Bahareh Kalantar

Assessment of the effects of training data selection on the landslide susceptibility mapping: a comparison between support vector machine (SVM), logistic regression (LR) and artificial neural networks (ANN)

ABSTRACT Landslide is a natural hazard that results in many economic damages and human losses every year. Numerous researchers have studied landslide susceptibility mapping (LSM), each attempting to improve the accuracy of the final outputs. However, few studies have been published on the training data selection effects on the LSM. Thus, this study assesses the training landslides random selection effects on support vector machine (SVM) accuracy, logistic regression (LR) and artificial neural networks (ANN) models for LSM in a catchment at the Dodangeh watershed, Mazandaran province, Iran. A 160 landslide locations inventory was collected by Geological Survey of Iran for this investigation. Different methods were implemented to define the landslide locations, such as inventory reports, satellite images and field survey. Moreover, 14 landslide conditioning factors were considered in the analysis of landslide susceptibility. These factors include curvature, plan curvature, profile curvature, altitude, slope angle, slope aspect, distance to faults, distance to stream, topographic wetness index, stream power index, terrain roughness index, sediment transport index, lithology and land use. The results show that the random landslide training data selection affected the parameter estimations of the SVM, LR and ANN algorithms. The results also show that the training samples selection had an effect on the accuracy of the susceptibility model because landslide conditioning factors vary according to the geographic locations in the study area. The LR model was found to be less sensitive than the SVM and ANN models to the training samples selection. Validation results showed that SVM and LR models outperformed the ANN model for all scenarios. The average overall accuracy of LR, SVM and ANN models are 81.42%, 79.82% and 70.2%, respectively.

Groundwater potential mapping using C5.0, random forest, and multivariate adaptive regression spline models in GIS

Ever increasing demand for water resources for different purposes makes it essential to have better understanding and knowledge about water resources. As known, groundwater resources are one of the main water resources especially in countries with arid climatic condition. Thus, this study seeks to provide groundwater potential maps (GPMs) employing new algorithms. Accordingly, this study aims to validate the performance of C5.0, random forest (RF), and multivariate adaptive regression splines (MARS) algorithms for generating GPMs in the eastern part of Mashhad Plain, Iran. For this purpose, a dataset was produced consisting of spring locations as indicator and groundwater-conditioning factors (GCFs) as input. In this research, 13 GCFs were selected including altitude, slope aspect, slope angle, plan curvature, profile curvature, topographic wetness index (TWI), slope length, distance from rivers and faults, rivers and faults density, land use, and lithology. The mentioned dataset was divided into two classes of training and validation with 70 and 30% of the springs, respectively. Then, C5.0, RF, and MARS algorithms were employed using R statistical software, and the final values were transformed into GPMs. Finally, two evaluation criteria including Kappa and area under receiver operating characteristics curve (AUC-ROC) were calculated. According to the findings of this research, MARS had the best performance with AUC-ROC of 84.2%, followed by RF and C5.0 algorithms with AUC-ROC values of 79.7 and 77.3%, respectively. The results indicated that AUC-ROC values for the employed models are more than 70% which shows their acceptable performance. As a conclusion, the produced methodology could be used in other geographical areas. GPMs could be used by water resource managers and related organizations to accelerate and facilitate water resource exploitation.

Improving the accuracy of landslide susceptibility model using a novel region-partitioning approach

Landslide is a natural disaster that threatens human lives and properties worldwide. Numerous have been conducted on landslide susceptibility mapping (LSM), in which each has attempted to improve the accuracy of final outputs. This study presents a novel region-partitioning approach for LSM to understand the effects of partitioning a focused region into smaller areas on the prediction accuracy of common regression models. Results showed that the partitioning of the study area into two regions using the proposed method improved the prediction rate from 0.77 to 0.85 when support vector machine was used, and from 0.87 to 0.88 when logistic regression model was utilized. The spatial agreements of the models were also improved after partitioning the area into two regions based on Shannon entropy equations. Our comparative study indicated that the proposed method outperformed the geographically weighted regression model that considered the spatial variations in landslide samples. Overall, the main advantages of the proposed method are improved accuracy and the reduction of the effects of spatial variations exhibited in landslide-conditioning factors.

Oil Palm Counting and Age Estimation from WorldView-3 Imagery and LiDAR Data Using an Integrated OBIA Height Model and Regression Analysis

The current study proposes a new method for oil palm age estimation and counting from Worldview-3 satellite image and light detection and range (LiDAR) airborne imagery. A support vector machine algorithm (SVM) of object-based image analysis (OBIA) was implemented for oil palm counting. The sensitivity analysis was conducted on four SVM kernel types with associated segmentation parameters to obtain the optimal crown coverage delineation. Extracting tree’s crown was integrated with height model and multiregression methods to accurately estimate the age of trees. The multiregression model with multikernel sizes was examined to achieve the most optimized model for age estimation. Applied models were trained and examined over five different oil palm plantations. The results of oil palm counting had an overall accuracy of 98.80%, while the overall accuracy of age estimation showed 84.91%, over all blocks. The relationship between tree’s height and age was significant which supports the polynomial regression function (PRF) model with a kernel size for under 10–12-year-old oil palm trees, while exponential regression function (ERF) is more fitted for older trees (i.e., 22 years old). Overall, recent remote sensing dataset and machine learning techniques are useful in monitoring and detecting oil palm plantation to maximize productivity.

Performance Evaluation and Sensitivity Analysis of Expert-Based, Statistical, Machine Learning, and Hybrid Models for Producing Landslide Susceptibility Maps

Landslides are active natural hazards in many areas of the world. Landslides damage and destroy man-made structures and landforms, causing many deaths and injuries every year.

Drone-based land-cover mapping using a fuzzy unordered rule induction algorithm integrated into object-based image analysis

ABSTRACT Land-cover maps provide essential data for a wide range of practical and small-scale applications. A number of data sources appropriate for land-cover extraction are available. Among these, images captured using unmanned aerial vehicles (UAVs) are low cost, have very high resolution, and can be acquired at any time with few restrictions. Over the past two decades, various classification techniques have been developed to extract land-cover features from UAV images, and object-based image analysis (OBIA) is the preferred technique based on the recent literature. This study presents a novel method that integrates the fuzzy unordered rule induction algorithm (FURIA) into OBIA to achieve accurate land-cover extraction from UAV images. The images were segmented using a multiresolution segmentation algorithm with an optimized scale parameter. The scale parameter was optimized using a novel approach that integrated feature space optimization into the plateau objective function. During the classification stage, significant features were selected via random forest, and rule sets were developed using FURIA. For comparison, result of the proposed approach was compared with those of decision tree (DT) rules and the Support Vector Machine (SVM) classification method. The results of this study indicate that the proposed method outperforms DT and SVM with an overall accuracy of 91.23%. A transferability evaluation showed that FURIA achieved accurate classification results on different UAV image subsets captured at different times. The findings suggest that fuzzy rules are more appropriate than conventional crisp rules for land-cover extraction from UAV images.

Multiple Moving Object Detection From UAV Videos Using Trajectories of Matched Regional Adjacency Graphs

Image registration has been long used as a basis for the detection of moving objects. Registration techniques attempt to discover correspondences between consecutive frame pairs based on image appearances under rigid and affine transformations. However, spatial information is often ignored, and different motions from multiple moving objects cannot be efficiently modeled. Moreover, image registration is not well suited to handle occlusion that can result in potential object misses. This paper proposes a novel approach to address these problems. First, segmented video frames from unmanned aerial vehicle captured video sequences are represented using region adjacency graphs of visual appearance and geometric properties. Correspondence matching (for visible and occluded regions) is then performed between graph sequences by using multigraph matching. After matching, region labeling is achieved by a proposed graph coloring algorithm which assigns a background or foreground label to the respective region. The intuition of the algorithm is that background scene and foreground moving objects exhibit different motion characteristics in a sequence, and hence, their spatial distances are expected to be varying with time. Experiments conducted on several DARPA VIVID video sequences as well as self-captured videos show that the proposed method is robust to unknown transformations, with significant improvements in overall precision and recall compared to existing works.

Optimized Rule-Based Flood Mapping Technique Using Multitemporal RADARSAT-2 Images in the Tropical Region

Flood is one of the most common natural disasters in Malaysia. Preparing an accurate flood inventory map is the basic step in flood risk management. Flood detection is a complex process because of the limitation of methodological approaches and cloud coverage over tropical areas. An efficient approach is proposed to identify flooded areas using multitemporal RADARSAT-2 imageries. First, multispectral Landsat image was used to extract and subtract permanent water bodies, and this image was later utilized to extract the same information from multitemporal RADARSAT-2 imageries. Next, water bodies during a flood event were extracted from RADARSAT-2 images. Permanent water bodies, shadow, and paddy were detected from synthetic aperture radar (SAR) images by analyzing their temporal backscattering values. During feature extraction, rule-based object-oriented technique was applied to classify both SAR and Landsat images. Image segmentation during object-based analysis was performed to distinguish the boundaries of various dimensions and scales of objects. Moreover, a Taguchi-based method was employed to optimize the segmentation parameters. After segmentation, the rules were defined and images were classified to produce an accurate flood inventory map for the 2014 Kelantan flood. A confusion matrix was generated to evaluate the performance of the classification method. The overall accuracy of 86.16% was achieved for RADARSAT-2 using rule-based classification and optimization technique. The resulting flood inventory map using the proposed approach supported the efficiency of the proposed methodology.

Single image dehazing using second-generation wavelet transforms and the mean vector L2-norm

Single image dehazing remains a seminal area of study in computer vision. Despite the huge number of studies that have addressed haze in a single image, the restoration images have not yet reached a satisfactory level in terms of visual appearance and time complexity burden. In this paper, a novel single image haze removal technique based on edge and fine texture preserving is introduced. To achieve better visual quality from the hazy image, the proposed technique uses mean vector L2-norm that is core of window sampling to estimate the transmission map. Then, second-generation wavelet transform filter is utilized in order to enhance the estimated transmission map of the resulted image. The usage of second-generation wavelet filter in this paper is due to its effectiveness while achieving fast speed. Experimental outcomes present that the proposed technique achieves competitive achievements in comparison with up-to-date state-of-the-art image dehazing methods in both quantitative and qualitative assessments, i.e., visual effects, universality, and computational processing speed.

Debris Flow Susceptibility Assessment Using Airborne Laser Scanning Data

Debris flows and related landslide failure phenomena occur in many mountainous areas worldwide and pose significant hazards to settlements, human lives, and transportation corridors. Debris flows occur on different terrains where sufficient debris materials are available and the angle of slope is steep enough. Flow behavior is of different types, namely, confined, unconfined, and transition.