonry structural systems and 42 human loss. Damage has been reported to be particularly concentrated at Kovancilar and Palu counties of Elazig province. Five hours after this earthquake, an aftershock of M _L  = 5.6 with a PGA of 0.08g struck the same region, developing the existing damages in the structures. In order to investigate this significant amount of reported damages under the effect of such low ground shakings, our reconnaissance team arrived at the region and unexpectedly came across a two-story RC building settled on a slope in Yukari Demirci village, which suffered moderate damage during the shakes. The outline of this paper can be summarized as the presentation of the results of the investigations in the order of describing the overall observed damages within the region; evaluation of the recorded motions; the details of the field-work carried out for the two story RC building and the analytical estimation of the site-assessed damages by means of nonlinear dynamic analysis. Employing the gathered data, the building is analytically modeled as plane frames and analyses are performed under the effects of the processed earthquake records, which are applied to the structure one after another in the consistent directions due to the building location. It is shown herein that the structural elements remain in the elastic range subjected to the processed recorded motions; henceforth acceleration time histories are scaled step by step up to 0.40g and computations are repeated for each acceleration level. Comparison with the observed and the analytically obtained damages confirmed that approximately 0.30g of peak ground acceleration should have to be exposed during the earthquakes.     

Landslide susceptibility mapping using GIS-based multi-criteria decision analysis,support vector machines,and logistic regression

Identification of landslides and production of landslide susceptibility maps are crucial steps that can help planners, local administrations, and decision makers in disaster planning. Accuracy of the landslide susceptibility maps is important for reducing the losses of life and property. Models used for landslide susceptibility mapping require a combination of various factors describing features of the terrain and meteorological conditions. Many algorithms have been developed and applied in the literature to increase the accuracy of landslide susceptibility maps. In recent years, geographic information system-based multi-criteria decision analyses (MCDA) and support vector regression (SVR) have been successfully applied in the production of landslide susceptibility maps. In this study, the MCDA and SVR methods were employed to assess the shallow landslide susceptibility of Trabzon province (NE Turkey) using lithology, slope, land cover, aspect, topographic wetness index, drainage density, slope length, elevation, and distance to road as input data. Performances of the methods were compared with that of widely used logistic regression model using ROC and success rate curves. Results showed that the MCDA and SVR outperformed the conventional logistic regression method in the mapping of shallow landslides. Therefore, multi-criteria decision method and support vector regression were employed to determine potential landslide zones in the study area.     

Selection of Optimal Object Features in Object-Based Image Analysis Using Filter-Based Algorithms

With the increase in spatial resolution of recent sensors, object-based image analysis (OBIA) has gained importance for producing detailed land use maps. One of the main advantages of OBIA is that a variety of spectral, spatial and textural features can be extracted for the segmented image objects that are later utilized in classification. However, using a large number of features not only increases the required computational time, but also requires a large number of ground samples, which is unavailable in most cases. For these reasons, feature selection (FS) has become an important research topic for OBIA based classification studies. In this study, three filter-based FS algorithms namely, Chi square, information gain and ReliefF were applied to determine the most effective object features that ensure high separability among landscape features. For this purpose, importance degree (i.e. ranks) of 110 input object features were firstly estimated by the algorithms, and correlation-based merit function was then applied to determine optimum feature subset size. Multi-resolution segmentation algorithm was applied for segmenting a WorldView-2 image. Support vector machine, random forest and nearest neighbour classifiers were all utilized to classify segmented image objects using the selected object features. Results revealed that the FS algorithms were effective for selecting the most relevant features. Also, the classifiers produced the highest performances with 24 out of 110 features selected by the information gain (IG) algorithm. Particularly, the support vector machine classifier produced the highest overall accuracy (92.00%) with 24 selected features determined by the IG algorithm. A significant improvement of about 4% was achieved by applying FS procedures that was found statistically significant in terms of Wilcoxon signed-ranks test.     

Estimation of Earthquake Damage to Buried Pipelines Caused by Ground Shaking

One of the most critical lessons of the recent earthquakes is the need for seismic planning for lifelines, with appropriate supplies and back up systems for emergency repair and restoration. Seismic planning, however requires physical loss estimations before the earthquakes occur. Buried pipeline damage correlations are critical part of loss estimation procedures applied to lifelines for future earthquakes. We review the existing pipeline damage relationships only for ground shaking (transient ground deformations) in the light of recent developments and evaluate them with Denizli City, Turkey water supply system. Eight scenario earthquakes with four different earthquake magnitudes between M6 and M7 caused by two different fault ruptures (Pamukkale and Karakova-Akhan Faults) were used. Analyses were performed by using Geographical Information Systems (GIS). This high number of different scenario earthquakes made it possible to compare the pipeline damage relationships at different ground shaking levels. Pipeline damage estimations for Denizli City were calculated for each damage relationship and earthquake scenario. Relative effects of damage relationships and scenario earthquakes on the results were compared and discussed. The results were presented separately for brittle, ductile, and all pipelines. It was shown that the variation in ductile pipeline damage estimations by various relationships was higher than the variation in brittle pipeline damage estimations for a particular scenario earthquake.